{"_id":{"$oid":"5c48e7f8f5c47b65811b022d"},"provenance_domain":{"version":"1.0.5"}}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cee"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ntdata.stat.csv","filename":"human_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aaf75fb0565c84ba7fbf909d8aa7fa8c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.869598","modified":"2020-04-10T11:24:56.809163","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human EBI-UniProtKB NT file contains proteome data for human [taxid:9606] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000003"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.871660","modified":"2019-02-19T14:44:27.899703","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000005"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cec"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-23T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-23T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"056c3469a6d5a227ad06af9834ae0ce7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.867420","modified":"2020-06-24T16:09:37.059682","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-24T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000001"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cef"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_glycosyltransferase.stat.csv","filename":"human_protein_glycosyltransferase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a0c2fe0c7d6cec1c17504b9f8ec1fd2c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosyltransferases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.870634","modified":"2020-04-10T11:25:21.808965","version":"1.7.9"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycosyltransferases dataset contains list of human [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the human proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list.  For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000004"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf4"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.875847","modified":"2019-02-19T14:46:01.499854","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000009"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.874820","modified":"2019-02-19T14:45:28.514598","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000008"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.stat.csv","filename":"mouse_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5a7e273dc273d99fd35bf626e002f232","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.867420","modified":"2020-04-10T12:31:16.220600","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Proteome Masterlist dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000007"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.876875","modified":"2019-02-19T14:46:18.887967","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000010"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.877904","modified":"2019-02-19T14:46:36.830310","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000011"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5ced"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.stat.csv","filename":"human_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ece0a2e8c1a4d893223c2991355ac6b4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.868557","modified":"2020-04-10T11:24:41.558452","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Canonical (UniProtKB) Sequences dataset contains human [taxid:9606] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000002"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.880988","modified":"2019-02-19T14:47:39.354378","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000014"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cfc"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.884069","modified":"2019-02-19T14:48:14.596827","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000017"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cff"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.887148","modified":"2019-04-23T13:50:51.348591","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000020"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cfe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.886120","modified":"2019-02-19T14:48:24.630823","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000019"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2019-05.nt","filename":"uniprot-proteome-10090-mus-musculus-2019-05.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ntdata.stat.csv","filename":"mouse_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8043bed22878eb5bf4c3530fdb18c886","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.879959","modified":"2020-04-10T12:31:39.470342","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse EBI-UniProtKB NT file contains proteome data for mouse [taxid:10090] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000013"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.890267","modified":"2019-02-19T13:44:51.567646","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000023"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d03"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mutid-map.final.csv","filename":"mutid-map.final.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_somatic.csv","filename":"human_cancer_mutation_somatic.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.stat.csv","filename":"human_protein_mutation_cancer.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"3dfad7db0cc423ebf0c0b009a172b0c0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Cancer Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.891293","modified":"2020-04-10T11:26:06.487519","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","cancer mutations","BioMuta","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/mutid-map.final.csv","filename":"mutid-map.final.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_somatic.csv","filename":"human_cancer_mutation_somatic.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the mutation data from the BioMuta and maps the UniProtKB accession to the UniProtKB canonical accessions as per the criterias"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Cancer Mutation dataset contains human [taxid:9606] mutation data from BioMuta database (https://hive.biochemistry.gwu.edu/biomuta).","The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer.","BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and NCBI RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates.","The dataset is imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen. ","Note the mutation shown in GlyGen are annotated based on passing of one or more filter criterias.","Filter criteria 1 - Positive Patient's Frequency Ratio ≥ 1.0%","Filter criteria 2 - Presence of mutation in number of cancer types ≥ 3 cancer types","Filter criteria 3 - Positive Patient's count ≥ 10 patients","Filter criteria 4 - Mutation reported and annotated in number of databases","Filter criteria 5 - Mutation minned from the literature using literaure mining tools","If there is also a germline mutation reported in dbSNP, the rsid is also shown","These filter criteria annotations are shown on the front end under the column Annotation Name","Also if the same mutation in the same cancer type on a given protein is reported in ICGC and TCGA then mutations from TCGA are only shown.","When mutations from TCGA are not available but are present in ICGC for the same protein and cancer type, ICGC mutations are shown in GlyGen","Two different DO child terms are merged into one single entry showing the parent cancer DO term from the DO cancer slim.","On the GlyGen interface, in Mutations section the mutations that have passed highest number of filter criteria are displayed first irrespective of their amio acid positions. For eg. the mutation entry that has passed 5 filter criteria will be shown first."],"bco_id":"http://data.glygen.org/GLY_000024"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d00"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.stat.csv","filename":"human_protein_info_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1f43b0ab58887b615c2bc61a8e1069a0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2020-04-10T11:25:40.102630","version":"1.7.9"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Information (NCBI RefSeq) dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000021"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d01"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_refseq.stat.csv","filename":"mouse_protein_info_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e5d1a611f1c3ed99bcd61130906d45c5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-01-23T17:21:05.888176","modified":"2020-04-10T12:31:52.568731","version":"1.7.9"},"description_domain":{"keywords":["protein information","protein length","protein summary","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000022"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d04"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"uri":{"access_time":"2019-10-08T17:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycohydrolase.stat.csv","filename":"human_protein_glycohydrolase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4ac11e83b06052c5ac6de5f8dc2fed73","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycohydrolases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"}],"created":"2019-01-23T17:21:05.892318","modified":"2020-04-10T11:26:26.178942","version":"1.7.9"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycohydrolases dataset contains a list of human [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000025"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2019-05.nt","filename":"uniprot-proteome-10090-mus-musculus-2019-05.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.stat.csv","filename":"mouse_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1c5719d871c4e4fd2f109451d9f63f3e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.878935","modified":"2020-04-10T12:31:27.615543","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Canonical (UniProtKB) Sequences dataset contains mouse [taxid:10090] protein canonical fasta sequences from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000012"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d06"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.894406","modified":"2019-02-19T13:47:11.999143","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000027"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d07"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}},{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/reviewed/human_protein_expression_normal.stat.csv","filename":"human_protein_expression_normal.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1efe8db7d62a829cd6e766137b6b13fc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Normal Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Normal)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.895453","modified":"2020-04-11T11:24:57.144309","version":"1.7.9"},"description_domain":{"keywords":["normal gene expression","BioXpress","UBERON","tissue","Bgee"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_expression_normal.csv","filename":"human_protein_expression_normal.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/gene symbol to UniProtKB canonical expression"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Gene Expression (Normal) dataset contains the normal expression information of human [taxid:9606] genes from BioXpress database. The GlyGen Interface shows the normal gene expression information for select UBERON ids only which are mapped to corresponding DOIDs and have gene expression in cancer information for those DOID. For more gene expression information of other UBERON IDs (tissues) for a given gene, please refer to BioXpress - https://hive.biochemistry.gwu.edu/bioxpress. BioXpress is a gene/miRNA expression and disease association database with expression levels mapped to genes or miRNAs. The current version of BioXpress contains only genes associated with cancer. If you are using this dataset please give proper attribution to GlyGen and BioXpress"],"bco_id":"http://data.glygen.org/GLY_000028"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d08"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_cancer.csv"}},{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_expression_disease.csv","filename":"human_protein_expression_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_expression_disease.stat.csv","filename":"human_protein_expression_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b1e61f6ba1fc20d0f9513d37e20ecad3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cancer Gene Expression","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Gene Expression (Cancer)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.896478","modified":"2020-04-11T11:26:52.178903","version":"1.7.9"},"description_domain":{"keywords":["gene expression (cancer)","Disease Ontology","differential expression","BioXpress"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_normal.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_expression_cancer.csv","filename":"human_protein_expression_cancer.csv"}],"prerequisite":[],"description":"The script extracts the expression information and maps the UniProtKB accession/ gene name to UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Gene Expression (Cancer) dataset contains the gene expression information in cancers from BioXpress database. The GlyGen interface shows the gene expression (cancer) information for select cancer types/DOIDs. For more cancer types/DOIDs please refer - https://hive.biochemistry.gwu.edu/bioxpress. If you use this dataset please give proper attribution to BioXpress and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000029"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d09"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_protein_glycosyltransferase_2018_11.csv","filename":"mouse_protein_glycosyltransferase_2018_11.csv"}},{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"}},{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosyltransferase.stat.csv","filename":"mouse_protein_glycosyltransferase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"677db6a5dbc6afe9ed3f7920e37b1258","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosyltransferases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"}],"created":"2019-01-23T17:21:05.897519","modified":"2020-04-10T12:33:36.526794","version":"1.7.9"},"description_domain":{"keywords":["GT","gycosyltransferase","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycosyltransferases dataset contains a list of mouse [taxid:10090] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000030"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d05"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2019-10-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-08T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-08T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_glycohydrolase.stat.csv","filename":"mouse_protein_glycohydrolase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c9c083b64b3c9810cc593f7d645c3bfa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycohydrolases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"}],"created":"2019-01-23T17:21:05.893381","modified":"2020-04-10T12:33:07.345657","version":"1.7.9"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycohydrolases dataset contains a list of mouse [taxid:10090] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000026"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_altnames.stat.csv","filename":"human_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1f3c14c8ce84d4e8271b8fdb1cd661ec","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.898547","modified":"2020-04-10T11:26:42.330163","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000031"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.872734","modified":"2019-02-19T14:44:52.840281","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000006"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_altnames.stat.csv","filename":"mouse_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"07148459dad3f21f9d106898ebcd85a6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.899575","modified":"2020-04-10T12:33:53.049810","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000032"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_uniprotkb.stat.csv","filename":"human_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4e6bc5f06579c3260a9971039d9dec9d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.900608","modified":"2020-04-10T11:27:03.338813","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_uniprotkb.csv","filename":"human_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Information dataset contains human [taxid:9606] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000033"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_blacklisted_pmids_uniprotkb.csv","filename":"human_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_uniprotkb.stat.csv","filename":"human_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"13e0d42203b064a9437c918b99e13879","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.902655","modified":"2020-04-10T11:27:33.124175","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_blacklisted_pmids_uniprotkb.csv","filename":"human_protein_blacklisted_pmids_uniprotkb.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_uniprotkb.csv","filename":"human_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Citations dataset contains publication information for human [taxid:9606] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2wwwdata/compiled/human_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000035"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d10"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.904697","modified":"2019-02-19T13:51:17.764255","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000037"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uuniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv","filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_uniprotkb.stat.csv","filename":"mouse_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"13957f779dcf6a6e4a1209f45a5c911c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.903678","modified":"2020-04-10T12:34:26.812397","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv","filename":"mouse_protein_blacklisted_pmids_uniprotkb.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_uniprotkb.csv","filename":"mouse_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Citations dataset contains publication information for mouse [taxid:10090] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2wwwdata/compiled/mouse_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000036"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d12"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"91c807a63a15372f71ae5f4d8062db8a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.906744","modified":"2020-04-10T12:34:43.152869","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000039"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d11"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a2ce91e08341ce939e3713cebcd423f8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.905721","modified":"2020-04-10T11:27:49.618489","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycosylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000038"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_uniprotkb.stat.csv","filename":"mouse_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"390e096645ec7751561933b8a817404a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.901631","modified":"2020-04-10T12:34:07.793851","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_uniprotkb.csv","filename":"mouse_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Information dataset contains mouse [taxid:10090] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000034"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d17"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.911864","modified":"2019-02-19T13:51:50.903415","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000044"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d13"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"log","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.1.log"}},{"mediatype":"log","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.2.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.stats.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c1060ed9dcbf9ec0431a39a9ed2364a2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [Human proteins]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-01-23T17:21:05.907769","modified":"2020-05-01T15:20:46.152020","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.1.log"},{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"human_proteoform_glycosylation_sites_unicarbkb.2.log"},{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file ;for script:human_glycosylation_current.csv) was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)."],"bco_id":"http://data.glygen.org/GLY_000040"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d14"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.1.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.2.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.stats.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e2d9af2ba8bb48ff47e33a9e598754f7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Mouse proteins]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-01-23T17:21:05.908793","modified":"2020-05-01T15:21:10.499362","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.1.log"},{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.2.log"},{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000007)."],"bco_id":"http://data.glygen.org/GLY_000041"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d19"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.913960","modified":"2019-02-19T13:52:44.339053","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000046"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d18"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.912928","modified":"2019-02-19T13:52:21.318112","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000045"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d16"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details","filename":"N-linked-ARG-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details","filename":"O-linked-ASP-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details","filename":"O-linked-GLU-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details","filename":"O-linked-SER-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details","filename":"O-linked-THR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details","filename":"O-linked-TYR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.stat.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fb43b4f1d185a8a723b78e9c60116498","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (RCSB PDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"}],"created":"2019-01-23T17:21:05.910839","modified":"2020-04-10T12:35:07.324192","version":"1.7.9"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG","filename":"N-linked-ARG-details"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycosylation Sites (RCSB PDB) dataset contains mouse [taxid:10090] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"bco_id":"http://data.glygen.org/GLY_000043"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.914987","modified":"2019-02-19T13:53:09.793765","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000047"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d15"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details","filename":"N-linked-ARG-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details","filename":"O-linked-ASP-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details","filename":"O-linked-GLU-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details","filename":"O-linked-SER-details"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details","filename":"O-linked-THR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details","filename":"O-linked-TYR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.stat.csv","filename":"human_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"55a5f36a69687e38a8566ec81182bd31","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (RCSB PDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"}],"created":"2019-01-23T17:21:05.909814","modified":"2020-04-10T11:28:20.560562","version":"1.7.9"},"description_domain":{"keywords":["PDB","glycosylation sites","amino acid","amino acid chain"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN","filename":"N-linked-ASN-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP","filename":"O-linked-ASP-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR-details"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."},{"name":"","step_number":0,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycosylation Sites (RCSB PDB) dataset contains human [taxid:9606] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"bco_id":"http://data.glygen.org/GLY_000042"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.916014","modified":"2019-02-19T13:53:31.852084","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000048"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.917039","modified":"2019-02-19T13:53:59.703677","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000049"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.918065","modified":"2019-02-19T13:54:27.678707","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000050"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.919138","modified":"2019-02-19T13:55:00.615875","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000051"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.920168","modified":"2019-02-19T13:55:53.482435","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000052"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d22"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.923235","modified":"2019-02-19T14:01:46.926371","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000055"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d20"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.stat.csv","filename":"human_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c9ab039c01186f9f5bc5c78a2b0269be","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.921192","modified":"2020-04-10T11:28:58.535003","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Isoform sequences (UniProtKB) dataset contains human [taxid:9606] protein fasta sequences for the human isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000053"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d23"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.924264","modified":"2019-02-19T14:02:17.421800","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000056"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d21"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.stat.csv","filename":"mouse_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0a9d95f5c973a02fd744c85e5ca3e7cd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.921192","modified":"2020-04-10T12:35:29.710043","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Isoform sequences (UniProtKB) dataset contains mouse [taxid:10090] protein fasta sequences for the mouse isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000054"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d24"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.925284","modified":"2019-02-19T14:02:54.659774","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000057"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d25"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.926306","modified":"2019-02-19T14:03:25.953144","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000058"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d26"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.927329","modified":"2019-02-19T14:03:56.869077","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000059"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d27"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.txt ","filename":"gdb.txt "}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycomedb.txt","filename":"glycomedb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyco.txt","filename":"glyco.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.txt","filename":"pbch.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.txt","filename":"taxa.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uckb.txt","filename":"uckb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/humanprot.txt","filename":"humanprot.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/ucdb.txt","filename":"ucdb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.txt","filename":"pdb.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_idmapping.csv","filename":"human_glycan_idmapping.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_idmapping.stat.csv","filename":"human_glycan_idmapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"ID mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycome Accessions","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-04-12T13:49:54.302994","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan","Glycan"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/gdb.txt","filename":"gdb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycomedb.txt","filename":"glycomedb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyco.txt","filename":"glyco.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.txt","filename":"pbch.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.txt","filename":"taxa.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uckb.txt","filename":"uckb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/humanprot.txt","filename":"humanprot.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/ucdb.txt","filename":"ucdb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.txt","filename":"pdb.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/GLYDS00060","filename":"human_glycan_idmapping.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were seperated into individual 2 column input files (glytoucan_acc, database_id) if required and the individual input file(s) were processed based on the compiled glycan list using a python script[make-glycan-csv.py] to generate the final output csv file. a) If the glycan has source/taxonomy annotation[taxid:9606] in GlyTouCan b) If the glycan is listed on human[taxid:9606] glycan webpage at UniCarbKB c) If the glycan is listed on a human [taxid:9606] protein webpage at UniCarbKB d) If the glycan is synthesized by a human[taxid:9606] protein [http://data.glygen.org/GLYDS00064] e) If the glycan is known to be attached to a human[taxid:9606] protein [http://data.glygen.org/GLYDS00040] f) If the glycan is a motif of the glycan mentioned under criteria a-f "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan-csv.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions mapped to different databases."],"bco_id":"http://data.glygen.org/GLY_000060"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d28"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac.zip","filename":"iupac.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_sequences.txt","filename":"iupac_sequences.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs_sequences.txt","filename":"wurcs_sequences.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct_sequences.txt","filename":"glycoct_sequences.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences.csv","filename":"human_glycan_sequences.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences.stat.csv","filename":"human_glycan_sequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"sequences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Sequences","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-04-12T13:54:19.905657","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan","Glycan","IUPAC","WURCS","GlycoCT"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac.zip","filename":"iupac.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/glycoct.zip","filename":"glycoct.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_sequences.txt","filename":"iupac_sequences.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs_sequences.txt","filename":"wurcs_sequences.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct_sequences.txt","filename":"glycoct_sequences.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences.csv","filename":"human_glycan_sequences.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were separated into individual 2 column input files (glytoucan_acc,format_sequence) if required and the individual input file(s) were processed based on the compiled glycan list using a python script[make-glycan-csv.py] to generate the final output csv file. a) If the glycan has source/taxonomy annotation[taxid:9606] in GlyTouCan b) If the glycan is listed on human[taxid:9606] glycan webpage at UniCarbKB c) If the glycan is listed on a human [taxid:9606] protein webpage at UniCarbKB d) If the glycan is synthesized by a human[taxid:9606] protein [http://data.glygen.org/GLYDS00064] e) If the glycan is known to be attached to a human[taxid:9606] protein [http://data.glygen.org/GLYDS00040] f) If the glycan is a motif of the glycan mentioned under criteria a-f "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan-csv.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions and their sequences in IUPAC, WURCS, GlycoCT format."],"bco_id":"http://data.glygen.org/GLY_000061"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d29"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.txt ","filename":"gdb.txt "}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycomedb.txt","filename":"glycomedb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyco.txt","filename":"glyco.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.txt","filename":"pbch.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.txt","filename":"taxa.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uckb.txt","filename":"uckb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouseprot.txt","filename":"mouseprot.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/ucdb.txt","filename":"ucdb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.txt","filename":"pdb.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_idmapping.csv","filename":"mouse_glycan_idmapping.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_idmapping.stat.csv","filename":"mouse_glycan_idmapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"ID mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycome Accessions (Mouse GlyTouCan Ac. MasterList)","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-09-09T15:17:06.019606","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan","Glycan"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.txt","filename":"gdb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycomedb.txt","filename":"glycomedb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyco.txt","filename":"glyco.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.txt","filename":"pbch.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.txt","filename":"taxa.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uckb.txt","filename":"uckb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouseprot.txt","filename":"mouseprot.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/ucdb.txt","filename":"ucdb.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.txt","filename":"pdb.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_idmapping.csv","filename":"mouse_glycan_idmapping.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were seperated into individual 2 column input files (glytoucan_acc, database_id) if required and the individual input file(s) were processed based on the compiled glycan list using a python script[make-glycan-csv.py] to generate the final output csv file. The List of GlyTouCans(glycan list) is compiled when the GlyTouCan accession is observed underone or more following criteria:  a) If the glycan has source/taxonomy annotation[taxid:10090] in GlyTouCan b) If the glycan is listed on mouse[taxid:10090] glycan webpage at UniCarbKB c) If the glycan is listed on a mouse[taxid:10090] protein webpage at UniCarbKB d) If the glycan is synthesized by a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00065] e) If the glycan is known to be attached to a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00041] f) If the glycan is a motif of the glycan mentioned under criteria a-f "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan-csv.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions mapped to different databases."],"bco_id":"http://data.glygen.org/GLY_000062"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac.zip","filename":"iupac.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_sequences.txt","filename":"iupac_sequences.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs_sequences.txt","filename":"wurcs_sequences.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct_sequences.txt","filename":"glycoct_sequences.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences.csv","filename":"mouse_glycan_sequences.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences.stat.csv","filename":"mouse_glycan_sequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"sequences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Sequences","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-04-12T14:06:55.506211","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan","Glycan","IUPAC","WURCS","GlycoCT"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac.zip","filename":"iupac.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_sequences.txt","filename":"iupac_sequences.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs_sequences.txt","filename":"wurcs_sequences.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct_sequences.txt","filename":"glycoct_sequences.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences.csv","filename":"mouse_glycan_sequences.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were separated into individual 2 column input files (glytoucan_acc,format_sequence) if required and the individual input file(s) were processed based on the compiled glycan list using a python script[make-glycan-csv.py] to generate the final output csv file. The List of GlyTouCans(glycan list) is compiled when the GlyTouCan accession is observed underone or more following criteria:  a) If the glycan has source/taxonomy annotation[taxid:10090] in GlyTouCan b) If the glycan is listed on mouse[taxid:10090] glycan webpage at UniCarbKB c) If the glycan is listed on a mouse[taxid:10090] protein webpage at UniCarbKB d) If the glycan is synthesized by a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00065] e) If the glycan is known to be attached to a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00041] f) If the glycan is a motif of the glycan mentioned under criteria a-f "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions and their sequences in IUPAC, WURCS, GlycoCT format. "],"bco_id":"http://data.glygen.org/GLY_000063"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_classification.csv","filename":"human_glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_classification.stat.csv","filename":"human_glycan_classification.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"979b9e16ab5d4a92a0b44d248e9311f2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification  (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.936736","modified":"2019-11-25T15:17:32.145772","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_classification.csv","filename":"human_glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000068"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mapped_n_glycans.csv","filename":"mapped_n_glycans.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.stat.csv","filename":"human_glycan_enzyme.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c6016074af52003e3f4a1cb69fc9d6d9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human proteins-Biosynthetic Enzyme","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-11-25T15:13:06.380633","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mapped_n_glycans.csv","filename":"mapped_n_glycans.csv"},{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"}],"prerequisite":[],"description":"The input files were downloaded from the authors and a python script was used to extract columns- GlyTouCanAccession,Enzyme_UniProtAccession, Enzyme_GeneName,Enzyme_GeneID,Enzyme_TaxonomyID from input file 1 and columns- glycan_ID,residue,residue_ID,parent_ID from input file 2 . The script additionally maps the UniProtKB accession to UniProtKB canonical accessions and extracts rows where UniProtKB canonical accession has taxid=9606"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the GlycO tree model. The glycans listed in the database may or may not have a human species (TaxID:9606) annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human biosynthetic enzyme association should not be considered as a human species annotation for that glycan."],"bco_id":"http://data.glygen.org/GLY_000064"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_properties.csv","filename":"human_glycan_properties.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_properties.stat.csv","filename":"human_glycan_properties.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f067be9edc4434412547f1b2f0a43b06","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Properties  (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.935676","modified":"2019-11-25T15:14:40.755532","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_properties.csv","filename":"human_glycan_properties.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethlyated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000067"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mapped_n_glycans.csv","filename":"mapped_n_glycans.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.stat.csv","filename":"mouse_glycan_enzyme.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"93e46c9634ef62c7924a7636067f15fb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse proteins-Biosynthetic Enzyme","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.933570","modified":"2019-11-25T15:13:40.931337","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mapped_n_glycans.csv","filename":"mapped_n_glycans.csv"},{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"}],"prerequisite":[],"description":"The input files were downloaded from the authors and a python script was used to extract columns- GlyTouCanAccession,Enzyme_UniProtAccession, Enzyme_GeneName,Enzyme_GeneID,Enzyme_TaxonomyID from input file 1 and columns- glycan_ID,residue,residue_ID,parent_ID from input file 2 . The script additionally maps the UniProtKB accession to UniProtKB canonical accessions and extracts rows where UniProtKB canonical accession has taxid=10090"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the GlycO tree model. The glycans listed in the database may or may not have a mouse species (TaxID:10090) annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a mouse biosynthetic enzyme association should not be considered as a mouse species annotation for that glycan."],"bco_id":"http://data.glygen.org/GLY_000065"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d30"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_classification.csv","filename":"mouse_glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_classification.stat.csv","filename":"mouse_glycan_classification.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6c44d08681f5621c88c46610d8e2910f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification  (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.937775","modified":"2019-11-25T15:18:33.079442","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_classification.csv","filename":"mouse_glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000069"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d31"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-cfg-extended.zip","filename":"images-cfg-extended.zip"}}],"output_subdomain":[{"mediatype":"tar","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_cfg_extended.tar.gz","filename":"glycan_images_cfg_extended.tar.gz"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_cfg_extended.tar.stat.csv","filename":"glycan_images_cfg_extended.tar.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aa23974fcd26a08dfdd2d2f843b62e27","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Images","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Images (CFG)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.938796","modified":"2020-03-16T13:24:27.781726","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Images"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/images-cfg-extended.zip","filename":"images-cfg-extended.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_images_cfg_extended.tar.gz","filename":"glycan_images_cfg_extended.tar.gz"}],"prerequisite":[],"description":"The input image files (zip folder) were downloaded from the author and a python script was used extract image files for the GlyTouCan accessions based on the acession masterlist. Refer to the usability domain for the master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan CFG images the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000070"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d33"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.940860","modified":"2019-02-19T14:04:43.787061","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000072"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d34"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.941909","modified":"2019-02-19T14:05:10.307734","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000073"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d32"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images.zip","filename":"images.zip"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_images.csv","filename":"mouse_glycan_images.csv"}}]},"bco_spec_version":"1.3.0","checksum":"19d2080ac52a47f9c9ab79184abbccd1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Images","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Images","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.939826","modified":"2019-11-25T15:19:08.050129","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan","Glycan","Classification","Motifs"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images.zip","filename":"images.zip"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_images.csv","filename":"mouse_glycan_images.csv"}],"prerequisite":[],"description":"This file contains GlyTouCan accessions with images in CFG extended format. The List of GlyTouCans(glycan list) is compiled when the GlyTouCan accession is observed under one or more following criteria:  a) If the glycan has source/taxonomy annotation[taxid:10090] in GlyTouCan b) If the glycan is listed on mouse[taxid:10090] glycan webpage at UniCarbKB c) If the glycan is listed on a mouse[taxid:10090] protein webpage at UniCarbKB d) If the glycan is synthesized by a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00065] e) If the glycan is known to be attached to a mouse[taxid:10090] protein [http://data.glygen.org/GLYDS00041]. A python script[make-glycan_images-directory.py] was used to extract images for the compiled glycan list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions with Images."],"bco_id":"http://data.glygen.org/GLY_000071"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d35"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.942968","modified":"2019-02-19T14:06:27.134501","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000074"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d36"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.943995","modified":"2019-02-19T14:08:33.746059","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000075"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d37"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.945022","modified":"2019-02-19T14:09:15.747085","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000076"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_properties.csv","filename":"mouse_glycan_properties.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_properties.stat.csv","filename":"mouse_glycan_properties.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"699703abf59c7bdf384456dabfaf8ae3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Properties  (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.934602","modified":"2019-11-25T15:14:11.511693","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_properties.csv","filename":"mouse_glycan_properties.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethlyated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000066"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d38"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.946079","modified":"2019-02-19T14:09:57.295655","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000077"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.949190","modified":"2019-02-19T14:10:41.602225","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000080"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d39"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_motif.csv","filename":"human_glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_motif.stat.csv","filename":"human_glycan_motif.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d8374de19eec1856cf5a7279c5dafc7c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Motif (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.947104","modified":"2019-11-25T15:19:40.757378","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Motif"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_motif.csv","filename":"human_glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000078"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_motif.csv","filename":"mouse_glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_motif.stat.csv","filename":"mouse_glycan_motif.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ca2c98036e78b97b52d1d1cb28f0f1c6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Motif (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.948124","modified":"2019-11-25T15:20:20.533257","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Motif"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_motif.csv","filename":"mouse_glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000079"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.952378","modified":"2019-02-19T14:12:30.636705","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000083"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d40"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.954630","modified":"2019-02-19T14:13:24.932675","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000085"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d41"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.955654","modified":"2019-02-19T14:13:50.053333","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000086"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv","filename":"protein_domap.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.csv","filename":"human_protein_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.stat.csv","filename":"human_protein_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"81012963ce93e31bbedfc291249ff849","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.953432","modified":"2020-04-10T11:29:36.357255","version":"1.7.9"},"description_domain":{"keywords":["disease","HPO","OMIM","Genomics England PanelApp","Monarch Initiative","MONDO","DO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.csv","filename":"human_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the OMIM phenotypes for UniProtKB accessions and MONDO disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv and Genomics England disease data from . The script maps the UniProtKB accessions to the UniprotKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Diseases dataset contains list of human [taxid:9606] diseases from OMIM, MONDO and Genomics England databases mapped to the UniProtKB protein canonical accessions and Disease Ontology (DO) identifiers..","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.","Genomics England is a company set up and owned by the Department of Health and Social Care to run the 100,000 Genomes Project, which aims to sequence 100,000 genomes from NHS patients with a rare disease and their families, and patients with cancer.","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, Genomics England,  EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000084"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d42"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_recnames.stat.csv","filename":"human_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"26472063b2bcda9ba2952108dbbf80e5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.956673","modified":"2020-04-10T11:30:02.137726","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for human [taxid:9606] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000087"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d44"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/doid.owl","filename":"doid.owl"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv","filename":"protein_domap.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv","filename":"http://data.glygen.org/ln2wwwdata/reviewed/protein_domap.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7fb1da84f68c86ba2419c8ed0164d0b0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Human Disease Ontology Mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Disease Ontology Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.958718","modified":"2020-08-19T14:11:37.389866","version":"1.7.9"},"description_domain":{"keywords":["disease ontology","mesh id","icd 10","icd 9","umls id","kegg"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/doid.owl","filename":"doid.owl"}],"output_list":[{"access_time":"2019-10-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_domap.csv","filename":"protein_domap.csv"}],"prerequisite":[],"description":"The script extract-from-endpoint.py extracts the cross-reference mapping between DOID and other databases such as ICD 9, ICD 10, UMLS, MeSH, Kegg and maps it to UniProtKB canonical accessions to be finally processed into a csv. The source owl file is loaded as triples in into the triplestore prior to the extraction"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)","If you use this dataset please provide proper attribution to GlyGen and Disease ontology"],"bco_id":"http://data.glygen.org/GLY_000089"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d46"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_bgee.stat.csv","filename":"mouse_protein_xref_bgee.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6668ad227dc9ab50f6bdc887adfc0eb8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Bgee","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T12:36:19.326409","version":"1.7.9"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref Bgee contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets"],"bco_id":"http://data.glygen.org/GLY_000091"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d47"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_biomuta.stat.csv","filename":"human_protein_xref_biomuta.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a4a227a1e0f3825f122ddd09c6f71404","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Biomuta","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BioMuta","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T11:44:11.813164","modified":"2020-04-10T11:32:04.779812","version":"1.7.9"},"description_domain":{"keywords":["mutation","BioMuta","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BioMuta database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref BioMuta contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BioMuta database accessions/identifiers. BioMuta is a single-nucleotide variation (SNV) and disease association database where variations are mapped to genomes and RefSeq nucleotide entries, and unified through UniProtKB/Swiss-Prot positional coordinates. The current version of BioMuta contains only nonsynonymous single-nucleotide variations (nsSNVs) associated with cancer. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000092"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d45"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_bgee.stat.csv","filename":"human_protein_xref_bgee.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"507ec4a66a07035c12fafa843a705b3a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Bgee","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T11:31:45.477452","version":"1.7.9"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref Bgee dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ","Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"bco_id":"http://data.glygen.org/GLY_000090"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d43"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_recnames.stat.csv","filename":"mouse_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bb21a5fd1ade67354185cb0ea43a0805","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.957692","modified":"2020-04-10T12:35:58.497780","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for mouse [taxid:10090] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000088"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d48"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_brenda.stat.csv","filename":"human_protein_xref_brenda.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"93533882206a8ecad50116c1ff2bb690","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref BRENDA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.961796","modified":"2020-04-10T11:32:22.994714","version":"1.7.9"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref BRENDA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"bco_id":"http://data.glygen.org/GLY_000093"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d49"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_brenda.stat.csv","filename":"mouse_protein_xref_brenda.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e8cc1073584f3a3409f78c9d243d4591","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref BRENDA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.961796","modified":"2020-04-10T12:37:00.217516","version":"1.7.9"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniprotKB Xref BRENDA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories.  It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"bco_id":"http://data.glygen.org/GLY_000094"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.stat.csv","filename":"human_protein_xref_cazy.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7c16f879cf83020c69876543cb4f3f05","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CAZy","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:05:44.324142","modified":"2020-04-10T11:32:58.654843","version":"1.7.9"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref CAZy contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"bco_id":"http://data.glygen.org/GLY_000095"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uuniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cdd.stat.csv","filename":"human_protein_xref_cdd.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"602c7af6878f5f47db0a26433ce91a4d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref CDD","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:09:02.680538","modified":"2020-04-10T11:33:22.447768","version":"1.7.9"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref CDD contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"bco_id":"http://data.glygen.org/GLY_000097"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cdd.stat.csv","filename":"mouse_protein_xref_cdd.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"47f4e0f82ffef3c64208ab267f2098db","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CDD","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:09:02.680538","modified":"2020-04-10T12:37:40.337326","version":"1.7.9"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref CDD contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"bco_id":"http://data.glygen.org/GLY_000098"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cazy.stat.csv","filename":"mouse_protein_xref_cazy.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0f1b584c1f699e2b4c04314e9d3b2d6b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref CAZy","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:05:44.324142","modified":"2020-04-10T12:37:20.052292","version":"1.7.9"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates"],"bco_id":"http://data.glygen.org/GLY_000096"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_chembl.stat.csv","filename":"human_protein_xref_chembl.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"584947d6a7b77d2cd3feee0629b60344","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref ChEMBL","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:09:44.596916","modified":"2020-04-10T11:33:38.480380","version":"1.7.9"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref ChEMBL contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"bco_id":"http://data.glygen.org/GLY_000099"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_chembl.stat.csv","filename":"mouse_protein_xref_chembl.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"38c5518643fee2f4f8ebf463f2f79ebf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref ChEMBL","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:09:44.596916","modified":"2020-04-10T12:38:13.714242","version":"1.7.9"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"bco_id":"http://data.glygen.org/GLY_000100"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d50"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.stat.csv","filename":"human_protein_xref_genecards.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c58abbf2a55cb67af7492c1a8817928b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Genecards cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref GeneCards","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:10:45.775261","modified":"2020-04-10T11:34:28.717269","version":"1.7.9"},"description_domain":{"keywords":["gene","GeneCards","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to GeneCards database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," GeneCards is a searchable, integrative database that provides comprehensive, user-friendly information on all annotated and predicted human genes. It automatically integrates gene-centric data from ~150 web sources, including genomic, transcriptomic, proteomic, genetic, clinical and functional information."],"bco_id":"http://data.glygen.org/GLY_000101"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genelocus.stat.csv","filename":"human_protein_genelocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b6d34458193c23a56cbe1b0fbff298f0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Locus (Ensembl)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.950210","modified":"2020-04-10T11:29:22.824792","version":"1.7.9"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Gene Locus (Ensembl) contains human [taxid:9606] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000081"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d51"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.stat.csv","filename":"human_protein_xref_hgnc.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5dc4bce87bf979dbca1bdc46523d0d89","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hgnc cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref HGNC","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:12:30.919588","modified":"2020-04-10T11:34:52.076213","version":"1.7.9"},"description_domain":{"keywords":["HGNC","gene symbol","gene name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to HGNC database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref HGNC dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to HGNC accessions/identifiers. he dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The HUGO Gene Nomenclature Committee is a committee of the Human Genome Organisation that sets the standards for human gene nomenclature. The HGNC approves a unique and meaningful name for every known human gene, based on a query of experts"],"bco_id":"http://data.glygen.org/GLY_000102"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d52"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.stat.csv","filename":"mouse_protein_xref_mgi.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ec45fc31c1289f1b50052c640c1ba615","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Mgi cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref MGI","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:11:47.098435","modified":"2020-04-10T12:39:06.868276","version":"1.7.9"},"description_domain":{"keywords":["gene symbol","gene name","MGI","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to MGI database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref MGI contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to MGI database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of mouse health and disease."],"bco_id":"http://data.glygen.org/GLY_000103"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d55"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.stat.csv","filename":"human_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6c44989b7f34d3a3534d6d0511db698f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:05:44.324142","modified":"2020-04-10T11:35:29.829977","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000106"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d53"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.stat.csv","filename":"human_protein_xref_geneid.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2772c05fdf03b9f9bbb63e36a3c1a40d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref NCBI Gene","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:11:47.098435","modified":"2020-04-10T11:35:13.079947","version":"1.7.9"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref NCBI Gene dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"bco_id":"http://data.glygen.org/GLY_000104"}
{"_id":{"$oid":"5c8bc84bf5c47b4a20d22e6b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_interpro.stat.csv","filename":"mouse_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5e7a0e73cb6f6de4b469bc887749b346","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:05:44.324142","modified":"2020-04-10T12:39:41.705015","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref InterPro contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them"],"bco_id":"http://data.glygen.org/GLY_000107"}
{"_id":{"$oid":"5c8bcd8cf5c47b4c381e56b5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_kegg.stat.csv","filename":"mouse_protein_xref_kegg.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a58ac447b3dd83323a7c6c993ff5da83","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref KEGG PATHWAY","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T12:40:17.376979","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref KEGG PATHWAY contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"bco_id":"http://data.glygen.org/GLY_000109"}
{"_id":{"$oid":"5c8bce48f5c47b4d41044d46"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[],"created":"","modified":"2019-03-15T14:41:43.658687","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000111"}
{"_id":{"$oid":"5c8bcd58f5c47b4beb295132"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_kegg.stat.csv","filename":"human_protein_xref_kegg.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c5046b0f86ca301281d7be8a15ab8fba","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref KEGG PATHWAY","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T11:36:03.305355","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref KEGG PATHWAY contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks."],"bco_id":"http://data.glygen.org/GLY_000108"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d54"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.stat.csv","filename":"mouse_protein_xref_geneid.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c3f1ef2307b811f906292e2bd3d659b0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref NCBI Gene","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T12:11:47.098435","modified":"2020-04-10T12:39:24.683558","version":"1.7.9"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref NCBI Gene dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide. "],"bco_id":"http://data.glygen.org/GLY_000105"}
{"_id":{"$oid":"5c8bce1ef5c47b4cf4e9ac02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_mim.stat.csv","filename":"human_protein_xref_mim.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ec3ae12a0c8230b351c1743c1f8e386b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Omim cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMIM","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T11:36:17.219338","version":"1.7.9"},"description_domain":{"keywords":["phenotype","genotype","OMIM","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMIM database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref OMIM contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMIM database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship."],"bco_id":"http://data.glygen.org/GLY_000110"}
{"_id":{"$oid":"5c8bce85f5c47b4d8e364936"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_nextprot.stat.csv","filename":"human_protein_xref_nextprot.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"62f5f7705b84fad0134347f317fc69df","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Nextprot cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref neXtProt","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T11:36:43.867976","version":"1.7.9"},"description_domain":{"keywords":["neXtProt","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to neXtProt database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref neXtProt contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to neXtProt database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data.",""],"bco_id":"http://data.glygen.org/GLY_000112"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"2019-10-26T17:45:17-0500","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genelocus.stat.csv","filename":"mouse_protein_genelocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ff7faf4373e19ddd5c66b19115465e17","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Locus (Ensembl)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.950210","modified":"2020-04-10T12:35:46.021413","version":"1.7.9"},"description_domain":{"keywords":["gene coordinates","chromosome","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Gene Locus dataset contains mouse [taxid:10090] UniProtKB canonical accessions mapped to the corresponding ensembl gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000082"}
{"_id":{"$oid":"5c8bceeef5c47b4e2b8ee531"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.stat.csv","filename":"mouse_protein_xref_oma.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ec52a352e66dec28adada8986c223755","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OMA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T12:40:33.108688","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref OMA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"bco_id":"http://data.glygen.org/GLY_000114"}
{"_id":{"$oid":"5c8bcec3f5c47b4ddb803a32"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.stat.csv","filename":"human_protein_xref_oma.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fe2411c90c51fa968468a3c6b59d6f2b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OMA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.959744","modified":"2020-04-10T11:37:06.606749","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref OMA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"bco_id":"http://data.glygen.org/GLY_000113"}
{"_id":{"$oid":"5c8bf53ef5c47b579730bf2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_orthodb.stat.csv","filename":"human_protein_xref_orthodb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c711aed5d7bca9702d0195545f96706e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref OrthoDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T14:55:58.596936","modified":"2020-04-10T11:37:34.729582","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref OrthoDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"bco_id":"http://data.glygen.org/GLY_000115"}
{"_id":{"$oid":"5c8bf5d8f5c47b57d9c431ba"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_orthodb.stat.csv","filename":"mouse_protein_xref_orthodb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5c6c77771b0fdcc66e3b1bb905d715c8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref OrthoDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T14:58:32.333977","modified":"2020-04-10T12:41:18.469469","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref OrthoDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"bco_id":"http://data.glygen.org/GLY_000116"}
{"_id":{"$oid":"5c8bf741f5c47b5845beebcd"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_panther.stat.csv","filename":"human_protein_xref_panther.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c34ee681ca09c56c261364c10bb5c060","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PANTHER","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T15:04:33.347577","modified":"2020-04-10T11:38:03.333354","version":"1.7.9"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref PANTHER contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"bco_id":"http://data.glygen.org/GLY_000117"}
{"_id":{"$oid":"5c8bf7b3f5c47b58714663d6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_panther.stat.csv","filename":"mouse_protein_xref_panther.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"089359e8416dd2152e03bc167c146df9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PANTHER","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T15:06:27.574866","modified":"2020-04-10T12:41:35.442817","version":"1.7.9"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref PANTHER contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products"],"bco_id":"http://data.glygen.org/GLY_000118"}
{"_id":{"$oid":"5c8bf849f5c47b58ebb826f6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2019-05.nt","filename":"uniprot-proteome-9606-homo-sapiens-2019-05.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pdb.stat.csv","filename":"human_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5994a05f0729f8909e75ea076ba6afbf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T15:08:57.534471","modified":"2020-04-10T11:38:26.443842","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref PDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000119"}
{"_id":{"$oid":"5c8c04aef5c47b59e714ed9a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pfam.stat.csv","filename":"mouse_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f756c6f8463786f292c4d824327688bf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:01:50.980059","modified":"2020-04-10T12:42:07.520014","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref Pfam contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000122"}
{"_id":{"$oid":"5c8bf8ebf5c47b59171e9974"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pdb.stat.csv","filename":"mouse_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"378639180b958b1220568bb9fbc0d0ae","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T15:11:39.076274","modified":"2020-04-10T12:41:51.241953","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref PDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000120"}
{"_id":{"$oid":"5c8c062ef5c47b5a1fde3210"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pro.stat.csv","filename":"human_protein_xref_pro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"04ae3a6a77320484c30927d109ba1442","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref PRO","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:08:14.880048","modified":"2020-04-10T11:39:35.092004","version":"1.7.9"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref PRO contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"bco_id":"http://data.glygen.org/GLY_000123"}
{"_id":{"$oid":"5c8c03e6f5c47b59903c90e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pfam.stat.csv","filename":"human_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2803051e3a98df541bedc317062b840a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T15:58:30.083377","modified":"2020-04-10T11:39:12.484631","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref Pfam contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000121"}
{"_id":{"$oid":"5c8c069ff5c47b5a4c9b083e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pro.stat.csv","filename":"mouse_protein_xref_pro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6885def977050f2fd1527ce836932f16","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref PRO","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:10:07.474480","modified":"2020-04-10T12:42:23.460565","version":"1.7.9"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniprotKB Xref PRO contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"bco_id":"http://data.glygen.org/GLY_000124"}
{"_id":{"$oid":"5c8c078ef5c47b5a94fa2779"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.stat.csv","filename":"human_protein_xref_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"96a5b2fe3f646d57862d9fbb74eb484e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref Reactome","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:14:06.456984","modified":"2020-04-10T11:39:49.739285","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. "],"bco_id":"http://data.glygen.org/GLY_000125"}
{"_id":{"$oid":"5c8c0817f5c47b5acea50e64"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_reactome.stat.csv","filename":"mouse_protein_xref_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"958bfc28adf24df2908352c0ccb98f92","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref Reactome","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:16:23.633025","modified":"2020-04-10T12:42:51.293005","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["TheMouse UniProtKB Xref Reactome contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"bco_id":"http://data.glygen.org/GLY_000126"}
{"_id":{"$oid":"5c8c0919f5c47b5b06462bf0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.stat.csv","filename":"human_protein_xref_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5e1f79ae72d8d6bb9795e5a4322f001e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref RefSeq","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:20:41.396963","modified":"2020-04-10T11:40:19.547480","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref RefSeq contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"bco_id":"http://data.glygen.org/GLY_000127"}
{"_id":{"$oid":"5c8c09b3f5c47b5b32e9fe6d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.stat.csv","filename":"mouse_protein_xref_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2f1efc080e7ecea705a7c256916c7d9e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref RefSeq","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:23:15.480143","modified":"2020-04-10T12:43:08.705441","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniprotKB Xref RefSeq contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"bco_id":"http://data.glygen.org/GLY_000128"}
{"_id":{"$oid":"5c8c101bf5c47b5ba53b598e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_unicarbkb.stat.csv","filename":"human_protein_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1b990efd253898f8ad02f588cccb26a1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref UniCarbKB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:50:35.816502","modified":"2020-04-10T11:40:40.491880","version":"1.7.9"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mapping.csv","filename":"human_protein_mapping.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref UniCarbKB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research."],"bco_id":"http://data.glygen.org/GLY_000129"}
{"_id":{"$oid":"5c8c10e0f5c47b5bfea63abf"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_unicarbkb.stat.csv","filename":"mouse_protein_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ada058c2077c701f371a7d8214db71aa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref UniCarbKB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T16:53:52.791212","modified":"2020-04-10T12:43:26.620318","version":"1.7.9"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse UniProtKB Xref UniCarbKB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000130"}
{"_id":{"$oid":"5c8c3c82f5c47b68be0cedc0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprotkb.stat.csv","filename":"human_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aa1bc357be76d5e004e5154226df0354","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T20:00:02.159427","modified":"2020-04-10T11:41:06.248826","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprotkb.csv","filename":"human_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Function (UniProtKB) dataset contains biological function annotation for human [taxid:9606] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000131"}
{"_id":{"$oid":"5c8c3d24f5c47b69152224e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_uniprotkb.stat.csv","filename":"mouse_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"22cc7a36e645f2592439787f971f653c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-15T20:02:44.685450","modified":"2020-04-10T12:43:43.058752","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_uniprotkb.csv","filename":"mouse_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Function (UniProtKB) dataset contains biological function annotation for mouse [taxid:10090] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000132"}
{"_id":{"$oid":"5c8d6c33f5c47b36c48385f3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/source/mouse_human_1-1_orthologs_oma_release-24_030619_15-02pm.csv","filename":"mouse_human_1-1_orthologs_oma_release-24_030619_15-02pm.csv"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/source/hom_mousehumansequence_v6.13_030619_17-16pm.csv","filename":"hom_mousehumansequence_v6.13_030619_17-16pm.csv"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:49:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:49:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.stat.csv","filename":"protein_ortholog.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d8a104e908f79b84432ec52a054419f9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Retired Protein Ortholog","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-03-16T17:35:47.116060","modified":"2019-09-13T15:19:20.683565","version":"1.7.9"},"description_domain":{"keywords":["protein ortholog","OMA ","MGI"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/source/mouse_human_1-1_orthologs_oma_release-24_030619_15-02pm.csv","filename":"mouse_human_1-1_orthologs_oma_release-24_030619_15-02pm.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/source/hom_mousehumansequence_v6.13_030619_17-16pm.csv","filename":"hom_mousehumansequence_v6.13_030619_17-16pm.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:49:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the 1:1 orthologs from OMA and MGI dataset and maps it to UniProtKB canonical accessions of human and mouse via other mapping files"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-csv.py","filename":"extract-from-csv.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Protein ortholog dataset contains the protein 1:1 orthologs of human [taxid:9606] and mouse [taxid:10090] species. The ortholog data is downloaded from MGI and OMA browser and the mapping is between human and mouse canonical orthologs","If you use this dataset please provide proper attribution to MGI, OMA Browser and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000137"}
{"_id":{"$oid":"5cb63eb3f5c47b10c5f37f2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_unicarbkb.csv","filename":"mouse_proteoform_citations_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_unicarbkb.stat.csv","filename":"mouse_proteoform_citations_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"61762447a12d8551aba14054397a444c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Citations (UniCarbKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-04-16T16:44:35.331041","modified":"2020-04-10T12:44:36.872060","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_unicarbkb.csv","filename":"mouse_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Proteoform Citations (UniCarbKB) contains mouse [taxid:10090] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. . The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/GLY_000139"}
{"_id":{"$oid":"5cb63fe0f5c47b114b15fef6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allrefs.txt","filename":"human_glycan_evidence.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_evidence.csv","filename":"human_glycan_evidence.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_glycan_citations.csv","filename":"human_glycan_citations.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_glycan_citations.csv","filename":"human_glycan_evidence.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_glycan_citations.log","filename":"human_glycan_citations.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_glycan_citations.stat.csv","filename":"human_glycan_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Citations","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fotchman","email":"bfochtman@gwu.edu"}],"created":"2019-04-16T16:49:36.812969","modified":"2019-04-18T16:06:37.966754","version":"1.7.9"},"description_domain":{"keywords":["citations"],"pipeline_steps":[{"name":"Linux","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allrefs.txt","filename":"allrefs.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_evidence.csv","filename":"human_glycan_evidence.csv"}],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"The columns \"evidence\" and \"uniprotkb_acc_canonical\" was extracted from the source file and was sorted and made unique."},{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_evidence.csv","filename":"human_glycan_evidence.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_citations.csv","filename":"human_glycan_citations.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_glycan_citations.log","filename":"human_glycan_citations.log"}],"prerequisite":[],"description":"The medline records for the PMIDs extracted from output file of step 2 were downloaded and data such as journal name, title and publication date was extracted."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Publication data for the PMID's sourced from UniCarbKB"],"bco_id":"http://data.glygen.org/GLY_000140"}
{"_id":{"$oid":"5cb642f9f5c47b1297d2df1f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allrefs.txt","filename":"mouse_glycan_evidence.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_evidence.csv","filename":"mouse_glycan_evidence.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_glycan_citations.csv","filename":"mouse_glycan_citations.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_glycan_citations.csv","filename":"mouse_glycan_evidence.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_glycan_citations.log","filename":"mouse_glycan_citations.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_glycan_citations.stat.csv","filename":"mouse_glycan_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Citations","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Brian Fotchman","email":"bfochtman@gwu.edu"}],"created":"2019-04-16T17:02:49.845204","modified":"2019-04-18T16:07:31.921693","version":"1.7.9"},"description_domain":{"keywords":["citations"],"pipeline_steps":[{"name":"Linux","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allrefs.txt","filename":"allrefs.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_evidence.csv","filename":"mouse_glycan_evidence.csv"}],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"The columns \"evidence\" and \"uniprotkb_acc_canonical\" was extracted from the source file and was sorted and made unique."},{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_evidence.csv","filename":"mouse_glycan_evidence.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_citations.csv","filename":"mouse_glycan_citations.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_glycan_citations.log","filename":"mouse_glycan_citations.log"}],"prerequisite":[],"description":"The medline records for the PMIDs extracted from output file of step 2 were downloaded and data such as journal name, title and publication date was extracted."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Publication data for the PMID's sourced from UniCarbKB"],"bco_id":"http://data.glygen.org/GLY_000141"}
{"_id":{"$oid":"5cf98adaf5c47b56c79d76b9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.stat.csv","filename":"human_proteoform_glycosylation_sites_harvard.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7637f5578e655641cc6c855a458e3289","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation sites (Harvard)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation (Harvard Department of Chemistry and Chemical Biology)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Harvard University","contribution":["authoredBy","contributedBy","providedBy"],"name":"Christina Woo","email":"cwoo@chemistry.harvard.edu"}],"created":"2019-06-06T17:51:22.706056","modified":"2020-05-01T15:22:27.881080","version":"1.7.9"},"description_domain":{"keywords":["Glycan","Publications","Proteoform"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv","filename":"T_Cell_O-GlcNAc_sites_CWoo_8-23-18.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"prerequisite":[],"description":"The input file was submitted by the author. An additional column \"Evidence\" with value \"GLYDS000142\" was added in the input file. A python script was used to process data to 1. map UniprotKB accessions to UniProtKB canonical accessions 2. Split the \"GlycoSite(s) (protein)\" column to amino acid and glycosylation site. 3.Split the \"GlycoSite(s) (protein)\" column into single value row. 4. Add two new columns: glycosylation_type=o-linked and evidence=29351928 (based on author's recommendation). A quality check is done to match the position + amino acid with the canonical fasta sequence (https://data.glygen.org/GLYDS000002). The rows which fail the QC are eliminated from the final output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""},{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on O-glycosylation sites on Human proteins. The data is submitted by Dr.Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. The GlyTouCan accession (G70994MS)is annotated to the glycan composition based on author's recommendation. Author's note: \"For the glycan assignment, it would be most technically correct to use a HexNAc molecule, although by and large, these are O-GlcNAc modifications, we cannot be 100% certain for every single one\". The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). The source publication:Woo CM, Lund PJ, Huang AC, Davis MM, Bertozzi CR, Pitteri SJ. Mapping and Quantification of Over 2000 O-linked Glycopeptides in Activated Human T Cells with Isotope-Targeted Glycoproteomics (Isotag). Mol Cell Proteomics. 2018;17(4):764-75. doi: 10.1074/mcp.RA117.000261. PubMed PMID: 29351928; PubMed Central PMCID: PMCPMC5880114)."],"bco_id":"http://data.glygen.org/GLY_000142"}
{"_id":{"$oid":"5d03ed62f5c47b17575f69c5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_24190977_s5.csv","filename":"glycosylation_sites_24190977_s5.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_23090970_s5.csv","filename":"glycosylation_sites_23090970_s5.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_23090970_s2.csv","filename":"glycosylation_sites_23090970_s2.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv","filename":"human_proteoform_glycosylation_sites_literature.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"UniCarbKB publications","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation (Literature)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-06-14T14:54:26.195339","modified":"2019-09-12T16:37:13.572422","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation","literature","publications"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_24190977_s5.csv","filename":"glycosylation_sites_24190977_s5.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_23090970_s5","filename":"glycosylation_sites_23090970_s5"},{"access_time":"","sha1_chksum":"","uri":",https://data.glygen.org/ln2wwwdata/source/glycosylation_sites_23090970_s2.csv","filename":"glycosylation_sites_23090970_s2.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLYDS000002)to generate the output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Wi?niewski, J. R., & Mann, M. (2012). Quantification of theN-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\").  The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001). "],"bco_id":"http://data.glygen.org/GLY_000143"}
{"_id":{"$oid":"5c8d4ff3f5c47b31a13ff81c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_refseq.csv","filename":"human_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_refseq.stat.csv","filename":"human_protein_function_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0ac7e7b27ce0a0de186b26f83ce54674","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Function (NCBI Refseq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-16T15:35:15.248632","modified":"2020-04-10T11:41:20.232299","version":"1.7.9"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Function (NCBI RefSeq) dataset contains biological function annotaion of human [taxid:9606] genes from GeneRIF section in the NCBI RefSeq database. The dataset is downloaded from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000133"}
{"_id":{"$oid":"5c8d56f4f5c47b3476ee9534"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.stat.csv","filename":"human_protein_transcriptlocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"21757d0644c3ff19306726b3be7da7df","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-16T16:05:08.939322","modified":"2020-04-10T11:41:42.489298","version":"1.7.9"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlistcsv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB human [taxid:9606] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts's start and end position The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000135"}
{"_id":{"$oid":"5d2df56ef5c47b469859568f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_accession_sources.csv","filename":"human_glycan_accession_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_accession_sources.stat.csv","filename":"human_glycan_accession_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"38d6c8f5e0a9d1e889dee7ed7f633aaf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Master List","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human GlyTouCan Masterlist","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"}],"created":"2019-07-16T12:03:58.614740","modified":"2019-11-14T15:45:53.855870","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Master List"],"pipeline_steps":[{"name":"python","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":""}],"output_list":[],"prerequisite":[],"description":"The output file was generated by appending the GlyTouCan accessions from 4 input files. The source column represents the category number based on the source input files: category_I : (Input file 1; where \"Taxid:9606\") The Glycan has a Human [taxid:9606] (Homo sapiens) species annotation from GlyTouCan and/UniCarbKB database. category_II: (Input file 2) The Glycan is synthesized by a Human [taxid:9606] (Homo sapiens) protein. category_III: (Input file 3) The Glycan is known to be attached to a Human [taxid:9606] (Homo sapiens) protein. category_IV: (Input file 4) The glycan is a motif of the glycan from categories I, II, III."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset contains a list of GlyTouCan accessions considered to be the GlyGen Human GlyTouCan Master list. The inclusion criteria are provided by a category number associated with the glycan (GlyTouCan Accession). category_I: The Glycan has a Human [taxid:9606] (Homo sapiens) species annotation from GlyTouCan and/or UniCarbKB database. category_II:  The Glycan is associated to a Human [taxid:9606] (Homo sapiens) bio-synthetic enzyme. category_III: The Glycan is known to be attached to a Human [taxid:9606] (Homo sapiens) protein. category_IV: The glycan is a motif of the glycan from categories I, II, III."],"bco_id":"http://data.glygen.org/GLY_000144"}
{"_id":{"$oid":"5c8d5751f5c47b34a28a481b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.stat.csv","filename":"mouse_protein_transcriptlocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"346d83a0b5d6e2f8a978339f3e5bcac9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-16T16:06:41.833239","modified":"2020-04-10T12:44:17.413281","version":"1.7.9"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Th Mouse Transcript Locus (Ensembl Transcript coordinates)contains UniProtKB mouse [taxid:10090] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts's start and end position. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000136"}
{"_id":{"$oid":"5d2dfad2f5c47b4a8a8f8db8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_accession_sources.csv","filename":"mouse_glycan_accession_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_accession_sources.stat.csv","filename":"mouse_glycan_accession_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a884f78f76ab042e0a79906b0018907c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Master List","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse GlyTouCan Masterlist","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"}],"created":"2019-07-16T12:26:58.392765","modified":"2019-11-14T15:46:12.423552","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Master List"],"pipeline_steps":[{"name":"python","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":""}],"output_list":[],"prerequisite":[],"description":"The output file was generated by appending the GlyTouCan accessions from 4 input files. The source column represents the category number based on the source input files: category_I : (Input file 1; where \"Taxid:9606\") The Glycan has aMouse [taxid:10090] (Mus musculus) species annotation from GlyTouCan and/UniCarbKB database. category_II: (Input file 2) The Glycan is synthesized by a Mouse [taxid:10090] (Mus musculus) protein. category_III: (Input file 3) The Glycan is known to be attached to a Mouse [taxid:10090] (Mus musculus) protein. category_IV: (Input file 4) The glycan is a motif of the glycan from categories I, II, III."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset contains a list of GlyTouCan accessions considered to be the GlyGen Mouse GlyTouCan Master list. The inclusion criteria are provided by a category number associated with the glycan (GlyTouCan Accession). category_ I: The Glycan has a mouse [taxid:10090] (Mus musculus) species annotation from GlyTouCan and/or UniCarbKB database. category_II:  The Glycan is associated to a Mouse [taxid:10090] (Mus musculus) biosynthetic enzyme. category_III: The Glycan is known to be attached to a Mouse [taxid:10090] (Mus musculus) protein. category_IV: The glycan is a motif of the glycan from categories I, II, III."],"bco_id":"http://data.glygen.org/GLY_000145"}
{"_id":{"$oid":"5d2dfdf1f5c47b4fd6db45e2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_enzyme.csv","filename":"rat_glycan_enzyme.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_accession_sources.csv","filename":"rat_glycan_accession_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_accession_sources.stat.csv","filename":"rat_glycan_accession_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"de08351d6fd2ea4dec1dfc3b751ec191","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Master List","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat GlyTouCan Masterlist","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"}],"created":"2019-07-16T12:40:17.523554","modified":"2019-11-14T15:46:51.350015","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Master List"],"pipeline_steps":[{"name":"python","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_enzyme.csv","filename":"rat_glycan_enzyme.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":""}],"output_list":[],"prerequisite":[],"description":"The output file was generated by appending the GlyTouCan accessions from 4 input files. The source column represents the category number based on the source input files: category_I : (Input file 1; where \"Taxid:9606\") The Glycan has a Rat [taxid:10116] (Rattus Norvegicus) species annotation from GlyTouCan and/UniCarbKB database. category_II: (Input file 2) The Glycan is synthesized by a Rat [taxid:10116] (Rattus Norvegicus) protein. category_III: (Input file 3) The Glycan is known to be attached to a Rat [taxid:10116] (Rattus Norvegicus) protein. category_IV: (Input file 4) The glycan is a motif of the glycan from categories I, II, III."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset contains the list of GlyTouCan accessions considered to be the GlyGen Rat GlyTouCan Master list. The inclusion criteria are provided by the category number associated with the glycan (GlyTouCan Accession). Category_ I: The Glycan has a Rat [taxid:10116] (Rattus norvegicus) species annotation from GlyTouCan and/or UniCarbKB database. category_II:  The Glycan is associated to a Rat [taxid:10116] (Rattus norvegicus) biosynthetic enzyme. category_III: The Glycan is known to be attached to a Rat [taxid:10116] (Rattus norvegicus) protein. category_IV: The glycan is a motif of the glycan from categories I, II, III."],"bco_id":"http://data.glygen.org/GLY_000146"}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f652"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_citations_glytoucan.csv","filename":"human_glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_citations_glytoucan.stat.csv","filename":"human_glycan_citations_glytoucan.stat.csv"}}]},"checksum":"cb252a701c0a9722491df80ce288f982","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.921123","modified":"2019-11-14T15:47:20.736346","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database.. The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000147","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_citations_glytoucan.csv","filename":"human_glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5cb63ba9f5c47b0fa29b8ece"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_unicarbkb.csv","filename":"human_proteoform_citations_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_unicarbkb.stat.csv","filename":"human_proteoform_citations_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"3f57c016c03d7bc490ff4c698e03e46c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (UniCarbKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-04-16T16:31:37.511217","modified":"2020-04-10T11:42:00.294531","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_unicarbkb.csv","filename":"human_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Proteoform Citations (UniCarbKB) contains human [taxid:9606] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/GLY_000138"}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f654"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_glycam_iupac.csv","filename":"human_glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_glycam_iupac.stat.csv","filename":"human_glycan_sequences_glycam_iupac.stat.csv"}}]},"checksum":"0021d009413ad38f77b4a61299a736dd","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences Glycam IUPAC (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.924099","modified":"2019-11-14T15:47:55.054156","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://dev.glycam.org/"],"bco_id":"http://data.glygen.org/GLY_000149","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_glycam_iupac.csv","filename":"human_glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f655"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_glycoct.csv","filename":"human_glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_glycoct.stat.csv","filename":"human_glycan_sequences_glycoct.stat.csv"}}]},"checksum":"b5d5f39219d19de4d80ee960a3b68335","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GlycoCT (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.925563","modified":"2019-11-14T15:48:11.371403","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000150","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_glycoct.csv","filename":"human_glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f653"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_monosaccharide_composition.csv","filename":"human_glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_monosaccharide_composition.stat.csv","filename":"human_glycan_monosaccharide_composition.stat.csv"}}]},"checksum":"8b4d41174276a254b550af8f44cfaaab","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide compositions (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.922667","modified":"2019-11-14T15:47:38.652499","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans  (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000148","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_monosaccharide_composition.csv","filename":"human_glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f657"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_iupac_extended.csv","filename":"human_glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_iupac_extended.stat.csv","filename":"human_glycan_sequences_iupac_extended.stat.csv"}}]},"checksum":"72a896247a60cbc47486791a4daf78b2","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences IUPAC Extended (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.928345","modified":"2019-11-14T15:48:57.596182","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000152","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_iupac_extended.csv","filename":"human_glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f658"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_smiles_isomeric.csv","filename":"human_glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_smiles_isomeric.stat.csv","filename":"human_glycan_sequences_smiles_isomeric.stat.csv"}}]},"checksum":"c0631da2bcd137fca5b1e96b28f9758c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.929715","modified":"2019-11-14T15:49:19.420890","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000167). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000153","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_smiles_isomeric.csv","filename":"human_glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f659"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_wurcs.csv","filename":"human_glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_wurcs.stat.csv","filename":"human_glycan_sequences_wurcs.stat.csv"}}]},"checksum":"1ebcfe162a61149be2ac52dd49f641da","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences WURCS (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.931104","modified":"2019-11-28T11:55:49.064805","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000154","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_wurcs.csv","filename":"human_glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_taxonomy.csv","filename":"human_glycan_taxonomy.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_taxonomy.stat.csv","filename":"human_glycan_taxonomy.stat.csv"}}]},"checksum":"4a650df61433ffa3141bd11ee42dad57","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Taxonomy (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.932542","modified":"2019-11-14T15:49:55.442135","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides NCBI TaxID for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy"],"bco_id":"http://data.glygen.org/GLY_000155","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_taxonomy.csv","filename":"human_glycan_taxonomy.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_bcsdb.csv","filename":"human_glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_bcsdb.stat.csv","filename":"human_glycan_xref_bcsdb.stat.csv"}}]},"checksum":"ca36b6561e4ab7849e5aeb7808a34bd6","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.933916","modified":"2019-11-14T15:50:16.929857","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"bco_id":"http://data.glygen.org/GLY_000156","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_bcsdb.csv","filename":"human_glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_carbbank.csv","filename":"human_glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_carbbank.stat.csv","filename":"human_glycan_xref_carbbank.stat.csv"}}]},"checksum":"a22669e16b3608e171627a0d78043415","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.935256","modified":"2019-11-14T15:50:52.601391","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"bco_id":"http://data.glygen.org/GLY_000157","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_carbbank.csv","filename":"human_glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_cfg.csv","filename":"human_glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_cfg.stat.csv","filename":"human_glycan_xref_cfg.stat.csv"}}]},"checksum":"3089830ee43c71d7159a0400c893405c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.936706","modified":"2019-11-14T15:51:08.951372","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"bco_id":"http://data.glygen.org/GLY_000158","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_cfg.csv","filename":"human_glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f656"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_inchi.csv","filename":"human_glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_sequences_inchi.stat.csv","filename":"human_glycan_sequences_inchi.stat.csv"}}]},"checksum":"f45ba73f0de05ad21c2a29a0efb25154","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences InChI (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.926947","modified":"2019-11-14T15:48:42.854766","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the InChI key and glycan sequences in InChI format  for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000167). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000151","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_sequences_inchi.csv","filename":"human_glycan_sequences_inchi.csv"}],"prerequisite":[],"description":"The GlyTouCan Ac. to PubChem CID mapping file was used download .sdf PubChem compound files from PubChem CID ftp and a python script was used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f660"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glyco.csv","filename":"human_glycan_xref_glyco.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glyco.stat.csv","filename":"human_glycan_xref_glyco.stat.csv"}}]},"checksum":"1ffab9901d0a913d0479ab18ec14c702","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycO (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.940822","modified":"2019-11-14T15:52:35.841398","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycO ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000161","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCO Cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glyco","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_glyco.csv","filename":"human_glycan_xref_glyco.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f661"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glycomedb.csv","filename":"human_glycan_xref_glycomedb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glycomedb.stat.csv","filename":"human_glycan_xref_glycomedb.stat.csv"}}]},"checksum":"58af1e8d2689d49395a21aec1c3a53bc","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycomeDB (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.942209","modified":"2019-11-14T15:52:56.600875","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycomeDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/"],"bco_id":"http://data.glygen.org/GLY_000162","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycomeDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycomeDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_glycomedb.csv","filename":"human_glycan_xref_glycomedb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/database_accession_2019_02_07_03_58_16.tsv","filename":"database_accession_2019_02_07_03_58_16.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_chebi_from_kegg.csv","filename":"human_glycan_xref_chebi_from_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_chebi_from_kegg.stat.csv","filename":"human_glycan_xref_chebi_from_kegg.stat.csv"}}]},"checksum":"d442fd08bb06a6154fa8ab4607fcd6ff","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [KEGG ID] (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.939472","modified":"2019-11-14T15:52:11.707654","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to KEGG glycan ID mapping (https://data.glygen.org/GLYDS000160) .  The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000160","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references (KEGG GLYCAN)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (KEGG Glycan ID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_chebi_from_kegg.csv","filename":"human_glycan_xref_chebi_from_kegg.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to KEGG glycan  mapping file to extract the KEGG Glycan ID to ChEBI ID mapping from the ChEBI FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f663"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glycosciencesde.csv","filename":"human_glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glycosciencesde.stat.csv","filename":"human_glycan_xref_glycosciencesde.stat.csv"}}]},"checksum":"644d36e4b99f47d79fef189c3b4b165f","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.945165","modified":"2019-11-14T15:53:34.608867","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"bco_id":"http://data.glygen.org/GLY_000164","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_glycosciencesde.csv","filename":"human_glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f65e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2019_05_06_10_23_08","filename":"CID-Synonym-filtered_2019_05_06_10_23_08"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/chebiId_inchi.tsv","filename":"chebiId_inchi.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_chebi.csv","filename":"human_glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_chebi.stat.csv","filename":"human_glycan_xref_chebi.stat.csv"}}]},"checksum":"daaa81369a9a6fffda3815341d7d9896","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [PubChem CID] (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.938103","modified":"2019-11-14T15:51:33.349837","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000167) .  One-to-many PubChem CID to ChEBI mappings are resolved using InChI seqences downloaded from both (PubChem CID and ChEBI) databases. The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000159","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references(PUBCHEM CID)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (PubChem CID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_chebi.csv","filename":"human_glycan_xref_chebi.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID  mapping file to extract the PubChem CID to ChEBI ID mapping from the PubChem FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f664"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_kegg.stat.csv","filename":"human_glycan_xref_kegg.stat.csv"}}]},"checksum":"0bb76137e5e13f6de3859a7f6f4cd393","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.946527","modified":"2019-11-14T15:54:07.699685","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"bco_id":"http://data.glygen.org/GLY_000165","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f667"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_unicarbdb.csv","filename":"human_glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_unicarbdb.stat.csv","filename":"human_glycan_xref_unicarbdb.stat.csv"}}]},"checksum":"4f8e5571b1b805c5ec6830d982dfbd8e","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.950940","modified":"2019-11-14T12:07:27.010363","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"bco_id":"http://data.glygen.org/GLY_000168","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_unicarbdb.csv","filename":"human_glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f666"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_pubchem.csv","filename":"human_glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_pubchem.stat.csv","filename":"human_glycan_xref_pubchem.stat.csv"}}]},"checksum":"d152d73877c6fb6526214fe13232ff9c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.949556","modified":"2019-11-14T12:03:49.211200","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"bco_id":"http://data.glygen.org/GLY_000167","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_pubchem.csv","filename":"human_glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f665"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_pdb.csv","filename":"human_glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_pdb.stat.csv","filename":"human_glycan_xref_pdb.stat.csv"}}]},"checksum":"ead890250224a99b6dcca74c29fb61f2","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.947940","modified":"2019-11-14T11:46:31.557204","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"bco_id":"http://data.glygen.org/GLY_000166","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_pdb.csv","filename":"human_glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f668"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_unicarbkb.csv","filename":"human_glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_unicarbkb.stat.csv","filename":"human_glycan_xref_unicarbkb.stat.csv"}}]},"checksum":"f2e4836a3943b709df3b80dc77307c15","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.952295","modified":"2019-11-14T12:13:54.134291","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000169","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_unicarbkb.csv","filename":"human_glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f669"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_citations_glytoucan.csv","filename":"rat_glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_citations_glytoucan.stat.csv","filename":"rat_glycan_citations_glytoucan.stat.csv"}}]},"checksum":"aaf2a23402b8d49228eea82af5800bca","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.953582","modified":"2019-11-14T15:55:00.280000","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database. The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000170","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan citations","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_citations_glytoucan.csv","filename":"rat_glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_enzyme.csv","filename":"rat_glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_enzyme.stat.csv","filename":"rat_glycan_enzyme.stat.csv"}}]},"checksum":"d35124fbd0c85afde80787b5030b4511","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Enzyme Data [Rat]","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.956498","modified":"2019-11-14T15:55:35.522540","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000172","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":[],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_enzyme.csv","filename":"rat_glycan_enzyme.csv"}],"prerequisite":[],"description":""}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_classification.csv","filename":"rat_glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_classification.stat.csv","filename":"rat_glycan_classification.stat.csv"}}]},"checksum":"d058f8045398784b314d346f99da8282","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.954924","modified":"2019-11-14T15:55:21.634325","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000171","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_classification.csv","filename":"rat_glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f662"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glyconnect.csv","filename":"human_glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_glycan_xref_glyconnect.stat.csv","filename":"human_glycan_xref_glyconnect.stat.csv"}}]},"checksum":"7bb249dc766fa18689ab42f7cc16b6b0","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect (Human GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.943598","modified":"2019-11-14T15:53:13.875679","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Human GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"bco_id":"http://data.glygen.org/GLY_000163","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_glyconnect.csv","filename":"human_glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_monosaccharide_composition.csv","filename":"rat_glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_monosaccharide_composition.stat.csv","filename":"rat_glycan_monosaccharide_composition.stat.csv"}}]},"checksum":"8c46e98012dac5c0bbf99a43e24ce12f","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide Composition (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.957851","modified":"2019-11-14T15:55:55.560340","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans  (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000173","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_monosaccharide_composition.csv","filename":"rat_glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_motif.csv","filename":"rat_glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_motif.stat.csv","filename":"rat_glycan_motif.stat.csv"}}]},"checksum":"52e5c8c82bbab2e01e31b4a15d0505fb","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Motif (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.959311","modified":"2019-11-14T15:56:21.353915","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000174","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Motif"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.tsv","filename":"allmotif.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_motif.csv","filename":"rat_glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f670"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_glycoct.csv","filename":"rat_glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_glycoct.stat.csv","filename":"rat_glycan_sequences_glycoct.stat.csv"}}]},"checksum":"91d4bc07b6d79026e5e0fa003bc6d9d0","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GlycoCT (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.963585","modified":"2019-11-14T15:57:21.128563","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession).The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146).  Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000177","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_glycoct.csv","filename":"rat_glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f671"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_inchi.csv","filename":"rat_glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_inchi.stat.csv","filename":"rat_glycan_sequences_inchi.stat.csv"}}]},"checksum":"00e77a58e1f037e499a8a9bbe43e2d10","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences InchI (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.964930","modified":"2019-11-14T15:57:38.735560","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the InChI key and glycan sequences in InChI format  for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000194). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000178","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_inchi.csv","filename":"rat_glycan_sequences_inchi.csv"}],"prerequisite":[],"description":"The GlyTouCan Ac. to PubChem CID mapping file was used download .sdf PubChem compound files from PubChem CID ftp and a python script was used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_glycam_iupac.csv","filename":"rat_glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_glycam_iupac.stat.csv","filename":"rat_glycan_sequences_glycam_iupac.stat.csv"}}]},"checksum":"90580629b5e8c172872856889447e465","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GLYCAM IUPAC (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.962191","modified":"2019-11-14T15:56:59.595804","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://dev.glycam.org/"],"bco_id":"http://data.glygen.org/GLY_000176","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_glycam_iupac.csv","filename":"rat_glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f672"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_iupac_extended.csv","filename":"rat_glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_iupac_extended.stat.csv","filename":"rat_glycan_sequences_iupac_extended.stat.csv"}}]},"checksum":"b827a336518e84858cdf61a75fa830be","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences IUPAC Extended (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.966326","modified":"2019-11-14T15:58:04.571839","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000179","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_iupac_extended.csv","filename":"rat_glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script was used to process the data to generate the final output file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f674"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_wurcs.csv","filename":"rat_glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_wurcs.stat.csv","filename":"rat_glycan_sequences_wurcs.stat.csv"}}]},"checksum":"d52c52454cafede722041a8a56164fb1","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences WURCS (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.969140","modified":"2019-11-14T15:58:45.192450","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000181","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_wurcs.csv","filename":"rat_glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f675"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_taxonomy.csv","filename":"rat_glycan_taxonomy.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_taxonomy.stat.csv","filename":"rat_glycan_taxonomy.stat.csv"}}]},"checksum":"5e9c5b2afd5d0d36f35f74ce555bc3cc","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Taxonomy (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.970607","modified":"2019-11-14T15:59:05.415159","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides NCBI TaxID for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy"],"bco_id":"http://data.glygen.org/GLY_000182","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_taxonomy.csv","filename":"rat_glycan_taxonomy.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f676"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_bcsdb.csv","filename":"rat_glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_bcsdb.stat.csv","filename":"rat_glycan_xref_bcsdb.stat.csv"}}]},"checksum":"b2e77510abb51765df51f5b7e5a828f3","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.971938","modified":"2019-11-14T15:59:20.902152","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"bco_id":"http://data.glygen.org/GLY_000183","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_bcsdb.csv","filename":"rat_glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f677"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_carbbank.csv","filename":"rat_glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_carbbank.stat.csv","filename":"rat_glycan_xref_carbbank.stat.csv"}}]},"checksum":"25d77e3e2a9e0a99d837ec351fbdd6bb","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.973321","modified":"2019-11-14T15:59:38.978367","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"bco_id":"http://data.glygen.org/GLY_000184","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_carbbank.csv","filename":"rat_glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f678"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_cfg.csv","filename":"rat_glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_cfg.stat.csv","filename":"rat_glycan_xref_cfg.stat.csv"}}]},"checksum":"570ff364d78ea7c7173068dd703aa690","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.975196","modified":"2019-11-14T15:59:56.010163","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"bco_id":"http://data.glygen.org/GLY_000185","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_cfg.csv","filename":"rat_glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f679"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2019_05_06_10_23_08","filename":"CID-Synonym-filtered_2019_05_06_10_23_08"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/chebiId_inchi.tsv","filename":"chebiId_inchi.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_chebi.csv","filename":"rat_glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_chebi.stat.csv","filename":"rat_glycan_xref_chebi.stat.csv"}}]},"checksum":"d2812bc6b861440a0268d48d1aacb234","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [PubChem CID] (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.976746","modified":"2019-11-14T16:00:09.822909","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000194) .  One-to-many PubChem CID to ChEBI mappings are resolved using InChI seqences downloaded from both (PubChem CID and ChEBI) databases. The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000186","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references(PUBCHEM CID)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (PubChem CID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_chebi.csv","filename":"rat_glycan_xref_chebi.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID  mapping file to extract the PubChem CID to ChEBI ID mapping from the PubChem FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glyco.csv","filename":"rat_glycan_xref_glyco.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glyco.stat.csv","filename":"rat_glycan_xref_glyco.stat.csv"}}]},"checksum":"06c2215b185ec1a4266df63dc41ec145","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycO (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.979439","modified":"2019-11-14T16:01:02.234520","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycO ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000188","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCO Cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glyco","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_glyco.csv","filename":"rat_glycan_xref_glyco.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5c8d509ef5c47b31f988a256"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"efseq_protein_all_10090.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_refseq.stat.csv","filename":"mouse_protein_function_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"41fa1d9fcccf24e1d6a8fbf4e6a972ed","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Function (NCBI Refseq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-03-16T15:38:06.344586","modified":"2020-04-10T12:44:03.077091","version":"1.7.9"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"},{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}],"prerequisite":[],"description":"The script extract-from-gp.py extracts protein function information from NCBI RefSeq gpff format files and maps it to the UniProtKb canonical accessions for a final dataset output in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Function (NCBI RefSeq) dataset contains biological function annotaion of mouse [taxid:10090] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000134"}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/database_accession_2019_02_07_03_58_16.tsv","filename":"database_accession_2019_02_07_03_58_16.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_chebi_from_kegg.csv","filename":"rat_glycan_xref_chebi_from_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_chebi_from_kegg.stat.csv","filename":"rat_glycan_xref_chebi_from_kegg.stat.csv"}}]},"checksum":"2aca0f267ced8053c784dedb8be3fc03","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [KEGG] (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.978103","modified":"2019-11-14T16:00:47.290217","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to KEGG glycan ID mapping (https://data.glygen.org/GLYDS000192) . The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000187","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references (KEGG GLYCAN)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (KEGG Glycan ID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_chebi_from_kegg.csv","filename":"rat_glycan_xref_chebi_from_kegg.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to KEGG glycan  mapping file to extract the KEGG Glycan ID to ChEBI ID mapping from the ChEBI FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glycomedb.csv","filename":"rat_glycan_xref_glycomedb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glycomedb.stat.csv","filename":"rat_glycan_xref_glycomedb.stat.csv"}}]},"checksum":"6d498d529ceff8300ebfa65f258a5d12","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycomeDB (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.980960","modified":"2019-11-14T16:01:20.596812","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycomeDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/"],"bco_id":"http://data.glygen.org/GLY_000189","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycomeDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycomeDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_glycomedb.csv","filename":"rat_glycan_xref_glycomedb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f66e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_properties.csv","filename":"rat_glycan_properties.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_properties.stat.csv","filename":"rat_glycan_properties.stat.csv"}}]},"checksum":"46262f5960c27d177fbd3664f60c0e07","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Properties (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.960689","modified":"2019-11-14T15:56:39.121619","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides information on the glycan properties such as mass, permethlyated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000175","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_properties.csv","filename":"rat_glycan_properties.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f673"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_smiles_isomeric.csv","filename":"rat_glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_sequences_smiles_isomeric.stat.csv","filename":"rat_glycan_sequences_smiles_isomeric.stat.csv"}}]},"checksum":"0c03a8dcbb86ee993761f46fe0a26ca9","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.967764","modified":"2019-11-14T15:58:18.360098","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000194). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000180","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_sequences_smiles_isomeric.csv","filename":"rat_glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glyconnect.csv","filename":"rat_glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glyconnect.stat.csv","filename":"rat_glycan_xref_glyconnect.stat.csv"}}]},"checksum":"84670aa08bb6449ddeb87b891e4f0f3c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.982312","modified":"2019-11-14T16:01:34.668690","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"bco_id":"http://data.glygen.org/GLY_000190","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_glyconnect.csv","filename":"rat_glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glycosciencesde.csv","filename":"rat_glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_glycosciencesde.stat.csv","filename":"rat_glycan_xref_glycosciencesde.stat.csv"}}]},"checksum":"b34de005569f88a989550cf0dad0a762","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.983665","modified":"2019-11-14T16:01:50.707564","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"bco_id":"http://data.glygen.org/GLY_000191","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_glycosciencesde.csv","filename":"rat_glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f684"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_citations_glytoucan.csv","filename":"mouse_glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_citations_glytoucan.stat.csv","filename":"mouse_glycan_citations_glytoucan.stat.csv"}}]},"checksum":"4c536ec189c371259d19882b26168cbf","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Citations (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.991803","modified":"2019-11-14T16:03:41.019583","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database. The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000197","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_citations_glytoucan.csv","filename":"mouse_glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f67f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_kegg.csv","filename":"rat_glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_kegg.stat.csv","filename":"rat_glycan_xref_kegg.stat.csv"}}]},"checksum":"0c11ecddc99fd7a5be066e2b70845e3f","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.985013","modified":"2019-11-14T16:02:05.286721","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"bco_id":"http://data.glygen.org/GLY_000192","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_kegg.csv","filename":"rat_glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f685"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_monosaccharide_composition.csv","filename":"mouse_glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_monosaccharide_composition.stat.csv","filename":"mouse_glycan_monosaccharide_composition.stat.csv"}}]},"checksum":"c1d2e3b0cda628fdc91f57ead7c14c5c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide Composition (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.993150","modified":"2019-11-14T16:03:53.027278","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans  (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000198","bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_monosaccharide_composition.csv","filename":"mouse_glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f686"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_glycam_iupac.csv","filename":"mouse_glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_glycam_iupac.stat.csv","filename":"mouse_glycan_sequences_glycam_iupac.stat.csv"}}]},"checksum":"b46426f05fafbcb60d16e5b66f62e02d","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GLYCAM IUPAC (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.994593","modified":"2019-11-14T16:04:13.023185","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://dev.glycam.org/"],"bco_id":"http://data.glygen.org/GLY_000199","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_glycam_iupac.csv","filename":"mouse_glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f687"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_glycoct.csv","filename":"mouse_glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_glycoct.stat.csv","filename":"mouse_glycan_sequences_glycoct.stat.csv"}}]},"checksum":"0454ee512e463c5538cad5184e63f775","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GlycoCT(Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.995996","modified":"2019-11-14T16:04:31.940497","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145).  Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000200","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_glycoct.csv","filename":"mouse_glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f682"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_unicarbdb.csv","filename":"rat_glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_unicarbdb.stat.csv","filename":"rat_glycan_xref_unicarbdb.stat.csv"}}]},"checksum":"b8c6e0b696974d01a76eca301511f9df","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.989162","modified":"2019-11-14T16:03:08.537694","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"bco_id":"http://data.glygen.org/GLY_000195","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_unicarbdb.csv","filename":"rat_glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f680"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_pdb.csv","filename":"rat_glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_pdb.stat.csv","filename":"rat_glycan_xref_pdb.stat.csv"}}]},"checksum":"c8aacec51ccfd2578e85a846209cfe48","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.986361","modified":"2019-11-14T16:02:26.355901","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"bco_id":"http://data.glygen.org/GLY_000193","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_pdb.csv","filename":"rat_glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f688"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_inchi.csv","filename":"mouse_glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_inchi.stat.csv","filename":"mouse_glycan_sequences_inchi.stat.csv"}}]},"checksum":"7293290bf230020e7cc145ffb3208004","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences InchI (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:41.997389","modified":"2019-11-14T16:04:46.497227","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the InChI key and glycan sequences in InChI format  for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000217). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000201","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_inchi.csv","filename":"mouse_glycan_sequences_inchi.csv"}],"prerequisite":[],"description":"The GlyTouCan Ac. to PubChem CID mapping file was used download .sdf PubChem compound files from PubChem CID ftp and a python script was used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f681"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_pubchem.csv","filename":"rat_glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_pubchem.stat.csv","filename":"rat_glycan_xref_pubchem.stat.csv"}}]},"checksum":"ab24e40449b37dc6a206fa75b490ba9c","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.987846","modified":"2019-11-14T16:02:50.600901","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"bco_id":"http://data.glygen.org/GLY_000194","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_pubchem.csv","filename":"rat_glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f683"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_unicarbkb.csv","filename":"rat_glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_glycan_xref_unicarbkb.stat.csv","filename":"rat_glycan_xref_unicarbkb.stat.csv"}}]},"checksum":"fd3d35f0646494c0cec8a25461695732","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB (Rat GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.990495","modified":"2019-11-14T16:03:24.444983","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Rat GlyTouCan accession master list (https://data.glygen.org/GLYDS000146). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000196","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/rat_glycan_xref_unicarbkb.csv","filename":"rat_glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb1f5c47b2eda74f689"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_iupac_extended.csv","filename":"mouse_glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_iupac_extended.stat.csv","filename":"mouse_glycan_sequences_iupac_extended.stat.csv"}}]},"checksum":"30141fcbdaee7ca26bab2eb122f8324a","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences IUPAC Extended (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:41.998750","modified":"2019-11-14T16:05:02.026051","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000202","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_iupac_extended.csv","filename":"mouse_glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script was used to process the data to generate the final output file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_wurcs.csv","filename":"mouse_glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_wurcs.stat.csv","filename":"mouse_glycan_sequences_wurcs.stat.csv"}}]},"checksum":"c634767350fcb5ed6dfec7bcf0a8ea7a","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences WURCS (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.003021","modified":"2019-11-14T16:05:39.734558","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000204","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_wurcs.csv","filename":"mouse_glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_smiles_isomeric.csv","filename":"mouse_glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_sequences_smiles_isomeric.stat.csv","filename":"mouse_glycan_sequences_smiles_isomeric.stat.csv"}}]},"checksum":"6a8183310b3e05808ba5252f6315d382","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:42.000249","modified":"2019-11-14T16:05:23.695250","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000217). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000203","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_sequences_smiles_isomeric.csv","filename":"mouse_glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_carbbank.csv","filename":"mouse_glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_carbbank.stat.csv","filename":"mouse_glycan_xref_carbbank.stat.csv"}}]},"checksum":"2f2690259ef89a86915ca978b87e6fc7","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.007628","modified":"2019-11-14T16:06:50.460058","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"bco_id":"http://data.glygen.org/GLY_000207","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_carbbank.csv","filename":"mouse_glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_taxonomy.csv","filename":"mouse_glycan_taxonomy.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_taxonomy.stat.csv","filename":"mouse_glycan_taxonomy.stat.csv"}}]},"checksum":"f7f21f13abad9b98b86449f172d32918","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Taxonomy (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.004458","modified":"2019-11-14T16:06:19.312721","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides NCBI TaxID for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy"],"bco_id":"http://data.glygen.org/GLY_000205","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_taxonomy.csv","filename":"mouse_glycan_taxonomy.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_bcsdb.csv","filename":"mouse_glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_bcsdb.stat.csv","filename":"mouse_glycan_xref_bcsdb.stat.csv"}}]},"checksum":"670cab3a812991e8be434f550fb58a5d","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.005944","modified":"2019-11-14T16:06:34.728644","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"bco_id":"http://data.glygen.org/GLY_000206","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_bcsdb.csv","filename":"mouse_glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f691"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/database_accession_2019_02_07_03_58_16.tsv","filename":"database_accession_2019_02_07_03_58_16.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_chebi_from_kegg.csv","filename":"mouse_glycan_xref_chebi_from_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_chebi_from_kegg.stat.csv","filename":"mouse_glycan_xref_chebi_from_kegg.stat.csv"}}]},"checksum":"b23e3fbf2f7e52d387c1a59e208ac779","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [KEGG ID] (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:42.011810","modified":"2019-11-14T16:07:40.107077","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to KEGG glycan ID mapping (https://data.glygen.org/GLYDS000215) . The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000210","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references(KEGG GLYCAN)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (KEGG Glycan ID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycan_xref_kegg.csv","filename":"human_glycan_xref_kegg.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_chebi_from_kegg.csv","filename":"mouse_glycan_xref_chebi_from_kegg.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to KEGG glycan  mapping file to extract the KEGG Glycan ID to ChEBI ID mapping from the ChEBI FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f692"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glyco.csv","filename":"mouse_glycan_xref_glyco.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glyco.stat.csv","filename":"mouse_glycan_xref_glyco.stat.csv"}}]},"checksum":"791ae49e21a453867a0d5faeca8be8d7","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycO (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.013217","modified":"2019-11-14T16:07:55.036101","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycO ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000211","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCO Cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glyco","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_glyco.csv","filename":"mouse_glycan_xref_glyco.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f693"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glycomedb.csv","filename":"mouse_glycan_xref_glycomedb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glycomedb.stat.csv","filename":"mouse_glycan_xref_glycomedb.stat.csv"}}]},"checksum":"bd0c0eca19d83a5d7147bac306f54e2a","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycomeDB (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.014602","modified":"2019-11-14T16:08:09.358625","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlycomeDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/"],"bco_id":"http://data.glygen.org/GLY_000212","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycomeDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycomeDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_glycomedb.csv","filename":"mouse_glycan_xref_glycomedb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f694"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glyconnect.csv","filename":"mouse_glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glyconnect.stat.csv","filename":"mouse_glycan_xref_glyconnect.stat.csv"}}]},"checksum":"c899292cf24a510fd6f969e1ad1b7c48","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.016014","modified":"2019-11-14T16:08:22.402179","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"bco_id":"http://data.glygen.org/GLY_000213","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_glyconnect.csv","filename":"mouse_glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f690"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2019_05_06_10_23_08","filename":"CID-Synonym-filtered_2019_05_06_10_23_08"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/chebiId_inchi.tsv","filename":"chebiId_inchi.tsv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_chebi.csv","filename":"mouse_glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_chebi.stat.csv","filename":"mouse_glycan_xref_chebi.stat.csv"}}]},"checksum":"64a9edf4328c02c2dd3f866a1af9a9cf","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [PubChem CID] (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-08-13T19:58:42.010421","modified":"2019-11-14T16:07:23.416743","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000217) .  One-to-many PubChem CID to ChEBI mappings are resolved using InChI seqences downloaded from both (PubChem CID and ChEBI) databases. The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000209","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references(PUBCHEM CID)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (PubChem CID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_chebi.csv","filename":"mouse_glycan_xref_chebi.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID  mapping file to extract the PubChem CID to ChEBI ID mapping from the PubChem FTP download file."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f695"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glycosciencesde.csv","filename":"mouse_glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_glycosciencesde.stat.csv","filename":"mouse_glycan_xref_glycosciencesde.stat.csv"}}]},"checksum":"412af215a7f62d5601759e2521cb95e8","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.017433","modified":"2019-11-14T16:08:39.115477","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"bco_id":"http://data.glygen.org/GLY_000214","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_glycosciencesde.csv","filename":"mouse_glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f696"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_kegg.csv","filename":"mouse_glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_kegg.stat.csv","filename":"mouse_glycan_xref_kegg.stat.csv"}}]},"checksum":"ebfdcd62e84fafb886c95d4ad7e472d3","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.019028","modified":"2019-11-14T16:08:53.399939","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"bco_id":"http://data.glygen.org/GLY_000215","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_kegg.csv","filename":"mouse_glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f697"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_pdb.csv","filename":"mouse_glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_pdb.stat.csv","filename":"mouse_glycan_xref_pdb.stat.csv"}}]},"checksum":"759b151f77314ff7fb3a7c82ab674186","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.020484","modified":"2019-11-14T16:09:15.311414","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"bco_id":"http://data.glygen.org/GLY_000216","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_pdb.csv","filename":"mouse_glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f698"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_pubchem.csv","filename":"mouse_glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_pubchem.stat.csv","filename":"mouse_glycan_xref_pubchem.stat.csv"}}]},"checksum":"95cf0aa960e6346043851044f2c394d3","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.021917","modified":"2019-11-14T16:09:41.822135","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"bco_id":"http://data.glygen.org/GLY_000217","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_pubchem.csv","filename":"mouse_glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d6845c1f5c47b50012e27b5"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"xavierh@email.gwu.edu"}],"created":"2019-08-29T17:38:09.605382","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000220"}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f699"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_unicarbdb.csv","filename":"mouse_glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_unicarbdb.stat.csv","filename":"mouse_glycan_xref_unicarbdb.stat.csv"}}]},"checksum":"db75183fc55ba72774d14dcbe87425fc","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.023294","modified":"2019-11-14T16:10:06.579875","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"bco_id":"http://data.glygen.org/GLY_000218","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_unicarbdb.csv","filename":"mouse_glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f69a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_unicarbkb.csv","filename":"mouse_glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_unicarbkb.stat.csv","filename":"mouse_glycan_xref_unicarbkb.stat.csv"}}]},"checksum":"1c378d46c7fdf73622be66a1d2cd3bcd","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.024662","modified":"2019-11-14T16:10:37.441501","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000219","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_unicarbkb.csv","filename":"mouse_glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d534eb2f5c47b2eda74f68f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_cfg.csv","filename":"mouse_glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_xref_cfg.stat.csv","filename":"mouse_glycan_xref_cfg.stat.csv"}}]},"checksum":"4233748ed8809e80a8e1df00d1318c61","provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG (Mouse GlyTouCan Masterlist)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-08-13T19:58:42.009025","modified":"2019-11-14T16:07:05.359789","version":"1.7.9"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-glycan-dataset.py","filename":"make-glycan-dataset.py"}}]},"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the Mouse GlyTouCan accession master list (https://data.glygen.org/GLYDS000145). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"bco_id":"http://data.glygen.org/GLY_000208","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"bco_spec_version":"1.3.0","description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make_glycan_dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-08-28T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycan_xref_cfg.csv","filename":"mouse_glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}]}
{"_id":{"$oid":"5d72a02ef5c47b0f4342334f"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.950487","modified":"2020-04-10T11:52:06.379367","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_recnames.csv","filename":"rat_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_recnames.stat.csv","filename":"rat_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for rat [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000222","checksum":"32c35823ff5b5bbe436c980f20e29f1a"}
{"_id":{"$oid":"5d715553f5c47b18c064d651"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}},{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.1.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.2.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.stats.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"991ab7dae241b906fc07aff5ff530ea2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation sites - UniCarbKB [Rat proteins]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-09-05T14:34:59.005886","modified":"2020-05-01T15:21:53.655183","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":0,"version":"","input_list":[{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/merge_human_rat_mouse_gps_06022020_130220.csv","filename":"merge_human_rat_mouse_gps_06022020_130220.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"},{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"2020-03-13T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/rat_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.1.log"},{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/rat_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"rat_proteoform_glycosylation_sites_unicarbkb.2.log"}],"prerequisite":[],"description":"The input file was received directly from the author (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (human_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (human_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_pmid: The PubMed ID value is zero or blank. 10) no_glycan_invalid_aa: row has no glycan and amino acid is invalid. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-13T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000244)."],"bco_id":"http://data.glygen.org/GLY_000221"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423350"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.951602","modified":"2020-04-10T11:42:38.341131","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_go_annotation.csv","filename":"human_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_go_annotation.stat.csv","filename":"human_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Gene Ontology (GO) dataset contains human [taxid:9606] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000223","checksum":"4e5f22ec6edc3fbf7a7fd436c67e82db"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423353"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (RCSB PDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Jasmine Young","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["contributedBy"],"name":"Chenghua Shao","email":"chenghua@rcsb.rutgers.edu"}],"created":"2019-09-06T14:06:38.954510","modified":"2020-04-10T11:52:41.075559","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details","filename":"N-linked-ARG-details"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN-details","filename":"N-linked-ASN-details"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details","filename":"O-linked-ASP-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details","filename":"O-linked-GLU-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details","filename":"O-linked-SER-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details","filename":"O-linked-THR-details"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details","filename":"O-linked-TYR-details"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs and PDB glycosite from the input .tsv files and maps it to the corresponding UniProtKB accessions and position using the coordinate file downloaded from the SIFTS database using the formula:(SP_BEG-RES_BEG)+ PDB-Position)]. The script also validates the UniProtKB glycosite (amino acid + position) with the corresponding fasta sequences downloaded from UniProtKB."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG-details","filename":"N-linked-ARG-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP-details","filename":"O-linked-ASP-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU-details","filename":"O-linked-GLU-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER-details","filename":"O-linked-SER-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR-details","filename":"O-linked-THR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR-details","filename":"O-linked-TYR-details"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb_chain_uniprot_2018_11_8_11_44_50.csv","filename":"pdb_chain_uniprot_2018_11_8_11_44_50.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.stat.csv","filename":"rat_proteoform_glycosylation_sites_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Glycosylation Sites (RCSB PDB) dataset contains rat [taxid:11106] proteins glycosites mapped from the associated RCSB PDB Id's using SIFTS database (https://www.ebi.ac.uk/pdbe/docs/sifts/). The glycosylation data (PDB ID, GlycoSite, Chain ID, Sugar (first link)) was retrieved from RCSB group. [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"bco_id":"http://data.glygen.org/GLY_000226","checksum":"613f11f077999a838157860d6208a742"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423354"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref ChEMBL","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.955413","modified":"2020-04-10T11:53:06.833357","version":"1.7.9"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_chembl.csv","filename":"rat_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_chembl.stat.csv","filename":"rat_protein_xref_chembl.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniprotKB Xref ChEMBL contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties"],"bco_id":"http://data.glygen.org/GLY_000227","checksum":"659beef9cae1418b945feca5d8a2a650"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423351"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.952590","modified":"2020-04-10T11:52:23.712035","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000224","checksum":"b2d488a7318be8e2db0585cf1de302e7"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423355"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Signal Peptide","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-19T16:00:40.680035","modified":"2020-04-10T11:43:36.288283","version":"1.7.9"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_annotation.csv","filename":"human_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_peptidesequences.fasta","filename":"human_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_cleavedsequences.fasta","filename":"human_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_fullsequences.fasta","filename":"human_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signalp_annotation.stat.csv","filename":"human_protein_signalp_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Protein Signal Peptide dataset contains human [taxid:9606] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes processed protein sequence’s files in fasta format viz. signal peptide squence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000228","checksum":"e4b8059d7a9fe2e1af013607668656ce"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423352"},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Glycosylation Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"}],"created":"2019-09-06T14:06:38.953629","modified":"2020-05-07T16:31:51.893274","version":"1.7.9"},"description_domain":{"keywords":["disease","HPO","OMIM","Congenital Disorders of Glycosylation (CDG)","Monarch Initiative"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"prerequisite":[],"description":"The script extracts the OMIM phenotypes for UniProtKB accessions and disease information from human_glyco-phenotype_disease_curation_list_v12-18-74.csv. The script maps the UniProtKB accessions to the UniprotKB canonical accessions."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_glyco_disease.stat.csv","filename":"human_protein_glyco_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Diseases dataset contains list of human [taxid:9606] diseases as described by OMIM and Monarch Initiave database ","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The Monarch Initiative is focused primarily on phenotype-related resources and brings in data associated with those phenotypes so that the users can begin to make connections among other biological entities of interest.","If you are using this dataset please give proper attribution to OMIM, Monarch Initiative, EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000225","checksum":"fcd713d390a9ff969fb191790a960b0d"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423356"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Oma cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OMA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.957228","modified":"2020-04-10T11:53:38.323623","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OMA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_oma.stat.csv","filename":"rat_protein_xref_oma.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref OMA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes."],"bco_id":"http://data.glygen.org/GLY_000229","checksum":"47cc38b6b6a68b7f14969136b253db3a"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335a"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.961010","modified":"2020-04-10T12:45:01.709793","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_intact.csv","filename":"mouse_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_intact.stat.csv","filename":"mouse_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Mouse UniProtKB Xref IntAct dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal"],"bco_id":"http://data.glygen.org/GLY_000233","checksum":"4102a5f3af14b2d2a68b47b173f599cf"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423359"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cazy cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CAZy","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.960116","modified":"2020-04-10T11:54:11.677966","version":"1.7.9"},"description_domain":{"keywords":["carbohydrate family","CAZy","glycosyltransferase","glycohydrolase"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cazy.csv","filename":"rat_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cazy.stat.csv","filename":"rat_protein_xref_cazy.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniprotKB Xref CAZy contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers.  The dataset is derived from 2019-0 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","CAZy is a database of Carbohydrate-Active enZymes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates."],"bco_id":"http://data.glygen.org/GLY_000232","checksum":"57dfb80831940a268253a3002e21668f"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335b"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Cdd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref CDD","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.961924","modified":"2020-04-10T11:55:22.166613","version":"1.7.9"},"description_domain":{"keywords":["protein domains","CDD","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cdd.csv","filename":"rat_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_cdd.stat.csv","filename":"rat_protein_xref_cdd.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref CDD contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins."],"bco_id":"http://data.glygen.org/GLY_000234","checksum":"e93a35f0c79a5fd06ab6f8b968e89cff"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335c"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.962804","modified":"2020-04-10T12:45:40.582715","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_refseq.csv","filename":"mouse_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_refseq.stat.csv","filename":"mouse_protein_citations_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Mouse Protein Citations (RefSeq) datasets contains mouse [taxid:10090] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000235","checksum":"8b3f130391f61f05022faa6626c4a85a"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335d"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.963796","modified":"2020-04-10T11:44:28.847200","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_intact.csv","filename":"human_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_intact.stat.csv","filename":"human_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human UniProtKB Xref IntAct dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"bco_id":"http://data.glygen.org/GLY_000236","checksum":"bf60fe4a4add926b646b8ca4ee08af26"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335e"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Transcript Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Transcript Locus (Ensembl Transcript coordinates)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.964793","modified":"2020-04-10T11:55:37.315722","version":"1.7.9"},"description_domain":{"keywords":["transcript locus","ensembl transcript id","ensembl peptide id","chromosome","Ensembl"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_transcriptlocus.csv","filename":"rat_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_transcriptlocus.stat.csv","filename":"rat_protein_transcriptlocus.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Ensembl Transcript Locus (Transcript coordinates)s contains UniProtKB rat [taxid:10116] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts's start and end position The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000237","checksum":"f245e6f3beaabf946882d458122766e9"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342335f"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref NCBI Gene","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.965792","modified":"2020-04-10T11:56:11.287893","version":"1.7.9"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_geneid.stat.csv","filename":"rat_protein_xref_geneid.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref NCBI Gene dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"bco_id":"http://data.glygen.org/GLY_000238","checksum":"6dea44d2a9e872ffe610bd2980ca4304"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423360"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.966707","modified":"2020-04-10T11:44:59.698908","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosylation_motifs.csv","filename":"human_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosylation_motifs.stat.csv","filename":"human_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for human [taxid:9606] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000239","checksum":"3339df0f7b3ecfabd01fac2d66b8cdc8"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423361"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.967574","modified":"2020-04-10T11:56:24.147942","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.stat.csv","filename":"rat_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Canonical Sequences (UniProtKB) dataset contains rat [taxid:10116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000240","checksum":"9303b5fa868c51ec200fea1c8922c86e"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423362"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.968442","modified":"2020-04-10T11:56:50.003593","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_uniprotkb.csv","filename":"rat_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_uniprotkb.stat.csv","filename":"rat_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Information dataset contains rat [taxid:10116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000241","checksum":"f462cae357bd332d064d624dc125e203"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423363"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.969307","modified":"2020-04-10T11:57:01.910679","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uuniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_go_annotation.csv","filename":"rat_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_go_annotation.stat.csv","filename":"rat_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Gene Ontology (GO) dataset contains rat [taxid:10116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000242","checksum":"8e318aa5047a0747ac932bb329d334b0"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423357"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Congenital Disorders of Glycosylation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"},{"orcid":"","affiliation":"MGI","contribution":["authoredBy"],"name":"Cynthia Smith","email":"cynthia.Smith@jax.org"},{"orcid":"","affiliation":"MGI","contribution":[],"name":"Judith Blake","email":"judith.Blake@jax.org"}],"created":"2019-09-06T14:06:38.958276","modified":"2020-04-10T11:43:57.908911","version":"1.7.9"},"description_domain":{"keywords":["congenital disorders of glycosylation","MGI","Monarch Initiative","phenotype"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_cdg_disease.csv","filename":"human_protein_cdg_disease.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_cdg_disease.csv","filename":"human_protein_cdg_disease.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_cdg_disease.csv","filename":"human_protein_cdg_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_cdg_disease.stat.csv","filename":"human_protein_cdg_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Congenital Disorders of Glycosylation dataset contains a list of congenital disorders of glycosylation mapped to human [taxid:9606] UniProtKB accessions. The dataset also contains mouse orthologs and links to phenotype page on MGI. If you use this dataset please provide proper attribution to Monarch Initiative and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000230","checksum":"7d733150e7fea7d765d5ae94c03caff3"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423358"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.959200","modified":"2020-04-10T11:53:53.248846","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Phosphorylation Sites (UniProtKB) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000231","checksum":"cec8c1d400d70a323c8e85abc86c4ad8"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423364"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.970158","modified":"2020-04-10T11:57:30.660847","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlistcsv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_interpro.csv","filename":"rat_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_interpro.stat.csv","filename":"rat_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniprotKB Xref InterPro contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000243","checksum":"c346998a1b362cd9ced36fb50c0bf332"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423368"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.973677","modified":"2020-04-10T11:58:59.288321","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_function_uniprotkb.csv","filename":"rat_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_function_uniprotkb.stat.csv","filename":"rat_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Function (UniProtKB) dataset contains biological function annotation for rat [taxid:10116] protein accesions from the UniProtKB database. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000247","checksum":"02357bbf1b043a525ccfc3809f7a4c4b"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423369"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.974540","modified":"2020-04-10T11:59:22.752887","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_maserlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pfam.csv","filename":"rat_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pfam.stat.csv","filename":"rat_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref Pfam contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000248","checksum":"cd5003ba49c9a23b2fc3db073dc36016"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423367"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Ontology (DO)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Retired Disease Ontology Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.972763","modified":"2019-09-12T16:19:09.007007","version":"1.7.9"},"description_domain":{"keywords":["ICD9","ICD10","Disease Ontology","OMIM","DOID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/human_do_061419.owl","filename":"human_do_061419.owl"}],"output_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/domap.csv","filename":"domap.csv"}],"prerequisite":[],"description":"The script the DOID, DO name  and cross-reference mapping between DOID and other databases such as ICD 9, ICD 10, UMLS, MeSH, Kegg. The source owl file is loaded as triples in into the triplestore prior to the extraction"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_do_061419.owl","filename":"human_do_061419.owl"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/domap.csv","filename":"domap.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/domap.stat.csv","filename":"domap.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Disease Ontology Mapping dataset contains Disease Ontology IDs, name and cross-refereces to KEGG, ICD10CMID, ICD9CMID, MESH ID, OMIM, UMLSID. If you use this dataset please provide proper attribution to Disease Ontology and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000246","checksum":""}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336c"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteoform Citations (UniCarbKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.978102","modified":"2020-04-10T12:00:35.900590","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","UniCarbKB","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_unicarbkb.csv","filename":"rat_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_unicarbkb.csv","filename":"rat_proteoform_citations_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_unicarbkb.stat.csv","filename":"rat_proteoform_citations_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Proteoform Citations (UniCarbKB) contains rat [taxid:10116] publication information of glycoproteins from UniCarbKB. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID from UniCarbKB. The dataset is contributed by UniCarbKB and processed by GlyGen. If you use this dataset please provide proper attribution to UniCarbKB and GlyGen [UniCarbKB - https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/GLY_000251","checksum":"da2870088aaacf5301455ca866078c2c"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336d"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.979310","modified":"2020-04-10T12:45:59.669796","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_go_annotation.csv","filename":"mouse_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_go_annotation.stat.csv","filename":"mouse_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Mouse Gene Ontology (GO) dataset contains mouse [taxid:10090] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000252","checksum":"4c4116b1f2e80d287e3818ff0cf05222"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336b"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Kegg Pathway cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref KEGG PATHWAY","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.976805","modified":"2020-04-10T12:00:10.191743","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","KEGG Pathway","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_kegg.csv","filename":"rat_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_kegg.stat.csv","filename":"rat_protein_xref_kegg.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref KEGG PATHWAY contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks"],"bco_id":"http://data.glygen.org/GLY_000250","checksum":"3b93a5e10410cf6ed8d5453aeae8bfc9"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336a"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Function (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.975527","modified":"2020-04-10T11:59:41.589685","version":"1.7.9"},"description_domain":{"keywords":["protein function","NCBI RefSeq","geneRIF","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the geneRIFs that contain protein function. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_function_refseq.csv","filename":"rat_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_function_refseq.stat.csv","filename":"rat_protein_function_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Function (NCBI RefSeq) dataset contains biological function annotaion of rat [taxid:10116] genes from GeneRIF section in the NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000249","checksum":"cc9f3df76057996a785870ba6a13e244"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423370"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.982193","modified":"2020-04-10T12:02:18.968682","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB","protein alternative name"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10116-rattus-norvegicus-2019-05.nt","filename":"uniprot-proteome-10116-rattus-norvegicus-2019-05.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.stat.csv","filename":"rat_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Isoform sequences (UniProtKB) dataset contains rat [taxid:10116] protein fasta sequences for the rat isoform accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000255","checksum":"a5ef2bd7af61989bc6396c531805865c"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336f"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.981217","modified":"2020-04-10T12:46:17.110364","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Mouse Phosphorylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000254","checksum":"a09fcb1abf99ddbda83d8cbfa0bcc31a"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342336e"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.980261","modified":"2020-04-10T12:01:50.512815","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv","filename":"rat_protein_blacklisted_pmids_uniprotkb.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv","filename":"rat_protein_blacklisted_pmids_uniprotkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_uniprotkb.csv","filename":"rat_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_uniprotkb.stat.csv","filename":"rat_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Citations dataset contains publication information for rat [taxid:10116] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2wwwdata/compiled/rat_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000253","checksum":"312b7c73e7a885d121c475c7ae583b2c"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423366"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.971888","modified":"2020-04-10T11:58:31.122542","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_uniprot-proteome-rattus-norvegicus.ntcsv","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pdb.csv","filename":"rat_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pdb.stat.csv","filename":"rat_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref PDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000245","checksum":"363fd0af6d046c5d7b9f6aed586d156e"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423365"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.971023","modified":"2020-04-10T11:58:01.582234","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.stat.csv","filename":"rat_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Proteome Masterlist dataset contains rat [taxid:10116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000244","checksum":"b466a03bd80828f9a89a6ede84abbfcb"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423375"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactome cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Reactome","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.987144","modified":"2020-04-10T12:03:36.049296","version":"1.7.9"},"description_domain":{"keywords":["pathways","reactions","REACTOME","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_reactome.csv","filename":"rat_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_reactome.stat.csv","filename":"rat_protein_xref_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref Reactome contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database."],"bco_id":"http://data.glygen.org/GLY_000260","checksum":"96c1e8e6e21cc31ca0c8a3b2dca09c2c"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423373"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Homologs","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Homolog Clusters","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-09-06T14:06:38.985197","modified":"2020-04-29T23:01:49.049875","version":"1.7.9"},"description_domain":{"keywords":["homologs","orthologs","MGI","OMA"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/mgi_homologs.csv","filename":"mgi_homologs.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"rat_human_orthologs_oma_release-24_061319_03-45pm.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}],"output_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/homolog_clusters.csv","filename":"homolog_clusters.csv"}],"prerequisite":[],"description":"The script extracts the human, mouse and rat homologs from the input files and using xref files maps the identifiers to UniProtKB canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mgi_orthologs_hom_allorganism_release6.14_060419_12-33pm.csv","filename":"mgi_orthologs_hom_allorganism_release6.14_060419_12-33pm.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv","filename":"mouse_human_orthologs_oma_release-24_061319_03-45pm.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_human_orthologs_oma_release-24_061319_12-24pm.csv","filename":"rat_human_orthologs_oma_release-24_061319_12-24pm.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mgi_homologs.csv","filename":"mgi_homologs.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_geneid.csv","filename":"rat_protein_xref_geneid.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_oma.csv","filename":"rat_protein_xref_oma.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_homolog_clusters.stat.csv","filename":"protein_homolog_clusters.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Homolog Clusters dataset contains homologs of human [taxid: 9606], mouse [taxid:10090] and rat [taxid:10116] species mapped to UniProtKB canonical accessions. The homologs data is downloaded from OMA browser and MGI. If you use this dataset please provide proper attribution to MGI, OMA Browser and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000258","checksum":"42c8ea80b64611a46a742fed4f9a391f"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423374"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Unicarbkb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref UniCarbKB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.986196","modified":"2020-04-10T12:03:03.470087","version":"1.7.9"},"description_domain":{"keywords":["glycoprotein","glycan","UniCarbKB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to UniCarbKB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_unicarbkb.csv","filename":"rat_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_unicarbkb.stat.csv","filename":"rat_protein_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref UniCarbKB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to UniCarbKB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","UniCarbKB is an initiative that aims to promote the creation of an online information storage and search platform for glycomics and glycobiology research."],"bco_id":"http://data.glygen.org/GLY_000259","checksum":"280c6c481dcdaeef16810f6f72c24a07"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423371"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.983152","modified":"2020-04-10T11:45:37.582881","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_refseq.csv","filename":"human_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_refseq.stat.csv","filename":"human_protein_citations_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Protein Citations (RefSeq) datasets contains human [taxid:9606] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000256","checksum":"50fdbf747be65d7bd787069082b258c4"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423376"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Panther cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PANTHER","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.988053","modified":"2020-04-10T12:03:58.907916","version":"1.7.9"},"description_domain":{"keywords":["protein family","PANTHER","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_panther.csv","filename":"rat_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_panther.stat.csv","filename":"rat_protein_xref_panther.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref PANTHER contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products."],"bco_id":"http://data.glygen.org/GLY_000261","checksum":"dea03227098e81c284b276fa6838c425"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423377"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref PRO","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.988943","modified":"2020-04-10T12:04:32.713589","version":"1.7.9"},"description_domain":{"keywords":["protein ontology","PRO","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pro.csv","filename":"rat_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_pro.stat.csv","filename":"rat_protein_xref_pro.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniprotKB Xref PRO contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them."],"bco_id":"http://data.glygen.org/GLY_000262","checksum":"a5b91f9c43842bc8bfc355e7baeeda7c"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423378"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.989848","modified":"2020-04-10T12:04:56.865321","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_intact.csv","filename":"rat_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_intact.stat.csv","filename":"rat_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref IntAct dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"bco_id":"http://data.glygen.org/GLY_000263","checksum":"c33cfaf52416f40277e03800cc87e3ed"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423379"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.990766","modified":"2020-04-10T12:05:22.894637","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_refseq.csv","filename":"rat_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_refseq.stat.csv","filename":"rat_protein_citations_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Citations (RefSeq) datasets contains rat [taxid:10116] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000264","checksum":"9d8d06b29a71b05b13a288029952b0f3"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337a"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.991804","modified":"2020-04-10T12:05:45.412679","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_altnames.csv","filename":"rat_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_altnames.stat.csv","filename":"rat_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for rat [taxid:10116] proteins. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000265","checksum":"da9be224f5a2b71c87e071370a1f1e4c"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337b"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Bgee cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref Bgee","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.992721","modified":"2020-04-10T12:07:42.440257","version":"1.7.9"},"description_domain":{"keywords":["gene expression","Bgee","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_bgee.csv","filename":"rat_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_bgee.stat.csv","filename":"rat_protein_xref_bgee.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref Bgee dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."," Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets."],"bco_id":"http://data.glygen.org/GLY_000266","checksum":"3e49ac06e66dfe64077e39ebb27c3f1f"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423372"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Orthodb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref OrthoDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.984081","modified":"2020-04-10T12:59:50.777117","version":"1.7.9"},"description_domain":{"keywords":["orthologs","OrthoDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_orthodb.csv","filename":"rat_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_orthodb.stat.csv","filename":"rat_protein_xref_orthodb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniProtKB Xref OrthoDB contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology."],"bco_id":"http://data.glygen.org/GLY_000257","checksum":"3901780946b8fb81aaa39e22d4102eb2"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337c"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Coordinates","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Locus (Ensembl)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.993695","modified":"2020-04-10T12:08:06.119863","version":"1.7.9"},"description_domain":{"keywords":["gene coordinates","start position","end position","Ensembl","strand"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/sourceuniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genelocus.csv","filename":"rat_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genelocus.stat.csv","filename":"rat_protein_genelocus.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Gene Locus (Ensembl) contains rat [taxid:10116] UniProtKB canonical accessions mapped to the corresponding ENSEMBL Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000267","checksum":"79224aea12c0f65419799fc7a1d5f46a"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423380"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Retired","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-09-06T14:06:38.997376","modified":"2019-09-12T17:07:16.377677","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2019-05.nt","filename":"uniprot-proteome-10090-mus-musculus-2019-05.nt"}}],"output_subdomain":[]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000271","checksum":""}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337f"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref BRENDA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.996476","modified":"2020-04-10T12:08:43.749336","version":"1.7.9"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_brenda.csv","filename":"rat_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_brenda.stat.csv","filename":"rat_protein_xref_brenda.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat UniprotKB Xref BRENDA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"bco_id":"http://data.glygen.org/GLY_000270","checksum":"3f0348c5e029cd69fc387ca295adcff7"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423381"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.998256","modified":"2020-04-10T12:09:02.588363","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycosylation_motifs.csv","filename":"rat_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycosylation_motifs.stat.csv","filename":"rat_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for rat [taxid:10116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000272","checksum":"a29e55c68a6af11a0bcf3832a7e927ae"}
{"_id":{"$oid":"5d72a02ff5c47b0f43423383"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:39.000407","modified":"2020-04-10T11:46:19.167448","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Phosphorylation Sites (UniProtKB) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000274","checksum":"c624e50fc115430319ae0b006fc84e76"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423382"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Rgd cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RGD","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.999441","modified":"2020-04-10T12:09:35.932688","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Rat Genome Database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_rgd.csv","filename":"rat_protein_xref_rgd.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_rgd.stat.csv","filename":"rat_protein_xref_rgd.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to Rat Genome Database (RGD) accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. f you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen.","The Rat Genome Database (RGD) is the premier site for genetic, genomic, phenotype, and disease data generated from rat research"],"bco_id":"http://data.glygen.org/GLY_000273","checksum":"679374ae90d277134ed29fb0e728373e"}
{"_id":{"$oid":"5d72a02ff5c47b0f43423385"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat UniProtKB Xref RefSeq","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:39.002473","modified":"2020-04-10T12:10:48.820805","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.stat.csv","filename":"rat_protein_xref_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat [taxid:10116] UniprotKB Xref RefSeq contains rat UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"bco_id":"http://data.glygen.org/GLY_000276","checksum":"57efe59c4850551245d751e3d819b10c"}
{"_id":{"$oid":"5d72bfe7f5c47b183c0ceec2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"","filename":""}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"8e7dc484c15a013dfdbca84ec10126db","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health & Science University","contribution":["authoredBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"}],"created":"2019-09-06T16:21:59.896067","modified":"2020-05-07T16:31:24.495023","version":"1.7.9"},"description_domain":{"keywords":["glycosylation diseases","MONDO ID","Monarch Initiative"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"output_list":[{"access_time":"","uri":"","filename":""}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycosylation Diseases dataset contains human [taxid:9606] glycosylations diseases mapped to UniProtKB canonical accessions from Monarch Initiative database. If you use this dataset please provide proper attribution to Monarch Initiative and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000277"}
{"_id":{"$oid":"5d78134925f6e85f83ba0d10"},"bco_id":"http://data.glygen.org/bco_id","extension_domain":{"dataset_categories":[{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"bco_spec_version":"1.3.0","checksum":"","execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script_driver":"manual"},"provenance_domain":{"version":"1.7.9","license":"https://creativecommons.org/licenses/by/4.0/"}}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337d"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Tyr O-Linked Glycosylation Sites","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.994596","modified":"2020-08-19T15:56:55.296314","version":"1.7.9"},"description_domain":{"keywords":["tyrosine","o-linked glycosylation","glycosylation sites"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position of glycosylation against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Human Tyr O-Linked Glycosylation Sites dataset contains human [taxid:9606] UniProtKB accessions that are Tyr O-Linked Glycosylated. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. If you use this dataset please provide proper attribution to GlyGen"],"bco_id":"http://data.glygen.org/GLY_000268","checksum":"5c087839901728f3f91e807acc3b9db4"}
{"_id":{"$oid":"5d72a02ef5c47b0f4342337e"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T14:06:38.995531","modified":"2020-04-10T12:46:48.152167","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosylation_motifs.csv","filename":"mouse_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosylation_motifs.stat.csv","filename":"mouse_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Mouse N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for mouse [taxid:10090] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKb accessions. If you use this dataset please provide proper attribution to GlyGen. The dataset is derived form 2019-09 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000269","checksum":"926eae881dabd3753f33df45b9d2bf44"}
{"_id":{"$oid":"5d72d1d8f5c47b1ffae82a8b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ntdata.stat.csv","filename":"rat_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4809e8d5cdcaccc86d4e674b3a21befa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-09-06T17:38:32.808468","modified":"2020-04-10T12:11:34.024096","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/urat_protein_ntdata.nt","filename":"rat_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat EBI-UniProtKB NT file contains proteome data for rat [taxid:10116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000278"}
{"_id":{"$oid":"5d796512f5c47b4de9b6f255"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}},{"uri":{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycohydrolase.stat.csv","filename":"rat_protein_glycohydrolase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"086f3f241cf050265f28aa56d952a464","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycohydrolases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycohydrolases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-11T17:20:18.184619","modified":"2020-04-10T12:12:13.136231","version":"1.7.9"},"description_domain":{"keywords":["glycohydrolase","glycosidase","EC Number","CAZy"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycohydrolase.csv","filename":"rat_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Glycohydrolases dataset contains a list of rat [taxid:9606] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam. . If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000280"}
{"_id":{"$oid":"5dcc4492f5c47b1d5e39fe83"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_classification.csv","filename":"glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_classification.stat.csv","filename":"glycan_classification.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"784c72a06cf786dbf6e4461f0a85edf2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Classification","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Classification","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T12:59:46.920689","modified":"2020-05-01T15:01:17.670378","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Classification"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_classification.csv","filename":"glycan_classification.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan classification such as glycan type and sub-type for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000282"}
{"_id":{"$oid":"5d7963c0f5c47b4b7fb8db11"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_protein_glycosyltransferase_2018_11.csv","filename":"rat_protein_glycosyltransferase_2018_11.csv"}},{"uri":{"access_time":"2019-10-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/rat_protein_glycosyltransferase.stat.csv","filename":"rat_protein_glycosyltransferase.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b9182eb1a62d7106c1b751d2c7ab4ea1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycosyltransferases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosyltransferases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-11T17:14:40.100826","modified":"2020-04-10T12:11:53.707894","version":"1.7.9"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","EC Number","GO"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_glycosyltransferase.csv","filename":"rat_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Glycosyltransferases dataset contains list of rat [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. If you use this dataset please provide proper attribution to GlyGen"],"bco_id":"http://data.glygen.org/GLY_000279"}
{"_id":{"$oid":"5dcc45f1f5c47b1f6cac300f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-08-07T10:18:01.567083","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotifs.tsv","filename":"allmotifs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-08-07T10:18:01.567083","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_motif.csv","filename":"glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_motif.stat.csv","filename":"glycan_motif.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d29efa3c4978bad536cab1e77e57b86c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Motif","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Motif","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy","authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:05:37.256972","modified":"2020-08-07T10:21:46.129393","version":"1.7.9"},"description_domain":{"keywords":["Glycan","Motif"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-08-07T10:16:01.567083","uri":"https://data.glygen.org/ln2wwwdata/source/allmotifs.tsv","filename":"allmotifs.tsv"},{"access_time":"2020-08-07T10:16:01.567083","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotifaligns.tsv","filename":"allmotifaligns.tsv"}],"output_list":[{"access_time":"2020-08-07T10:18:01.567083","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_motif.csv","filename":"glycan_motif.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list.The data incudes curated list of the motif accessions and other information like: motif name,reducing end,alternative name,aglycon."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-08-07T10:18:01.567083","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-08-07T10:18:01.567083","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan motifs for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000283"}
{"_id":{"$oid":"5dcc491cf5c47b20a5acac95"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/annotated_glycans.csv","filename":"annotated_glycans.csv"}},{"uri":{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"uri":{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-08-07T10:44:40.160813","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-08-07T10:44:40.160813","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_enzyme.stat.csv","filename":"glycan_enzyme.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c27655fd2c1582e50f9d1b19cc42f9a3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Biosynthetic Enzyme","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Enzyme","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Will York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["contributedBy"],"name":"Allison Nairn","email":"avnairn@uga.edu"}],"created":"2019-11-13T13:19:08.883378","modified":"2020-08-07T10:47:48.909998","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-08-07T10:44:40.160813","uri":"https://data.glygen.org/ln2wwwdata/source/annotated_glycans.csv","filename":"annotated_glycans.csv"},{"access_time":"2020-08-07T10:42:40.160813","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_recnames.csv","filename":"human_protein_recnames.csv"},{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}],"output_list":[{"access_time":"2020-08-07T10:44:40.160813","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}],"prerequisite":[],"description":"The input file was downloaded from the source authors and a python script was used to extract columns: glytoucan_ac,residue_name,residue_id,uniprot,gene_name,gene_id,parent_residue_id,type,species. The script also assigned protein recommended name based on the UniProtKB accession. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-08-07T10:42:40.160813","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on biosynthetic enzymes (UniProtKB Ac.) associated to the glycan structures (GlyTouCan Accessions). The enzymes listed are human or mouse proteins that are associated with the canonical monosaccharides. The association of a glycan structure to the canonical monosaccharides are based on the GlycO tree model. The glycans listed in the database may or may not have a human (TaxID:9606) or mouse (TaxID:10090) species annotation from the source (GlyTouCan or UniCarbKB) database. Please note that a human or mouse biosynthetic enzyme association should not be considered as a human or mouse species annotation for that glycan."],"bco_id":"http://data.glygen.org/GLY_000284"}
{"_id":{"$oid":"5dcc4ad5f5c47b214b05895f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_citations_glytoucan.stat.csv","filename":"glycan_citations_glytoucan.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2cf0777f42a691b0c32bdb1f7884a74a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Citations","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan citations","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:26:29.074237","modified":"2020-05-01T15:02:48.739748","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Citations"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pubs.tsv","filename":"pubs.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_citations_glytoucan.csv","filename":"glycan_citations_glytoucan.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citations for the associated glycan (GlyTouCan Accession) from GlyTouCan and UniCarbKB database.The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000285"}
{"_id":{"$oid":"5dcc4d12f5c47b2263ad62f5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_monosaccharide_composition.stat.csv","filename":"glycan_monosaccharide_composition.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d8275d34e792d9a5dbd77de8724f55b1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Monosaccharide composition","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Monosaccharide compositions","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:36:02.199874","modified":"2020-05-01T15:03:19.131525","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Monosaccharide Composition"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_monosaccharide_composition.csv","filename":"glycan_monosaccharide_composition.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the monosaccharide compositions for the associated glycans (GlyTouCan Accession). It provides the count for sugar residues such as Hexose (Hex), N-Acetylhexosamine (HexNAc), Deoxyhexose (dHex), N-Acetylneuraminic Acid ( NeuAc), N-Glycolylneuraminic Acid (NeuGc), Other (Xxx). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000286"}
{"_id":{"$oid":"5dcc726cf5c47b296253ec93"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_glycam_iupac.stat.csv","filename":"glycan_sequences_glycam_iupac.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"777c0f09ecf4faeba124cb0c82a1af91","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCAM IUPAC sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences Glycam IUPAC","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:15:24.688189","modified":"2020-05-01T15:03:34.197549","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycam IUPAC"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycam_iupac.zip","filename":"glycam_iupac.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_glycam_iupac.csv","filename":"glycan_sequences_glycam_iupac.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in Glycam IUPAC format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://dev.glycam.org/"],"bco_id":"http://data.glygen.org/GLY_000287"}
{"_id":{"$oid":"5dcc40d7f5c47b1c5f4f33eb"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.stat.csv","filename":"glycan_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a19f2b82fbea198afd21be5019910ed7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Properties","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"GlyGen-Glycan masterlist","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T12:43:51.676216","modified":"2020-04-30T10:39:19.196066","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Properties"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_masterlist.csv","filename":"glycan_masterlist.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to process the dataset. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides information on the glycan properties such as mass, permethlyated mass, topology, base composition, composition and the number of monosaccharides for the associated glycan (GlyTouCan Accession). This dataset is the master-list of the GlyTouCan accessions currently present in GlyGen. Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000281"}
{"_id":{"$oid":"5dcc73cdf5c47b29f7054cef"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_glycoct.stat.csv","filename":"glycan_sequences_glycoct.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"85478cc4fb672edc04b161b5c0d9df67","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoCT sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences GlycoCT","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:21:17.865259","modified":"2020-05-01T15:03:52.208714","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoCT"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycoct.zip","filename":"glycoct.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_glycoct.csv","filename":"glycan_sequences_glycoct.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in GlycoCT format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000288"}
{"_id":{"$oid":"5dcc74ebf5c47b2a8119f909"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.stat.csv","filename":"glycan_sequences_inchi.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"698f439dc577c398fb993f92ff26a6c5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"InChI Sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences InChI","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-11-13T16:26:03.109539","modified":"2020-03-16T13:17:30.653608","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","InChI"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/inchi_sdf.tar.gz","filename":"inchi_sdf.tar.gz"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}],"prerequisite":[],"description":"The GlyTouCan Ac. to PubChem CID mapping file was used download .sdf PubChem compound files from PubChem CID ftp and a python script was used to extract the values for headers-<PUBCHEM_COMPOUND_CID> , <PUBCHEM_IUPAC_INCHI>, <PUBCHEM_IUPAC_INCHIKEY>  from the sdf files to generate the final output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the InChI key and glycan sequences in InChI format  for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping (https://data.glygen.org/GLYDS000281). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000144). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000289"}
{"_id":{"$oid":"5dcc7633f5c47b2b1a3d3bb7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_iupac_extended.stat.csv","filename":"glycan_sequences_iupac_extended.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2b41fedecbcb00698bd32b43873f7629","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"IUPAC Extended format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences IUPAC Extended","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:31:31.525156","modified":"2020-05-01T15:05:00.162142","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","IUPAC Extended"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/iupac_extended.zip","filename":"iupac_extended.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_iupac_extended.csv","filename":"glycan_sequences_iupac_extended.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in IUPAC extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000290"}
{"_id":{"$oid":"5d72a02ff5c47b0f43423384"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Information (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:39.001496","modified":"2020-04-10T12:10:02.728045","version":"1.7.9"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_refseq.stat.csv","filename":"rat_protein_info_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"parametric_domain":[],"usability_domain":["The Rat Protein Information (NCBI RefSeq) dataset contains rat [taxid:10116] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000275","checksum":"1bccc00b1601414eb9bcec214a9dc81a"}
{"_id":{"$oid":"5dcc77b4f5c47b2bd2bf006a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2020_04_29_15_19_03.gz","filename":"CID-SMILES_2020_04_29_15_19_03.gz"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_smiles_isomeric.stat.csv","filename":"glycan_sequences_smiles_isomeric.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"241bf8757179ba345ee0014873cf428e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SMILES Isomeric sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences SMILES Isomeric","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-11-13T16:37:56.677676","modified":"2020-05-01T16:34:08.669990","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SMILES Isomeric"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/CID-SMILES_2020_04_29_15_19_03.gz","filename":"CID-SMILES_2020_04_29_15_19_03.gz"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_smiles_isomeric.csv","filename":"glycan_sequences_smiles_isomeric.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID mapping file to extract the SMILES ISOMERIC sequence data from downloaded file from PubChem FTP"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in SMILES Isomeric format for the associated glycans (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://pubchem.ncbi.nlm.nih.gov/; https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000291"}
{"_id":{"$oid":"5dcc78e8f5c47b2c64651840"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_wurcs.stat.csv","filename":"glycan_sequences_wurcs.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e60434eb05010ce6540917052ce8487e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"WURCS sequence format","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Sequences WURCS","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:43:04.029210","modified":"2020-05-01T15:05:42.073015","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","WURCS"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/wurcs.zip","filename":"wurcs.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_sequences_wurcs.csv","filename":"glycan_sequences_wurcs.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the glycan sequences in WURCS extended format for the associated glycans (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000292"}
{"_id":{"$oid":"5dcc7df6f5c47b310d7a5f29"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/database_accession_2020_04_29_03_38_01.tsv","filename":"database_accession_2020_04_29_03_38_01.tsv"}},{"uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi_from_kegg.csv","filename":"glycan_xref_chebi_from_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi_from_kegg.stat.csv","filename":"glycan_xref_chebi_from_kegg.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b33a184b06a327eb217f2752138b0005","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references (KEGG GLYCAN)","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [KEGG ID] ","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-11-13T17:04:38.641719","modified":"2020-06-22T10:52:02.353365","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (KEGG Glycan ID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/database_accession_2020_04_29_03_38_01.tsv","filename":"database_accession_2020_04_29_03_38_01.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_chebi_from_kegg.csv","filename":"glycan_xref_chebi_from_kegg.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to KEGG glycan  mapping file to extract the KEGG Glycan ID to ChEBI ID mapping from the ChEBI FTP download file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to KEGG glycan ID mapping .  The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000297"}
{"_id":{"$oid":"5dcc7a12f5c47b2d06da7f3f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_taxonomy.csv","filename":"glycan_taxonomy.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_taxonomy.stat.csv","filename":"glycan_taxonomy.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e8d11029c0f9b0222aad475952566348","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Taxonomy","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:48:02.390870","modified":"2020-04-03T16:30:31.164173","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/taxa.tsv","filename":"taxa.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_taxonomy.csv","filename":"glycan_taxonomy.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides NCBI TaxID for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy"],"bco_id":"http://data.glygen.org/GLY_000293"}
{"_id":{"$oid":"5dcc8239f5c47b31f85ce83c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_cfg.stat.csv","filename":"glycan_xref_cfg.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f36dcc1b3fe47b3db72be1808125f64e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CFG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CFG","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T17:22:49.976947","modified":"2020-05-01T15:07:59.578688","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CFG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cfg.tsv","filename":"cfg.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_cfg.csv","filename":"glycan_xref_cfg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to CFG ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://www.functionalglycomics.org/"],"bco_id":"http://data.glygen.org/GLY_000298"}
{"_id":{"$oid":"5dcc7ae9f5c47b2dad46a995"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_bcsdb.stat.csv","filename":"glycan_xref_bcsdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"34b9dd4470e79b26c3ce5a7e774edc10","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"BCSDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref BCSDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:51:37.145018","modified":"2020-05-01T15:06:14.232324","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","BCSDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/bcsdb.tsv","filename":"bcsdb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_bcsdb.csv","filename":"glycan_xref_bcsdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to BCSDB ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; http://csdb.glycoscience.ru/bacterial/"],"bco_id":"http://data.glygen.org/GLY_000294"}
{"_id":{"$oid":"5dcc7c9cf5c47b2ed3a146f5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-08-07T10:56:08.179608","uri":"https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2020_07_29_13_25_00.gz","filename":"CID-Synonym-filtered_2020_07_29_13_25_00.gz"}},{"uri":{"access_time":"2020-08-07T10:56:08.179608","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-08-07T10:58:08.179608","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_chebi.stat.csv","filename":"glycan_xref_chebi.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8d24fa55868a66c7e44fcfe23ecbcf59","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"ChEBI cross-references(PUBCHEM CID)","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref ChEBI [PubChem CID]","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EBI-ChEBI","contribution":["contributedBy"],"name":"Gareth Owen","email":"gowen@ebi.ac.uk"}],"created":"2019-11-13T16:58:52.830892","modified":"2020-08-07T11:13:26.470844","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","ChEBI (PubChem CID)","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-08-07T10:56:08.179608","uri":"https://data.glygen.org/ln2wwwdata/source/CID-Synonym-filtered_2020_07_29_13_25_00.gz","filename":"CID-Synonym-filtered_2020_07_29_13_25_00.gz"},{"access_time":"2020-08-07T10:56:08.179608","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_sequences_inchi.csv","filename":"glycan_sequences_inchi.csv"}],"output_list":[{"access_time":"2020-08-07T10:58:08.179608","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_chebi.csv","filename":"glycan_xref_chebi.csv"}],"prerequisite":[],"description":"A python script was generated to use the GlyTouCan Ac. to PubChem CID  mapping file to extract the PubChem CID to ChEBI ID mapping from the PubChem FTP download file. Certain one-to-many PubChem to ChEBI mappings were resolved by matching the InCHI sequences associated with PubChem CID and ChEBI ID from respective databases."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-08-07T10:58:08.179608","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-08-07T10:58:08.179608","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to ChEBI Id's for the associated glycan (GlyTouCan Accession) based on the GlyTouCan to PubChem CID mapping . Using PubChem CID as an anchor database the GlyTouCans from dataset https://data.glygen.org/GLYDS000305 (v1.5.13) are being mapped or registed into ChEBI (by Gareth Owen) using different applications (like KNIME and ClassyFire). The newly added glycans from ChEBI are added back to PubChem through ChEBI's monthly submissions. This dataset uses the PubChem FTP files to map to ChEBI ID and thus only includes ChEBI ID for glycans added in PubChem via ChEBI. One-to-many PubChem CID to ChEBI mappings are resolved using InChI seqences downloaded from both (PubChem CID and ChEBI) databases. The listed GlyTouCan Accessions are derived from the  GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://pubchem.ncbi.nlm.nih.gov/;https://www.ebi.ac.uk/chebi/"],"bco_id":"http://data.glygen.org/GLY_000296"}
{"_id":{"$oid":"5dcc842bf5c47b32a4b4af10"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glyco.csv","filename":"glycan_xref_glyco.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glyco.stat.csv","filename":"glycan_xref_glyco.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b7ef2d78f84c71a5034f403db80b40f4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GLYCO Cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycO","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T17:31:07.996954","modified":"2020-03-24T14:47:22.386127","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glyco","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_glyco.csv","filename":"glycan_xref_glyco.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GlycO ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000299"}
{"_id":{"$oid":"5dcd8030f5c47b0857c6dbee"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycosciencesde.stat.csv","filename":"glycan_xref_glycosciencesde.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b37a13513228d4fd6a9eee5bba253e64","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycosciences.de","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref Glycosciences.de","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:26:24.134158","modified":"2020-05-01T15:08:59.612334","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Glycosciences.de","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycosciencesde.tsv","filename":"glycosciencesde.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_glycosciencesde.csv","filename":"glycan_xref_glycosciencesde.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GLYCOSCIENCES.DE ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;http://www.glycosciences.de/"],"bco_id":"http://data.glygen.org/GLY_000302"}
{"_id":{"$oid":"5dcc86b1f5c47b33dfa05e2c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycomedb.csv","filename":"glycan_xref_glycomedb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycomedb.stat.csv","filename":"glycan_xref_glycomedb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"29437403f386f8a098560a556d715b1d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycomeDB cross-references","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycomeDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T17:41:53.046982","modified":"2020-03-24T14:46:44.978010","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycomeDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/gdb.tsv","filename":"gdb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_glycomedb.csv","filename":"glycan_xref_glycomedb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GlycomeDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/"],"bco_id":"http://data.glygen.org/GLY_000300"}
{"_id":{"$oid":"5dcd7e5df5c47b077a12c419"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect.tsv","filename":"glyconnect.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glyconnect.stat.csv","filename":"glycan_xref_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0d2fbb7451d8659b2f4088c2c79bfe98","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlyConnect cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlyConnect","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:18:37.879581","modified":"2020-05-01T15:08:20.788219","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlyConnect","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect","filename":"glyconnect"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_glyconnect.csv","filename":"glycan_xref_glyconnect.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GlyConnect ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/;https://glyconnect.expasy.org"],"bco_id":"http://data.glygen.org/GLY_000301"}
{"_id":{"$oid":"5dcd815af5c47b09236bd9be"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_kegg.stat.csv","filename":"glycan_xref_kegg.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"72883ceb305a95b96bb40a0968aaaec0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"KEGG cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref KEGG","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:31:22.083466","modified":"2020-05-01T15:09:16.990736","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","KEGG","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/kegg.tsv","filename":"kegg.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_kegg.csv","filename":"glycan_xref_kegg.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to KEGG glycan ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.genome.jp/kegg/glycan/"],"bco_id":"http://data.glygen.org/GLY_000303"}
{"_id":{"$oid":"5dcd82eaf5c47b09a617f9fa"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_pdb.stat.csv","filename":"glycan_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"55921eb15028fc9cf729c960b07c07de","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:38:02.465398","modified":"2020-05-01T15:09:32.597135","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pdb.tsv","filename":"pdb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_pdb.csv","filename":"glycan_xref_pdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to PDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://www.rcsb.org/"],"bco_id":"http://data.glygen.org/GLY_000304"}
{"_id":{"$oid":"5dcd8518f5c47b0a7d9284e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_pubchem.stat.csv","filename":"glycan_xref_pubchem.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5cbb3eff46101cea1d2d4e3d264fa743","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"PubChem","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"","category_name":"species"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref PubChem","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:47:20.058924","modified":"2020-05-01T15:15:26.085137","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","PubChem","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pbch.tsv","filename":"pbch.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_pubchem.csv","filename":"glycan_xref_pubchem.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the accession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to PubChem compound (CID) and substance (SID) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://pubchem.ncbi.nlm.nih.gov"],"bco_id":"http://data.glygen.org/GLY_000305"}
{"_id":{"$oid":"5dcc7bbff5c47b2e3d8dd0df"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_carbbank.stat.csv","filename":"glycan_xref_carbbank.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6abc50a11eb55ca0dd501ea9d883c471","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"CarbBanK cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref CarbBank","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:55:11.149043","modified":"2020-05-01T15:07:34.924820","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","CarbBank","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/carbbank.tsv","filename":"carbbank.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_carbbank.csv","filename":"glycan_xref_carbbank.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to CarbBank ID's for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.genome.jp/dbget-bin/www_bfind?carbbank"],"bco_id":"http://data.glygen.org/GLY_000295"}
{"_id":{"$oid":"5dcd8bb4f5c47b0fd850ee6b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviwed/protein_domap.csv","filename":"protein_domap.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.stat.csv","filename":"human_protein_genomics_england_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fce22d179c2f7b1f22b98e5d51f552f4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Genomics England- Congenital Disorders of Glycosylation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-11-14T12:15:32.954297","modified":"2019-12-02T16:44:17.799023","version":"1.7.9"},"description_domain":{"keywords":["Protein","UniProtKB Accession","Genomics England","Panel App"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviwed/protein_domap.csv","filename":"protein_domap.csv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genomics_england_disease.csv","filename":"human_protein_genomics_england_disease.csv"}],"prerequisite":[],"description":"The input file was downloaded from the Genomics England (https://panelapp.genomicsengland.co.uk/panels/25/) from panel \"Congenital disorders of glycosylation\". A python script was used to process the data. 1. Map the HGNC/gene symbol to UniProtKB canonical accessions from the GlyGen protein masterlist. 2. Only those gene-disease associations are considered where one of the source is \"Expert Review Green\". 3. The MIM ID (Mendelian Inheritance ID) from column \"Phenotypes\" is mapped to DOID (Disease Ontology ID) using input file 2."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"/make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides Genes involved in the Congenital disorders of glycosylation from Genomics England PanelApp ( PanelApp crowdsources expert knowledge to establish consensus diagnostic gene panels. Antonio Rueda Martin and Eleanor Williams, Rebecca E. Foulger, Sarah Leigh, Louise C. Daugherty, Olivia Niblock, Ivone U. S. Leong, Katherine R. Smith, Oleg Gerasimenko, Eik Haraldsdottir, Ellen Thomas, Richard H. Scott, Emma Baple, Arianna Tucci, Helen Brittain, Anna de Burca, Kristina Ibañez, Dalia Kasperaviciute, Damian Smedley, Mark Caulfield, Augusto Rendon & Ellen M. McDonagh. Nat Genet (2019) doi:10.1038/s41588-019-0528-2)"],"bco_id":"http://data.glygen.org/GLY_000308"}
{"_id":{"$oid":"5ddff24ff5c47b2c16349ebc"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_reactome.stat.csv","filename":"human_protein_citations_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bc06d76a2e66db73755a51721bb1b871","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Citations (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T12:49:42.900057","modified":"2020-04-10T11:47:03.575935","version":"1.7.9"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations_reactome.csv","filename":"human_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000310"}
{"_id":{"$oid":"5de2aa71f5c47b4cbee8bd3f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_reactome.csv","filename":"mouse_protein_citations_reactome.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f1499fe1fe62811ded0429215726b7ae","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Citations (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T12:47:42.900057","modified":"2020-04-10T12:47:07.882877","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","Reactome","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations_reactome.csv","filename":"mouse_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Citations (Reactome) dataset contains publication information for mouse [taxid:10090] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000311"}
{"_id":{"$oid":"5de2abb6f5c47b4dd489db0d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_reactome.csv","filename":"rat_protein_citations_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_reactome.stat.csv","filename":"rat_protein_citations_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"edc382cab865d00db2f49139543e05d0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Citations (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T12:49:42.900057","modified":"2020-04-10T12:12:38.822163","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","Reactome","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_citations_reactome.csv","filename":"rat_protein_citations_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Citations (Reactome) dataset contains publication information for rat [taxid:10116] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000312"}
{"_id":{"$oid":"5dcd8a2cf5c47b0ed9feb244"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.stat.csv","filename":"glycan_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b3fbc70ddc907b6cb2cdb210d1e9f3ce","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbKB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbKB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T12:09:00.597068","modified":"2020-05-01T15:15:45.987205","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbKB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb.tsv","filename":"unicarbkb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to UniCarbKB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; http://www.unicarbkb.org/"],"bco_id":"http://data.glygen.org/GLY_000307"}
{"_id":{"$oid":"5de2b02cf5c47b4e7bb6b137"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_binary_interactions.stat.csv","filename":"mouse_protein_binary_interactions.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b3401653293fd0aecf5a50999054fb98","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Binary Interactions (IntAct)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T13:08:44.669121","modified":"2020-04-10T12:47:31.915371","version":"1.7.9"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_binary_interactions.csv","filename":"mouse_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Binary Interaction (IntAct) dataset contains mouse [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000314"}
{"_id":{"$oid":"5dcdb7f1f5c47b2ef53e1a86"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_synthesized.stat.csv","filename":"glycan_synthesized.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4bf4e35fddf9447d3ea7a1f5e2b80a98","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"synthesized Glycan","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Synthesized glycans","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Gerardus JOSEPHUS Boons","email":"gjboons@ccrc.uga.edu"},{"orcid":"","affiliation":"The Boons Group (UGA)","contribution":["authoredBy"],"name":"Lin Liu","email":"linliu@ccrc.uga.edu"}],"created":"2019-11-14T15:24:17.374565","modified":"2019-11-14T15:42:16.118844","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Synthesized Glycan","ID/Accession Mapping"],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"access_time":"","uri":"","filename":""}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_synthesized.csv","filename":"glycan_synthesized.csv"}],"prerequisite":[],"description":"Authors provided figures for  fully-defined glycan strutures (images) long with the associated publication (PubMed ID). Based on the images, the glycans were mapped or registered in the GlyTouCan database manually. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"","name":"manual","uri":{"access_time":"","sha1_chksum":"","uri":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset lists the synthesized glycans which are identified by the the GlyTouCan accessions. Source:- The Boons Group. https://www.ccrc.uga.edu/~gjboons/boons/Home.htm()"],"bco_id":"http://data.glygen.org/GLY_000309"}
{"_id":{"$oid":"5de2af86f5c47b4e4e4792dc"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_binary_interactions.stat.csv","filename":"human_protein_binary_interactions.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8f956bde0660e3a6618543ac871a0cb8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Binary Interactions (IntAct)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T13:05:58.133075","modified":"2020-04-11T11:27:29.829157","version":"1.7.9"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_binary_interactions.csv","filename":"human_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Binary Interaction (IntAct) dataset contains human [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000313"}
{"_id":{"$oid":"5de2b0a4f5c47b4ec8dadbbe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_binary_interactions.stat.csv","filename":"rat_protein_binary_interactions.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4705f59182ed4430bc421a445b68fe51","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Binary Interactions (IntAct)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T13:10:44.152278","modified":"2020-04-10T12:13:23.100034","version":"1.7.9"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_binary_interactions.csv","filename":"rat_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Binary Interaction (IntAct) dataset contains rat [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000315"}
{"_id":{"$oid":"5de2bbddf5c47b4fd3a186e5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv","filename":"human_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e1f39436a9a51ea4b09e0801a483c38d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T13:58:37.032006","modified":"2020-04-11T11:28:33.003978","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.csv","filename":"human_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000316"}
{"_id":{"$oid":"5de2bd78f5c47b50488f22b7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ptm_annotation_uniprotkb.stat.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"38771cfc76a89449bb961f0a9438d372","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T14:05:28.986536","modified":"2020-04-10T12:47:48.210199","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ptm_annotation_uniprotkb.csv","filename":"mouse_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Mouse Protein PTM Annotation (UniProtKB) dataset contains mouse [taxid:10090] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000317"}
{"_id":{"$oid":"5de2bde2f5c47b5075dffdd8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ptm_annotation_uniprotkb.stat.csv","filename":"rat_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"879c56f1d903ab4b49f90b0e18902dfa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T14:07:14.445471","modified":"2020-04-10T12:14:03.498068","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ptm_annotation_uniprotkb.csv","filename":"rat_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Protein PTM Annotation (UniProtKB) dataset contains rat [taxid:10116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000318"}
{"_id":{"$oid":"5de2cb02f5c47b5463232a3f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_reactions_reactome.stat.csv","filename":"mouse_protein_reactions_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a50e8977ef426f1a0fd06edb6c5da327","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Reactions (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T15:03:14.488331","modified":"2020-04-10T12:48:04.969443","version":"1.7.9"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_reactions_reactome.csv","filename":"mouse_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Reactions (Reactome) dataset contains reactions information for pathways for mouse [taxid:10090] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000319"}
{"_id":{"$oid":"5de2cbccf5c47b54c6b2555d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_reactions_reactome.stat.csv","filename":"human_protein_reactions_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"da5d97c48cedb367a1653ff872c4cae7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Reactions (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T15:06:36.890527","modified":"2020-04-11T11:29:06.501899","version":"1.7.9"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_reactions_reactome.csv","filename":"human_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Reactions (Reactome) dataset contains reactions information for pathways for human [taxid:9606] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000320"}
{"_id":{"$oid":"5de2cc46f5c47b55141a1d17"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_reactions_reactome.stat.csv","filename":"rat_protein_reactions_reactome.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"82f5f18073ce50e9552c1d8b295adb62","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Reactions Reactome","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Reactions (Reactome)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-11-30T15:08:38.029791","modified":"2020-04-10T12:14:22.002556","version":"1.7.9"},"description_domain":{"keywords":["Reactome","Pathway","Reactions","PMID"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_reactions_reactome.csv","filename":"rat_protein_reactions_reactome.csv"}],"prerequisite":[],"description":"The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Reactions (Reactome) dataset contains reactions information for pathways for rat [taxid:10116] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000321"}
{"_id":{"$oid":"5dcd8773f5c47b0bd0073557"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbdb.stat.csv","filename":"glycan_xref_unicarbdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b705d2680e7df389f35b86ef391f500f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"UniCarbDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref UniCarbDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:57:23.383521","modified":"2019-11-14T12:08:38.872161","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","UnicarbDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbdb.tsv","filename":"unicarbdb.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_unicarbdb.csv","filename":"glycan_xref_unicarbdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to UniCarbDB ID(s) for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://www.glycome-db.org/; https://unicarb-db.expasy.org/"],"bco_id":"http://data.glygen.org/GLY_000306"}
{"_id":{"$oid":"5de4286cf5c47b2e6fac4e67"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"human_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"57099bb4a2cfe1e6f680c21d1c4a1ac8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-01T15:54:04.720467","modified":"2020-04-10T11:47:40.652475","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_enzyme_annotation_uniprotkb.csv","filename":"human_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Human Protein Enzyme Annotation (UniProtKB) dataset contains human [taxid:9606] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions.  The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000323"}
{"_id":{"$oid":"5de422bcf5c47b2c8a7d2cf5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_site_annotation_uniprotkb.stat.csv","filename":"human_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e1d264b5807a86b261b8c97f15f69652","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-01T15:29:48.229274","modified":"2020-04-11T11:30:23.073973","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_site_annotation_uniprotkb.csv","filename":"human_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Human Protein Site Annotation (UniProtKB) dataset contains human [taxid:9606] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000322"}
{"_id":{"$oid":"5de429c4f5c47b2ec1608459"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5ab6e77459732f0e02675d817a458bf2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-01T15:59:48.968222","modified":"2020-04-10T12:48:22.718557","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_enzyme_annotation_uniprotkb.csv","filename":"mouse_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Mouse Protein Enzyme Annotation (UniProtKB) dataset contains mouse [taxid:10090] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000324"}
{"_id":{"$oid":"5de7ebb9f5c47b59afd189ae"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_site_annotation_uniprotkb.stat.csv","filename":"rat_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4e81df3c2b1b9c1689d32e7d928cf3a0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-04T12:24:09.578947","modified":"2020-04-10T12:15:22.091310","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_site_annotation_uniprotkb.csv","filename":"rat_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Protein Site Annotation (UniProtKB) dataset contains rat [taxid:10116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000328"}
{"_id":{"$oid":"5e4173e2f5c47b0fd619ae00"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_human_2020_06_08_10_37_47.json","filename":"glyconnect_human_2020_06_08_10_37_47.json"}},{"uri":{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"uri":{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/glygen_masterlist.csv","filename":"glygen_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-08-07T11:40:29.063014","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"","uri":{"access_time":"2020-08-07T11:40:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_glyconnect.1.log","filename":"human_proteoform_glycosylation_sites_glyconnect.1.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"887dd6d3750d7fe8cf250495c9e9fb3f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (GlyConnect) ","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-02-10T10:16:50.152756","modified":"2020-08-19T13:57:36.415562","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-08-07T11:38:29.063014","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_human_2020_06_08_10_37_47.json","filename":"glyconnect_human_2020_06_08_10_37_47.json"},{"access_time":"2020-08-07T11:38:29.063014","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"},{"access_time":"2020-08-07T11:38:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv","filename":"https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv"}],"output_list":[{"access_time":"2020-08-07T11:40:29.063014","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_glyconnect.1.log","filename":"human_proteoform_glycosylation_sites_glyconnect.1.log"},{"access_time":"2020-08-07T11:40:29.063014","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (human_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-08-07T11:40:29.063014","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-08-07T11:40:29.063014","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Glycosylation Sites (GlyConnect) dataset contains human [taxid:9606] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Homo sapiens). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000329"}
{"_id":{"$oid":"5de42a40f5c47b2f0c84ba26"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"19d0e0f656d7874b958fe2ba99d315fc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-01T16:01:52.242488","modified":"2020-04-10T12:15:03.261517","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_enzyme_annotation_uniprotkb.csv","filename":"rat_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Protein Enzyme Annotation (UniProtKB) dataset contains rat [taxid:10116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000325"}
{"_id":{"$oid":"5de57561f5c47b0b600bbf79"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/ully_determined.csv","filename":"fully_determined.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_fully_determined.stat.csv","filename":"glycan_fully_determined.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"385b4fd9454d546dbe52df97dbc7f37f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"external","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Fully determined glycans","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-12-02T15:34:41.971945","modified":"2020-05-01T15:16:22.796955","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Fully determined"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/fully_determined.csv","filename":"fully_determined.csv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/glycan_fully_determined.csv","filename":"glycan_fully_determined.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides set of glycans whoch are fully determined. Each glycan is associated with a GlyTouCan Accession. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"bco_id":"http://data.glygen.org/GLY_000326"}
{"_id":{"$oid":"5e418fe2f5c47b111cca84ff"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-08-07T15:00:35.734998","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_mouse_2020_06_08_10_41_58.json","filename":"glyconnect_mouse_2020_06_08_10_41_58.json"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2020-08-07T15:00:35.734998","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-06T13:47:43-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/mouse_proteoform_glycosylation_sites_glyconnect.1.log","filename":"mouse_proteoform_glycosylation_sites_glyconnect.1.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aa993ad62e8d89164a5794b4471fd69b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (GlyConnect) ","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-02-10T12:16:18.548585","modified":"2020-08-07T15:07:41.538669","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-08-07T15:00:35.734998","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_mouse_2020_06_08_10_41_58.json","filename":"glyconnect_mouse_2020_06_08_10_41_58.json"},{"access_time":"2020-08-07T15:00:35.734998","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2020-08-07T15:00:35.734998","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2020-08-07T15:00:35.734998","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (mouse_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-08-07T15:00:35.734998","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-08-07T15:00:35.734998","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycosylation Sites (GlyConnect) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Mus musculus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000330"}
{"_id":{"$oid":"5e419104f5c47b11a2a5ffe8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_rat_2020_06_08_1043_10.json","filename":"glyconnect_rat_2020_06_08_1043_10.json"}},{"uri":{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"uri":{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://data.glygen.org/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-10T12:45:27.721901","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/rat_proteoform_glycosylation_sites_glyconnect.1.log","filename":"rat_proteoform_glycosylation_sites_glyconnect.1.log"}},{"mediatype":"csv","uri":{"access_time":"2020-02-10T12:45:27.721901","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.stat.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"17f891d4e151ca9251f47ec30c0ba71f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites (GlyConnect) ","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["authoredBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-02-10T12:21:08.095461","modified":"2020-08-07T15:06:59.061228","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-10T12:43:27.721901","uri":"https://data.glygen.org/ln2wwwdata/source/glyconnect_rat_2020_06_08_1043_10.json","filename":"glyconnect_rat_2020_06_08_1043_10.json"},{"access_time":"2020-02-10T12:43:27.721901","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_canonicalsequences.fasta","filename":"rat_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2020-02-10T12:45:27.721901","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/rat_proteoform_glycosylation_sites_glyconnect.1.log","filename":"rat_proteoform_glycosylation_sites_glyconnect.1.log"}],"prerequisite":[],"description":"The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (rat_proteoform_glycosylation_sites_glyconnect.1.log)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-02-10T12:43:27.721901","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Glycosylation Sites (GlyConnect) dataset contains rat [taxid:10116] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Rattus Norvegicus). If you use this dataset please provide proper attribution to GlyConnect and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000331"}
{"_id":{"$oid":"5e41960ef5c47b1305bb9add"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-06T13:47:43-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_matrixdb.stat.csv","filename":"human_protein_matrixdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"3c9ec306015b7c9bbe9440bd3138a4b2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Interaction data (MatrixDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"}],"created":"2020-02-10T12:42:38.432328","modified":"2020-05-01T15:23:10.031133","version":"1.7.9"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"output_list":[{"access_time":"2020-02-06T13:47:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_matrixdb.csv","filename":"human_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Human Interaction data (MatrixDB) dataset contains interaction data between Human [taxid:9606] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000332"}
{"_id":{"$oid":"5e41a8a9f5c47b1551229d85"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-06T13:47:43-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_matrixdb.stat.csv","filename":"mouse_protein_matrixdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c964f1fb351853e6b006ac5f0bd6f7e2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Interaction data (MatrixDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"}],"created":"2020-02-10T14:02:01.224476","modified":"2020-05-01T15:23:29.016841","version":"1.7.9"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2020-02-06T13:47:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_matrixdb.csv","filename":"mouse_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Mouse Interaction data (MatrixDB) dataset contains interaction data between Mouse [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000333"}
{"_id":{"$oid":"5e41a95cf5c47b15e1d4a98a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-06T13:47:43-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_matrixdb.stat.csv","filename":"rat_protein_matrixdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"3ad3b1b3011e7a2f3e081cc4650674f9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"MatrixDB","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Interaction data (MatrixDB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"MatrixDB","contribution":["contributedBy"],"name":"Sylvie Ricard-Blum","email":"sylvie.ricard-blum@univ-lyon1.fr"}],"created":"2020-02-10T14:05:00.767732","modified":"2020-05-01T15:23:47.281162","version":"1.7.9"},"description_domain":{"keywords":["protein-GAGs interaction","MatrixDB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb_CORE.csv","filename":"matrixdb_CORE.csv"},{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"2020-02-06T13:47:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_matrixdb.csv","filename":"rat_protein_matrixdb.csv"}],"prerequisite":[],"description":"The tab file (matrixdb_CORE.tab (labeled as “Core MatrixDB dataset as PSI-MI TAB 2.7 file”) was downloaded directly from the MatrixDB database. Following rules were applied to extract specific data from the file. The rules were also verified by the author. 1)Rule 1: where column \"Alt. ID(s) interactor A\" has \"GAG\" AND column \"ID(s) interactor B\" has \"uniprotkb\" as prefixs. 2)Rule 2: where column \"Alt. ID(s) interactor B\" has \"GAG\" AND column \"#ID(s) interactor A\" has \"uniprotkb\" as prefixes. 3)for Rule 1: 3a) Add values from column \"Biological role(s) interactor A\" to new column \"gag_interactor_biological_role\". 3b)Add from column \"Biological role(s) interactor B\" to new column \"protein_interactor_biological_role\".3c)Add  from column \"Publication Identifier(s)\" to new column \"evidence\". 4)for Rule 2: 4a)Add values from\"Biological role(s) interactor A\" to column \"protein_interactor_biological_role\". 4b)Add  from \"Biological role(s) interactor B\" to column gag_interactor_biological_role\". 4c)Add from \"Publication Identifier(s)\" to column \"evidence\". 5) finally the UniProtKB accessions were mapped to UniProtKB canonical accessions based on the GlyGen protein master list (https://data.glygen.org/GLYDS000001)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Interaction data (MatrixDB) dataset contains interaction data between Rat [taxid:10090] proteins and Glycosaminoglycans (GAGs) from MatrixDB database (http://matrixdb.univ-lyon1.fr/ ;PMID:19147664). If you use this dataset please provide proper attribution to MatrixDB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000334"}
{"_id":{"$oid":"5e41ab62f5c47b1683d764f7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}},{"uri":{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv_protein_canonicalsequences.fasta","filename":"hcv_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-06T13:47:43-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c5e6cfd7d87568a72c3d6e3feb4f01e9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"external","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (Literature + UniCarbKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell","email":"m.campbell2@griffith.edu.au"}],"created":"2020-02-10T14:13:38.047090","modified":"2020-05-04T10:54:34.390088","version":"1.7.9"},"description_domain":{"keywords":["reported glycosylation","HCV"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/source/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"access_time":"2020-02-06T13:45:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2020-02-06T13:45:43-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"2020-02-06T13:47:43-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"prerequisite":[],"description":"1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually.  4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence of the 2019-09 UniProtKB release for that protein."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The HCV1a [TaxID:1108] glycosylations sites dataset contains glycosylation sites experimentally reported on Hepatitis C Virus 1a protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428–444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from publication [PMID:18187336] were assigned to GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/GLY_000335"}
{"_id":{"$oid":"5e41b340f5c47b17627b11df"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/protein_xref_glycoprotdb.csv","filename":"protein_xref_glycoprotdb.csv"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_glycoprotdb.stat.csv","filename":"mouse_protein_xref_glycoprotdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"19f63d1d23975782e4e49309778e12be","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlycoProtDB cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Xref GlycoProtDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyTouCan ","contribution":["authoredBy"],"name":"Kiyoko F. Aoki-Kinoshita","email":"kkiyoko@soka.ac.jp"}],"created":"2020-02-10T14:47:12.024589","modified":"2020-04-09T18:03:03.346761","version":"1.7.9"},"description_domain":{"keywords":["GlycoProtDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/protein_xref_glycoprotdb.csv","filename":"protein_xref_glycoprotdb.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_glycoprotdb.csv","filename":"mouse_protein_xref_glycoprotdb.csv"}],"prerequisite":[],"description":"The input file was received directly from the author (Kiyoko F. Aoki-Kinoshita). all the accessions from the input file were checked in the UniProtKB through ID mapping tool. It was found that all the UniProtKB accessions belonged to the Mouse [TaxID:10090] species. The QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions. Any GlycoProtDB ID which was mapped to a protein outside GlyGen protein master list was excluded from the output file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse (TaxID:10090) Xref GlycoProtDB  contains x-refs to IDs present in the GlycoProtDB database (https://acgg.asia/gpdb2/index). If you use this dataset please provide proper attribution to GlycoProtDB and GlyGen. "],"bco_id":"http://data.glygen.org/GLY_000336"}
{"_id":{"$oid":"5e5d413df5c47b3be7717e5e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycoepitope.tsv","filename":"glycoepitope.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-02T16:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_glycoepitope.stat.csv","filename":"glycan_xref_glycoepitope.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e383bfeaa4956f1dd2370dfe6ddd7ad1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"GlycoEpitope cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref GlycoEpitope","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T12:24:13.829417","modified":"2020-05-01T15:16:40.640402","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","GlycoEpitope","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-02T16:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycoepitope.tsv","filename":"glycoepitope.tsv"}],"output_list":[{"access_time":"2020-03-02T16:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_glycoepitope.csv","filename":"glycan_xref_glycoepitope.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to GlycoEpitope for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.glycoepitope.jp/"],"bco_id":"http://data.glygen.org/GLY_000337"}
{"_id":{"$oid":"5e5d433af5c47b3c86299c53"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb.tsv","filename":"matrixdb.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-02T16:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_matrixdb.stat.csv","filename":"glycan_xref_matrixdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e017485d804c36e717092c3274d05e06","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"MatrixDB cross-references","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Xref MatrixDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T12:32:42.836682","modified":"2020-05-01T15:17:01.690959","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","MatrixDB","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-02T16:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/matrixdb.tsv","filename":"matrixdb.tsv"}],"output_list":[{"access_time":"2020-03-02T16:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_xref_matrixdb.csv","filename":"glycan_xref_matrixdb.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides cross-references to MatrixDB for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/;http://matrixdb.univ-lyon1.fr/"],"bco_id":"http://data.glygen.org/GLY_000338"}
{"_id":{"$oid":"5de7ea09f5c47b5981bea996"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_site_annotation_uniprotkb.stat.csv","filename":"mouse_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b1bf7593576b7a870dbddf429116d22a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-12-04T12:16:57.929402","modified":"2020-04-10T12:48:40.647497","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_site_annotation_uniprotkb.csv","filename":"mouse_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Mouse Protein Site Annotation (UniProtKB) dataset contains mouse [taxid:10090] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000327"}
{"_id":{"$oid":"5e5d44e1f5c47b3dcb635bde"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-29T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-png.tbz.00","filename":"images-snfg-extended-png.tbz.00"}},{"uri":{"access_time":"2020-04-29T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-png.tbz.01","filename":"images-snfg-extended-png.tbz.01"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-29T15:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_snfg_extended_png.tar.stat.csv","filename":"glycan_images_snfg_extended_png.tar.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"821d90c1be1974fa2c00b63f6126ef3f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (PNG format)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T12:39:45.400128","modified":"2020-04-29T16:30:03.530379","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","png"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-29T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-png.tbz.00","filename":"images-snfg-extended-png.tbz.00"},{"access_time":"2020-04-29T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-png.tbz.01","filename":"images-snfg-extended-png.tbz.01"}],"output_list":[{"access_time":"2020-04-29T15:02:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_images_snfg_extended_png.tar.gz","filename":"glycan_images_snfg_extended_png.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-png.tbz.?? > images-snfg-extended-png.tbz 2. tar xvf images-snfg-extended-png.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-29T15:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000339"}
{"_id":{"$oid":"5e5d5555f5c47b2996894879"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/names.tsv","filename":"names.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-02T16:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_names.csv","filename":"glycan_names.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_names.stat.csv","filename":"glycan_names.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b76b39bbccf6ab142a2bca0a395d6c2a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"names","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Names","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T13:49:57.958726","modified":"2020-05-01T15:17:30.489457","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Names","Cross-references","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-02T16:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/names.tsv","filename":"names.tsv"}],"output_list":[{"access_time":"2020-03-02T16:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_names.csv","filename":"glycan_names.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides names for the associated glycan (GlyTouCan Accession) in different formats. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000340"}
{"_id":{"$oid":"5e67b4ecf5c47b3cad4f1d11"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"511171dafeb9409ff995be1436e5ab39","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"","name":"HCV 1a Glycosylation Sites (literature)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"rsn13@gwu.edu"}],"created":"2020-03-10T11:40:28.613680","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000343"}
{"_id":{"$oid":"5e6a4fadf5c47b6258bbd42e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.stat.csv","filename":"hcv1a_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9b68c6c885937f53b1f772b08520bc8a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:05:17.851540","modified":"2020-04-09T17:28:32.506158","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Proteome Materlist dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000344"}
{"_id":{"$oid":"5e6a5416f5c47b62ed50c85c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.stat.csv","filename":"hcv1a_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f8acc22b4f90e47c6079579c2a4ca9b2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:24:06.518525","modified":"2020-04-09T17:29:36.257009","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Canonical (UniProtKB) Sequences dataset contains hcv1a [taxid:11108] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000346"}
{"_id":{"$oid":"5e6a565ef5c47b63a0dbd9fb"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_canonicalsequences.stat.csv","filename":"hcv1b_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c9b31db487fe067ce8d19f1c29cba6c0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:33:50.191985","modified":"2020-04-09T18:00:40.119923","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Canonical (UniProtKB) Sequences dataset contains hcv1b [taxid:11116] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000347"}
{"_id":{"$oid":"5e5d56a2f5c47b2a3138df80"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/species.tsv","filename":"species.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_species.csv","filename":"glycan_species.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_species.stat.csv","filename":"glycan_species.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9eb057b2b893d2276f67179077a00d1e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NCBI TaxID","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Species ","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T13:55:30.488616","modified":"2020-06-25T13:32:13.597601","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NCBI TaxID"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/species.tsv","filename":"species.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_species.csv","filename":"glycan_species.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides species annotation for the associated glycan (GlyTouCan Accession) generated from direct TaxID annotation and/or inferred via subsumption. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/; https://www.ncbi.nlm.nih.gov/taxonomy."],"bco_id":"http://data.glygen.org/GLY_000341"}
{"_id":{"$oid":"5e5d5d1ef5c47b2bacc2a509"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-02T16:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_species_customized_neuac_neugc.stat.csv","filename":"glycan_species_customized_neuac_neugc.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"49e176ff107f1e260aaa0f9221201263","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"NeuAc ","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"Mammalian species annotation","category_name":"tags"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycans with NeuAc (Customized table)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-03-02T14:23:10.848312","modified":"2020-05-01T15:18:30.118777","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","NeuAc","Mammalian species annotation "],"pipeline_steps":[{"name":"manual","step_number":1,"version":"","input_list":[{"access_time":"2020-03-02T16:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/monocomp.tsv","filename":"monocomp.tsv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/species.tsv","filename":"species.tsv"}],"output_list":[{"access_time":"2020-03-02T16:04:18-0500","uri":"http://data.glygen.org/ln2wwwdata/reviewed//data/projects/glygen/generated/datasets/unreviewed/glycan_species_customized_neuac_neugc.csv","filename":"glycan_species_customized_neuac_neugc.csv"}],"prerequisite":[],"description":"Based on the submitted user query (different sialic acid-containing mammalian glycan structures reported in your database), the  list of glycans that have \"NeuAc\" were from input file 1 (monocomp.tsv;column:5 ;filter:not \"0\"). The selected GlyTouCan accessions were mapped to input file 2 (glycan_species.tsv) where the value is \"true\".  "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"-","name":"LINUX","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":""}}],"script":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"N/A","filename":"N/A"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides glycans that have atleast one \"NeuAc\" residue in the current GlyGen dataset (https://data.glygen.org/GLYDS000281). The GlyTouCan accessions included in this list have mammalian species annotation (human/mouse/rat) through direct TaxID annotation and/or inferred via subsumption. This table was customized based on a GlyGen user query submitted through GlyGen help on Feb 17th 2020."],"bco_id":"http://data.glygen.org/GLY_000342"}
{"_id":{"$oid":"5e6a580ef5c47b6427cbdf93"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_allsequences.stat.csv","filename":"hcv1b_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2b73581c6f935bffc9ee99be0f4c2cad","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:41:02.468576","modified":"2020-04-09T18:01:38.456477","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_allsequences.fasta","filename":"hcv1b_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Isoform sequences (UniProtKB) dataset contains hcv1b [taxid:11116] protein fasta sequences for the hcv1b isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000349"}
{"_id":{"$oid":"5e6b9549f5c47b311989c8da"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_hcv1a_sequenceinfo.stat.csv","filename":"hcv1a_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7ec315c849eaf5c37800ec982224cef8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T10:14:33.505586","modified":"2020-04-09T17:30:49.970440","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_sequenceinfo.csv","filename":"hcv1a_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1a accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Sequences Info (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB protein sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000350"}
{"_id":{"$oid":"5e6b9796f5c47b31a48bf5fa"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_hcv1b_sequenceinfo.stat.csv","filename":"hcv1b_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5b65fe6d7a987af67bc6ddcd3e1de4ae","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T10:24:22.090435","modified":"2020-04-09T18:02:19.150603","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_sequenceinfo.csv","filename":"hcv1b_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB protein sequence info for all hcv1b isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Sequence Info (UniProtKB) dataset contains hcv1b [taxid:11108] UniProtKB protein sequence information that includes sequence version fasta header for the hcv1b accessions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000351"}
{"_id":{"$oid":"5e6b98bcf5c47b31f399a998"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_ntdata.stat.csv","filename":"hcv1a_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"552c7e23411a7e90d23ed4dbbfc97eca","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T10:29:16.162139","modified":"2020-04-09T17:32:06.901550","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/hcv1a_protein_ntdata.nt","filename":"hcv1a_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) EBI-UniProtKB NT file contains proteome data for hcv1a [taxid:11108] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000352"}
{"_id":{"$oid":"5e6b9dcbf5c47b330c5a9686"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_info_uniprotkb.stat.csv","filename":"hcv1a_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4b11c1bf5938ded81ee5c525c53e0c76","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T10:50:51.969235","modified":"2020-04-09T17:33:15.173529","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_info_uniprotkb.csv","filename":"hcv1a_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Information dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000354"}
{"_id":{"$oid":"5e6ba607f5c47b33e78fc78f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_citations_uniprotkb.stat.csv","filename":"hcv1a_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"3df38b30240248cb7d56dec45187b8e0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T11:25:59.634509","modified":"2020-04-09T17:33:53.624980","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_citations_uniprotkb.csv","filename":"hcv1a_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Citations dataset contains publication information for hcv1a [taxid:11108] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2wwwdata/compiled/hcv1a_protein_blacklisted_pmids_uniprotkb.csv. The dataset is derived from 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000355"}
{"_id":{"$oid":"5e6bccf7f5c47b34fe4a0878"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_citations_uniprotkb.stat.csv","filename":"hcv1b_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d2229ca580efe727a35c2e8c27e899c5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T14:12:07.407873","modified":"2020-04-09T18:03:43.664394","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_citations_uniprotkb.csv","filename":"hcv1b_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Citations dataset contains publication information for hcv1b [taxid:11116] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000356"}
{"_id":{"$oid":"5e6bcf6ef5c47b355c0f0ddf"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_recnames.stat.csv","filename":"hcv1a_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1e5c2f139ebf7d592bc155b2c0fa3a97","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T14:22:38.820189","modified":"2020-04-09T17:34:37.686447","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_recnames.csv","filename":"hcv1a_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000357"}
{"_id":{"$oid":"5e6bd0f9f5c47b3645639b08"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_recnames.stat.csv","filename":"hcv1b_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5cf1dea76983ad39f6057cc76c60cda6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T14:29:13.567811","modified":"2020-04-09T18:04:32.472010","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_idmapping.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_recnames.csv","filename":"hcv1b_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for hcv1b [taxid:10116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000358"}
{"_id":{"$oid":"5e6d2b80f5c47b0826dad36f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_altnames.stat.csv","filename":"hcv1a_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7351d2134d74e16b35576505c90fe446","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:07:44.343644","modified":"2020-04-09T17:35:12.930685","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_altnames.csv","filename":"hcv1a_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1a [taxid:11108] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000359"}
{"_id":{"$oid":"5e6d2d6cf5c47b08bb2b5e7a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_go_annotation.stat.csv","filename":"hcv1a_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"70912450f4b48035439e38cf0877b596","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:15:56.229012","modified":"2020-04-09T17:37:43.450803","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_go_annotation.csv","filename":"hcv1a_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Gene Ontology (GO) dataset contains hcv1a [taxid:11108] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000361"}
{"_id":{"$oid":"5e6a5301f5c47b629fd468da"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-23T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-23T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.stat.csv","filename":"hcv1b_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4a99e519a79da8bcd54ba6afdbba9bb8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:19:29.356135","modified":"2020-04-09T18:00:12.734921","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-24T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Proteome Materlist dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000345"}
{"_id":{"$oid":"5e6a5753f5c47b63f9bf2e71"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_allsequences.stat.csv","filename":"hcv1a_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f83d579202af7ba8158bd65b000e2264","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-12T11:37:55.146916","modified":"2020-04-09T17:30:07.599611","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_allsequences.fasta","filename":"hcv1a_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all hcv1a isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Isoform sequences (UniProtKB) dataset contains hcv1a [taxid:11108] protein fasta sequences for the hcv1a isoform accessions from the UniProtKB database,. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000348"}
{"_id":{"$oid":"5e6d2e50f5c47b08f164d0b3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_go_annotation.stat.csv","filename":"hcv1b_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1ae831e7d5fcd78f1abc741e39860f1b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:19:44.880963","modified":"2020-04-09T18:05:41.159736","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_go_annotation.csv","filename":"hcv1b_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Gene Ontology (GO) dataset contains hcv1b [taxid:11116] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000362"}
{"_id":{"$oid":"5e6b99f3f5c47b32415d1095"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_ntdata.stat.csv","filename":"hcv1b_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"93fcfcc317f942e2139872bafd642f53","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-13T10:34:27.467680","modified":"2020-04-09T18:02:47.875660","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/hcv1b_protein_ntdata.nt","filename":"hcv1b_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) EBI-UniProtKB NT file contains proteome data for hcv1b [taxid:11116] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000353"}
{"_id":{"$oid":"5e6d2eecf5c47b094318e817"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"08055ba127bc0363be692a56aba1e1aa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:22:20.601417","modified":"2020-04-09T17:38:19.494458","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1a_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein PTM Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000363"}
{"_id":{"$oid":"5e6d2febf5c47b0972221e95"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0e21be00d5f3a44fbdade103b916aa20","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:26:35.442241","modified":"2020-04-09T18:06:05.126892","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_ptm_annotation_uniprotkb.csv","filename":"hcv1b_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein PTM Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000364"}
{"_id":{"$oid":"5e6d30d0f5c47b09d63ba4e3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"73825a869a47b82ef00b3c173836a956","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:30:24.048685","modified":"2020-04-09T17:38:58.477778","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1a_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000365"}
{"_id":{"$oid":"5e6d3c10f5c47b0a5b70f8e8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e551a38623724f82c02f0873ca063418","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T16:18:24.887237","modified":"2020-04-09T18:06:57.529880","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_enzyme_annotation_uniprotkb.csv","filename":"hcv1b_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Enzyme Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000366"}
{"_id":{"$oid":"5e6d4a58f5c47b0c50d36e02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"22a29c5d4e9531e723cfc9e383f176f1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:19:20.779869","modified":"2020-04-09T18:07:37.578247","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_site_annotation_uniprotkb.csv","filename":"hcv1b_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) (HCV) Protein Site Annotation (UniProtKB) dataset contains hcv1b [taxid:11116] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000367"}
{"_id":{"$oid":"5e6d4c53f5c47b0cb00c9308"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_intact.stat.csv","filename":"hcv1a_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8a7623b31a81c6379c3e301d1c0178dd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:27:47.710028","modified":"2020-04-09T17:39:53.805662","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_intact.csv","filename":"hcv1a_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref IntAct dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"bco_id":"http://data.glygen.org/GLY_000368"}
{"_id":{"$oid":"5e6d4ca0f5c47b0cdcfe13ac"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_intact.stat.csv","filename":"hcv1b_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"04218df6c322324e0a9c7c0e05f939e4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:29:04.813092","modified":"2020-04-09T18:08:05.219025","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_intact.csv","filename":"hcv1b_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref IntAct dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"bco_id":"http://data.glygen.org/GLY_000369"}
{"_id":{"$oid":"5e6d4eedf5c47b0d8e112b38"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-11108-homo-sapiens-2019-05.nt","filename":"uniprot-proteome-11108-homo-sapiens-2019-05.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pdb.stat.csv","filename":"hcv1a_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"86b3d62dbef655772612cc52c0ceb253","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:38:53.233399","modified":"2020-04-09T17:44:01.356479","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pdb.csv","filename":"hcv1a_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref PDB contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000372"}
{"_id":{"$oid":"5e6d4fb9f5c47b0dd2f02c5a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-11116-homo-sapiens-2019-05.nt","filename":"uniprot-proteome-11116-homo-sapiens-2019-05.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pdb.stat.csv","filename":"hcv1b_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9869cedb993b29e77d07a3ca43f997d7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:42:17.307133","modified":"2020-04-09T18:09:19.836070","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pdb.csv","filename":"hcv1b_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref PDB contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000373"}
{"_id":{"$oid":"5e6d2c40f5c47b08545c7ec9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_altnames.stat.csv","filename":"hcv1b_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0c81ccbbec32ddb4cf997ead84e57b23","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T15:10:56.943062","modified":"2020-04-09T18:04:54.875946","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_altnames.csv","filename":"hcv1b_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for hcv1b [taxid:11116] proteins. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000360"}
{"_id":{"$oid":"5e6d5147f5c47b0e4c238f83"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pfam.stat.csv","filename":"hcv1b_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7482f42df354713891fdef33e607ca6e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:48:55.153656","modified":"2020-04-09T18:09:48.976742","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_pfam.csv","filename":"hcv1b_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000375"}
{"_id":{"$oid":"5e6e4dfef5c47b54882c14f3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_euhcvdb.stat.csv","filename":"hcv1a_protein_xref_euhcvdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0ed921f2621f44bd8927eda67a2eb278","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref euHCVdb","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T11:47:10.216940","modified":"2020-04-09T17:47:25.305931","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_euhcvdb.csv","filename":"hcv1a_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"bco_id":"http://data.glygen.org/GLY_000376"}
{"_id":{"$oid":"5e6d5065f5c47b0e208afcbe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pfam.stat.csv","filename":"hcv1a_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"32df6f471927f86613a558294c6961a0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:45:09.021420","modified":"2020-04-09T17:44:45.309455","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_pfam.csv","filename":"hcv1a_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000374"}
{"_id":{"$oid":"5e6e4e57f5c47b54b5adebe3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_euhcvdb.stat.csv","filename":"hcv1b_protein_xref_euhcvdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a9c556f0fad9c51a04bd4fac66930074","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"euHCVdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref euHCVdb","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T11:48:39.326362","modified":"2020-04-09T18:10:14.217756","version":"1.7.9"},"description_domain":{"keywords":["euHCVdb","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_euhcvdb.csv","filename":"hcv1b_protein_xref_euhcvdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to euHCVdb database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to euHCVdb database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The euHCVdb is mainly oriented towards protein sequence, structure and function analyses and structural biology of HCV."],"bco_id":"http://data.glygen.org/GLY_000377"}
{"_id":{"$oid":"5e6e50caf5c47b5568b00598"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1a_protein_xref_viruspathogenresource.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bb1768d8b01627d1fe94c6bf17bb0a45","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref ViPR","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T11:59:06.096223","modified":"2020-04-09T17:51:44.919431","version":"1.7.9"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_viruspathogenresource.csv","filename":"hcv1a_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Virus Pathogen Resource (ViPR) contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"bco_id":"http://data.glygen.org/GLY_000378"}
{"_id":{"$oid":"5e6e516ff5c47b55a95d8e6b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_viruspathogenresource.stat.csv","filename":"hcv1b_protein_xref_viruspathogenresource.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4833e415abb9ffce089d0a67fc6e2dc4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"ViPR cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref ViPR","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:01:51.641730","modified":"2020-04-09T18:10:47.193099","version":"1.7.9"},"description_domain":{"keywords":["VIrus Pathogen Resource (ViPR)","Hepaptitis C Virus (HCV)","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_viruspathogenresource.csv","filename":"hcv1b_protein_xref_viruspathogenresource.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to VIrus Pathogen Resource (ViPR) database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Virus Pathogen Resource contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Virus Pathogen Database and Analysis Resource (ViPR) is an integrative and comprehensive publicly available database and analysis resource to search, analyze, visualize, save and share data for viral pathogens in the U.S. National Institute of Allergy and Infectious Diseases (NIAID) Category A-C Priority Pathogen lists for biodefense research, and other viral pathogens causing emerging/reemerging infectious diseases."],"bco_id":"http://data.glygen.org/GLY_000379"}
{"_id":{"$oid":"5e6e527bf5c47b55f77fd154"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_hepatitisconline.stat.csv","filename":"hcv1a_protein_xref_hepatitisconline.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4429686003b66a6f0ca9442618f7d605","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref Hepatitis C Online","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:06:19.473408","modified":"2020-04-09T17:53:06.626473","version":"1.7.9"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_hepatitisconline.csv","filename":"hcv1a_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref Pfam contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000380"}
{"_id":{"$oid":"5e6e52c6f5c47b5623ba1f54"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_hepatitisconline.stat.csv","filename":"hcv1b_protein_xref_hepatitisconline.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4ead5f3bd3848552f6e452b6a201f9d5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Hepatitis C Online cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref Hepatitis C Online","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:07:34.129887","modified":"2020-04-09T18:11:25.232592","version":"1.7.9"},"description_domain":{"keywords":["Hepatitis C Online","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_hepatitisconline.csv","filename":"hcv1b_protein_xref_hepatitisconline.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Hepatitis C Online database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref Pfam contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to Hepatitis C Online database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000381"}
{"_id":{"$oid":"5e6e56d2f5c47b5905c7e3c0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1ccf09f6515c9db345019e5f2380c7b7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:24:50.340202","modified":"2020-04-09T17:54:08.766039","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Glycosylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000382"}
{"_id":{"$oid":"5e6e5757f5c47b5934e1abc9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"16eced56b2c145252ea2115bdf47edb1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:27:03.522584","modified":"2020-04-09T18:12:53.311327","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Glycosylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000383"}
{"_id":{"$oid":"5e6e57fcf5c47b5981acd430"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"785a4308bd2d85bf9c3ccdab9a091774","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:29:48.651730","modified":"2020-04-09T17:55:14.244075","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Phosphorylation Sites (UniProtKB) dataset contains hcv1a [taxid:11108] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000384"}
{"_id":{"$oid":"5e6e5872f5c47b59ae1b691b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4c3ee90b1026692d10d8ec55b1d5a427","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:31:46.752443","modified":"2020-04-09T18:15:03.519557","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Phosphorylation Sites (UniProtKB) dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000385"}
{"_id":{"$oid":"5e6d4e00f5c47b0d1f067b10"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_interpro.stat.csv","filename":"hcv1a_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ee57082bd72ce98f9359f5760c6a724f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:34:56.163332","modified":"2020-04-10T12:20:53.186821","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_interpro.csv","filename":"hcv1a_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniProtKB Xref InterPro contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000370"}
{"_id":{"$oid":"5e6e5ce0f5c47b5af2591939"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genenames_refseq.stat.csv","filename":"mouse_protein_genenames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b2e57ec7aede9962f99ec0344ada5712","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T12:50:40.430263","modified":"2020-04-03T21:26:42.535344","version":"1.7.9"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genenames_refseq.csv","filename":"mouse_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Gene Symbols (NCBI RefSeq) dataset contains mouse [taxid:10090] gene symbols/names (primary gene name and gene synonyms) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000388"}
{"_id":{"$oid":"5e6e5d6bf5c47b5b14174575"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_refseq.stat.csv","filename":"rat_protein_genenames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6e2087bca5a87305d279cb64af4029ab","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T12:52:59.660127","modified":"2020-03-16T16:49:59.557835","version":"1.7.9"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_refseq.csv","filename":"rat_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Gene Symbols (NCBI RefSeq) dataset contains rat [taxid:10116] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000389"}
{"_id":{"$oid":"5e6e5e6cf5c47b5b63fe34e2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_uniprotkb.stat.csv","filename":"rat_protein_genenames_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"275591af3b8ee304892334f81e30c1e8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Gene Symbols (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:52:59.660127","modified":"2020-04-10T12:19:10.137424","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_genenames_uniprotkb.csv","filename":"rat_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for rat [taxid:10116] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000390"}
{"_id":{"$oid":"5e6e59eef5c47b5a095a2c4f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_brenda.stat.csv","filename":"hcv1a_protein_xref_brenda.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1c5115dfde4cc9e4c292d911408092e5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a UniProtKB Xref BRENDA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T12:38:06.673108","modified":"2020-04-09T17:56:27.770821","version":"1.7.9"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_xref_brenda.csv","filename":"hcv1a_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) UniprotKB Xref BRENDA contains hcv1a [taxid:11108] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"bco_id":"http://data.glygen.org/GLY_000386"}
{"_id":{"$oid":"5e6e60fef5c47b5ca889efb8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genenames_uniprotkb.stat.csv","filename":"mouse_protein_genenames_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e241e568eec585e8d8ec1ed0768039ef","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Symbols (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T13:08:14.330050","modified":"2020-03-16T16:34:14.974060","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_genenames_uniprotkb.csv","filename":"mouse_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for mouse [taxid:10090] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000391"}
{"_id":{"$oid":"5e6e6556f5c47b5d8b8b37c0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinnames_refseq.csv","filename":"human_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinnames_refseq.stat.csv","filename":"human_protein_proteinnames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6a29e590ce087396e54d76254de53bd6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Names (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:26:46.282740","modified":"2020-04-10T11:49:01.913927","version":"1.7.9"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_info_refseq.csv","filename":"human_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000392"}
{"_id":{"$oid":"5e6e5b9bf5c47b5aaf0940ce"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_refseq.csv.stat.csv","filename":"human_pprotein_genenames_refseq.csv.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"15a48600857ed0fa6c1f5cdbac35d6ad","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T12:45:15.358749","modified":"2020-04-10T11:48:37.249118","version":"1.7.9"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_refseq.csv","filename":"human_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Gene Symbols (NCBI RefSeq) dataset contains human [taxid:9606] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000387"}
{"_id":{"$oid":"5e6e65e3f5c47b5db704d5fd"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_proteinnames_refseq.csv","filename":"mouse_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_proteinnames_refseq.stat.csv","filename":"mouse_protein_proteinnames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6f65c65377572b933807f4b5c4fbdf6b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Names (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:29:07.339002","modified":"2020-03-16T11:18:46.916940","version":"1.7.9"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_info_refseq.csv","filename":"mouse_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Names (NCBI RefSeq) dataset contains mouse [taxid:10090] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000393"}
{"_id":{"$oid":"5e6e6815f5c47b5ec035001f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_submittednames.stat.csv","filename":"human_protein_submittednames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9ec5b568fc6336197464c2710b3b8153","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Submitted Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T13:38:29.540245","modified":"2020-04-10T11:49:36.985464","version":"1.7.9"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_submittednames.csv","filename":"human_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for human [taxid:9606] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000395"}
{"_id":{"$oid":"5e6e6858f5c47b5eec7f49dc"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_submittednames.stat.csv","filename":"mouse_protein_submittednames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fa200e09a98efa74b1054b3971a20dc2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Submitted Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T13:39:36.626348","modified":"2020-03-16T11:15:40.779396","version":"1.7.9"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_submittednames.csv","filename":"mouse_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for mouse [taxid:10090] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000396"}
{"_id":{"$oid":"5e6e6959f5c47b5f3c269a62"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_submittednames.stat.csv","filename":"rat_protein_submittednames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"db934aea5b59cd98428c68690fb15396","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Submitted Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Submitted Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T13:43:53.106298","modified":"2020-03-16T11:16:17.615859","version":"1.7.9"},"description_domain":{"keywords":["protein submitted name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_submittednames.csv","filename":"rat_protein_submittednames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot.. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000397"}
{"_id":{"$oid":"5e6e74a7f5c47b60cadd6a57"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_human_sequenceinfo.stat.csv","filename":"human_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"def455f931d6358756a7419a18f96118","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T14:32:07.364795","modified":"2020-04-10T11:49:57.046096","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_sequenceinfo.csv","filename":"human_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Protein Sequence Info (UniProtKB) dataset contains human [taxid:9606] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000398"}
{"_id":{"$oid":"5e6e7541f5c47b610de3b05b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_mouse_sequenceinfo.stat.csv","filename":"mouse_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0a936849cfa143d4b283190476658653","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T14:34:41.443981","modified":"2020-03-15T15:16:13.169046","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_sequenceinfo.csv","filename":"mouse_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all mouse isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Protein Sequence Info (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000399"}
{"_id":{"$oid":"5e6e75def5c47b61875b24aa"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_rat_sequenceinfo.stat.csv","filename":"rat_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5bb1331a91fff1bc7c35c6a42131182b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-15T14:37:18.669955","modified":"2020-03-15T15:15:57.622792","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_sequenceinfo.csv","filename":"rat_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all rat isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Sequence Info (UniProtKB) dataset contains rat [taxid:10116] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000400"}
{"_id":{"$oid":"5e74f2a3f5c47b5bfd1ab440"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_glycosylation_motifs.stat.csv","filename":"hcv1a_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0d1e2c11071cfc54bb7f8633ddb1ab03","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1a N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-20T12:43:15.223816","modified":"2020-04-09T17:57:50.422851","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_canonicalsequences.fasta","filename":"hcv1a_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_glycosylation_motifs.csv","filename":"hcv1a_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1a [taxid:11108] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000402"}
{"_id":{"$oid":"5e6f9a97f5c47b3b570d5cf7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_uniprotkb.stat.csv","filename":"human_protein_genenames_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4971be17d37df60e4d1adcf32e38c0f7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Symbols (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-16T11:26:15.442401","modified":"2020-04-10T11:50:21.709627","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_genenames_uniprotkb.csv","filename":"human_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for human [taxid:9606] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000401"}
{"_id":{"$oid":"5e74f32df5c47b5c6369b4a9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_glycosylation_motifs.stat.csv","filename":"hcv1b_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2d658981a33af1ff10580615b3e21402","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1b N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-20T12:45:33.474142","modified":"2020-04-09T18:15:36.917227","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_canonicalsequences.fasta","filename":"hcv1b_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_glycosylation_motifs.csv","filename":"hcv1b_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for hcv1b [taxid:11116] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2019-09 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000403"}
{"_id":{"$oid":"5e751f37f5c47b617bca758e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ncbi_linkouts.stat.csv","filename":"human_protein_ncbi_linkouts.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e70c170b66e9c90d4b271820146531ba","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human NCBI Protein Linkouts","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-20T15:53:27.297125","modified":"2020-04-07T10:34:22.920866","version":"1.7.9"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}],"output_list":[{"access_time":"2020-03-19T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ncbi_linkouts.csv","filename":"human_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human NCBI Protein Linkouts contains human [taxid:9606] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"bco_id":"http://data.glygen.org/GLY_000405"}
{"_id":{"$oid":"5e751fbaf5c47b61e941dc1a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ncbi_linkouts.stat.csv","filename":"mouse_protein_ncbi_linkouts.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6b56b8b22f800a74eb382abb2d10c6d5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse NCBI Protein Linkouts","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-20T15:55:38.335185","modified":"2020-04-07T10:35:18.106559","version":"1.7.9"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}],"output_list":[{"access_time":"2020-03-19T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ncbi_linkouts.csv","filename":"mouse_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse NCBI Protein Linkouts contains mouse [taxid:10090] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"bco_id":"http://data.glygen.org/GLY_000406"}
{"_id":{"$oid":"5e7507f9f5c47b5f8a09551b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pharos_protein_all_9606.json","filename":"pharos_protein_all_9606.json"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_pharos.csv"}},{"mediatype":"txt","uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/glygen_pharos_xref_mapping.log","filename":"glygen_pharos_xref_mapping.log"}},{"mediatype":"csv","uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pharos.stat.csv","filename":"human_protein_xref_pharos.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c53567bddf1720e7e0b673a6d9c81dcf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pharos cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"Human UniProtKB Xref Pharos","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"University of New Mexico","contribution":["contributedBy"],"name":"Tudor I Oprea","email":"TOprea@salud.unm.edu"},{"orcid":"","affiliation":"NIH","contribution":["contributedBy"],"name":"Paul Barrett","email":"paul.barrett@nih.gov"},{"orcid":"","affiliation":"NIH/NIGRI","contribution":["contributedBy"],"name":"Ajay Pillai","email":"ajay.pillai3@nih.gov"}],"created":"2020-03-20T14:14:17.733990","modified":"2020-04-03T23:11:14.573454","version":"1.7.9"},"description_domain":{"keywords":["Pharos","Illuminating the Druggable Genome","drug-targeted protein families","G-protein-coupled receptors (GPCRs)","ion channels (ICs)","kinases"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/pharos_protein_all_9606.json","filename":"pharos_protein_all_9606.json"}],"output_list":[{"access_time":"2020-03-19T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_pharos.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. the accessions that are not mapped are logged in the log file. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen","Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes.","The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases","Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072","https://pharos.nih.gov/about"],"bco_id":"http://data.glygen.org/GLY_000404"}
{"_id":{"$oid":"5e6e66bcf5c47b5df991ca5c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_proteinnames_refseq.csv","filename":"rat_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_proteinnames_refseq.stat.csv","filename":"rat_protein_proteinnames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"dfef05ad3647e731682626ed78d9f77c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Names (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2020-03-16T11:19:19.372957","version":"1.7.9"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10116.gpff","filename":"refseq_protein_all_10116.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_info_refseq.csv","filename":"rat_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Protein Names (NCBI RefSeq) dataset contains rat [taxid:10116] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000394"}
{"_id":{"$oid":"5e751ffcf5c47b6217c6288f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-03-19T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ncbi_linkouts.stat.csv","filename":"rat_protein_ncbi_linkouts.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6704e6887f15131221b91b90e399e716","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"NCBI Linkouts","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat NCBI Protein Linkouts","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-20T15:56:44.646296","modified":"2020-04-07T10:36:34.047702","version":"1.7.9"},"description_domain":{"keywords":["NCBI Protein Linkouts","RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-03-19T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}],"output_list":[{"access_time":"2020-03-19T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_ncbi_linkouts.csv","filename":"rat_protein_ncbi_linkouts.csv"}],"prerequisite":[],"description":"The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-19T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat NCBI Protein Linkouts contains rat [taxid:10116] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID.","The RefSeq accessions are The dataset is derived from NCBI RefSeq Release 96, September 9, 2019"],"bco_id":"http://data.glygen.org/GLY_000407"}
{"_id":{"$oid":"5e823970f5c47b56bff01671"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}}],"output_subdomain":[{"mediatype":"gif","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d14476fdce51e1a8fc82694c3876fcb0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"gif","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Animated GIF)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"orcid":"","affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"}],"created":"2020-03-30T14:24:48.403793","modified":"2020-04-10T11:13:53.063863","version":"1.7.9"},"description_domain":{"keywords":["Glycoprotein","images"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/source/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x_optimized.gif"}],"prerequisite":[],"description":"The input animated gif file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"","name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as an animated GIF through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"bco_id":"http://data.glygen.org/GLY_000408"}
{"_id":{"$oid":"5e836ba8f5c47b2af2244c89"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}}],"output_subdomain":[{"mediatype":"mp4","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"62f73f66ca91b01bbdfaed30f385db7c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycoprotein","category_name":"protein"},{"category_value":"Videos","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"mp4","category_name":"file_type"},{"category_value":"internal","category_name":"scope"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"3D model of SARS-CoV-2 spike glycoprotein (Video)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xiying Ding","email":"xzd@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdWith"],"name":"Robel Kahsay","email":"rkahsay@gwu.edu"},{"orcid":"","affiliation":"Complex Carbohydrate Research Center","contribution":["contributedBy"],"name":"Dr. Robert Woods","email":"rwoods.glycam@gmail.com"}],"created":"2020-03-31T12:11:20.452848","modified":"2020-04-09T17:51:59.891567","version":"1.7.9"},"description_domain":{"keywords":["Glycoprotein","video"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/source/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_swiss_gn2g2m3_speed2x.mp4","filename":"sarscov2_protein_swiss_gn2g2m3_speed2x.mp4"}],"prerequisite":[],"description":"The input video file was downloaded from the GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"","name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Based on the RCSB PDB struture 6VSB (https://www.rcsb.org/structure/6vsb), a 3-D model of SARS-CoV-2 (TaxID:2697049) spike glycoprotein is generated by Prof. Dr. Robert Woods's group at the Complex Carbohydrate Research Center, University of Georgia. The 3D model can be downloaded as a .mp4 video through this GlyGen data object. For more information visit GlyGen wiki (https://wiki.glygen.org/index.php/SARS-CoV-2_spike_glycoprotein)"],"bco_id":"http://data.glygen.org/GLY_000409"}
{"_id":{"$oid":"5e84bc8af5c47b7eedc5aaf0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"tsv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv","filename":"protein_glygen_uniprotkb_xref_mapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b546f69e618b5fe6e39ead05995dec87","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-UniProtKB Crossreferences","category_name":"tags"},{"category_value":"tsv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-UniProtKB Crossreferences Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-01T12:08:42.022917","modified":"2020-06-04T13:32:16.780973","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The GlyGen-UniProtKB Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of UniProtKB to GlyGen crossreferences. In the dataset, the UniProtKB glycoprotein accessions have corresponding glycosylation annotation present in the datasets. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000410"}
{"_id":{"$oid":"5e86a086f5c47b1851a8bebf"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_allsequences.stat.csv","filename":"sarscov2_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"91b2a435c827e94e1dc3f27f04e31018","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:33:42.595609","modified":"2020-04-29T18:24:30.587295","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Isoform sequences (UniProtKB) dataset contains sarscov2 [taxid:2697049] protein fasta sequences for the sarscov2 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000412"}
{"_id":{"$oid":"5e86a3b4f5c47b190830fc00"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_binary_interactions.stat.csv","filename":"sarscov1_protein_binary_interactions.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ba09abdc026643d1bd5963eb80f35c59","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Binary Interaction","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Binary Interactions (IntAct)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:47:16.534551","modified":"2020-04-09T18:18:50.610305","version":"1.7.9"},"description_domain":{"keywords":["Binary Interactions","IntAct","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":0,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_binary_interactions.csv","filename":"sarscov1_protein_binary_interactions.csv"}],"prerequisite":[],"description":"The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Binary Interaction (IntAct) dataset contains sarscov1 [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000414"}
{"_id":{"$oid":"5e86a20bf5c47b18abbe8afe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_altnames.stat.csv","filename":"sarscov1_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d99ea4eba4448155e3712c32be52d588","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:40:11.377827","modified":"2020-04-09T18:18:05.800985","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_altnames.csv","filename":"sarscov1_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000413"}
{"_id":{"$oid":"5e86a577f5c47b194c7cd07e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_canonicalsequences.stat.csv","filename":"sarscov1_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d73335eb7f931f925bbbf2209121a03d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:54:47.663774","modified":"2020-04-09T18:19:29.277638","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Canonical (UniProtKB) Sequences dataset contains sarscov1 [taxid:694009] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000415"}
{"_id":{"$oid":"5e6d4e59f5c47b0d4b9d1d9a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_interpro.stat.csv","filename":"hcv1b_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"13afe5b693ae03beac6e9200abb713a0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-03-14T17:36:25.023947","modified":"2020-04-09T18:08:50.807739","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_xref_interpro.csv","filename":"hcv1b_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) UniProtKB Xref InterPro contains hcv1b [taxid:11116] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000371"}
{"_id":{"$oid":"5e86a7fcf5c47b1a53100d9e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_refseq.csv","filename":"sarscov1_protein_citations_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_refseq.stat.csv","filename":"sarscov1_protein_citations_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"047710f45f760a76631a34e1d872fd3d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Citations (RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2020-04-09T18:39:36.624800","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","RefSeq","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_refseq.csv","filename":"sarscov1_protein_citations_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the publication information. The script also maps RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Citations (RefSeq) datasets contains sarscov1 [taxid:694009] UniProtKB accessions mapped to publication information (pmid, title, journal name, publication, date, authors of corresponding RefSeq accessions. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000417"}
{"_id":{"$oid":"5e86ab96f5c47b1b9cdfe2bb"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b0171f7e4070e9dbc9599197075c4a00","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T23:20:54.157333","modified":"2020-04-09T18:40:45.115534","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov1_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000419"}
{"_id":{"$oid":"5e86a971f5c47b1adba1ed31"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_uniprotkb.stat.csv","filename":"sarscov1_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aa73c29f78e8223854a63c5da84a51e9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:40:17.006737","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_uniprotkb.csv","filename":"sarscov1_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Citations dataset contains publication information for sarscov1 [taxid:694009] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000418"}
{"_id":{"$oid":"5e86aed6f5c47b1d24480aa0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cd3cfd41646e0f011b5c8c3b81b6cfc6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"enzyme annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Enzyme Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T23:34:46.503960","modified":"2020-04-10T12:50:33.285258","version":"1.7.9"},"description_domain":{"keywords":["enzyme annotation","enzyme ","UniProtKB","enzyme activity","EC number"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_enzyme_annotation_uniprotkb.csv","filename":"sarscov2_protein_enzyme_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Enzyme Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000420"}
{"_id":{"$oid":"5e86b2e6f5c47b1dbc38bf44"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_function_uniprotkb.stat.csv","filename":"sarscov1_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9156ad54310c3ae70cff360b5f5d79a6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T23:52:06.244702","modified":"2020-04-09T18:41:33.892961","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_function_uniprotkb.csv","filename":"sarscov1_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov1 [taxid:694009] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000421"}
{"_id":{"$oid":"5e869f71f5c47b1818513fcb"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_allsequences.stat.csv","filename":"sarscov1_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ff1dd8d430b96cfe649a8e0ac04174df","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Isoform sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:29:05.258509","modified":"2020-04-09T18:17:37.954163","version":"1.7.9"},"description_domain":{"keywords":["protein isoform sequences","fasta","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_allsequences.fasta","filename":"sarscov1_protein_allsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Isoform sequences (UniProtKB) dataset contains sarscov1 [taxid:694009] protein fasta sequences for the sarscov1 isoform accessions from the UniProtKB database. The dataset is derived from 2020_01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000411"}
{"_id":{"$oid":"5e86b531f5c47b1e5c662510"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_function_uniprotkb.stat.csv","filename":"sarscov2_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"495769d3ac5ce19e024b076c89f7eaff","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:25:10.311615","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_function_uniprotkb.csv","filename":"sarscov2_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Function (UniProtKB) dataset contains biological function annotation for sarscov2 [taxid:2697049] protein accesions from the UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000422"}
{"_id":{"$oid":"5e86b9e0f5c47b1ffa4c4022"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_uniprotkb.stat.csv","filename":"sarscov1_protein_genenames_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"90746ce7937ddf66754c23e5a59bee09","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Gene Symbols (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T00:21:52.771924","modified":"2020-04-09T18:42:44.385015","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_uniprotkb.csv","filename":"sarscov1_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov1 [taxid:694009] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000425"}
{"_id":{"$oid":"5e86bb0ef5c47b202a826338"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_uniprotkb.stat.csv","filename":"sarscov2_protein_genenames_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0cb1aa505721674dc621473366975238","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Symbols","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Symbols (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:25:51.302937","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_uniprotkb.csv","filename":"sarscov2_protein_genenames_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB gene symbols for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Symbols (UniProtKB) dataset contains UniProtKB gene symbols/names for sarscov2 [taxid:2697049] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature  commitees. (for more info - https://www.uniprot.org/help/gene_name). The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000426"}
{"_id":{"$oid":"5e86bd13f5c47b20b1ab6c85"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_glycosylation_motifs.stat.csv","filename":"sarscov1_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b948263b82ce6be0cbe830c4f54d4e31","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T00:35:31.181876","modified":"2020-04-09T18:43:07.886517","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_canonicalsequences.fasta","filename":"sarscov1_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_glycosylation_motifs.csv","filename":"sarscov1_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov1 [taxid:694009] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000427"}
{"_id":{"$oid":"5e86b7e2f5c47b1efcfd4088"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_refseq.csv.csv","filename":"sarscov2_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_refseq.stat.csv","filename":"sarscov2_protein_genenames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bbdb0d752816713eb874f78f13cc24bb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 Gene Symbols (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-03T00:13:22.346676","modified":"2020-04-10T12:25:32.159174","version":"1.7.9"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_genenames_refseq.csv","filename":"sarscov2_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Symbols (NCBI RefSeq) dataset contains sarscov2 [taxid:9606] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000424"}
{"_id":{"$oid":"5e86bd8df5c47b20de0f5981"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.stat.csv","filename":"sarscov2_protein_glycosylation_motifs.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"322ee948d5fd04ece05d8363d94a1ec2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"N-Glycosylation Sequon","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 N-Glycosylation Sequon","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:26:05.361474","version":"1.7.9"},"description_domain":{"keywords":["n-glycosylation sequon","NXS/T","n-glycosylation motif","n-glycosylation consensus sequence"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_glycosylation_motifs.csv","filename":"sarscov2_protein_glycosylation_motifs.csv"}],"prerequisite":[],"description":"The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info -  https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for sarscov2 [taxid:2697049] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. The dataset is derived form 2020_01 UniprotKB release."],"bco_id":"http://data.glygen.org/GLY_000428"}
{"_id":{"$oid":"5e874940f5c47b6707b2ed29"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_go_annotation.stat.csv","filename":"sarscov1_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"01c14e860244377dcbb52518e82514f6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:43:47.432104","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"2020-01","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_go_annotation.csv","filename":"sarscov1_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-01","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Ontology (GO) dataset contains sarscov1 [taxid:694009] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000429"}
{"_id":{"$oid":"5e8749f8f5c47b6760977032"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_go_annotation.stat.csv","filename":"sarscov2_protein_go_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fbf7a948d6d1821ea99a979f9566bfa8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Gene Ontology (Go)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Gene Ontology (GO)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:26:18.336828","version":"1.7.9"},"description_domain":{"keywords":["go id","go name","molecular function","biological process","cellular component","Gene Ontology (GO)"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_go_annotation.csv","filename":"sarscov2_protein_go_annotation.csv"}],"prerequisite":[],"description":"The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequnces"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Gene Ontology (GO) dataset contains sarscov2 [taxid:2697049] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000430"}
{"_id":{"$oid":"5e874b19f5c47b67c79c1e52"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_refseq.stat.csv","filename":"sarscov1_protein_info_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0cde058123662665d046e5a1d6d78659","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Information (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-03T10:41:29.856591","modified":"2020-04-09T18:44:15.204965","version":"1.7.9"},"description_domain":{"keywords":["protein information","protein length","NCBI RefSeq","protein summary"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Information (NCBI RefSeq) dataset contains sarscov1 [taxid:694009] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000431"}
{"_id":{"$oid":"5e874c29f5c47b682c1bdd19"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_uniprotkb.stat.csv","filename":"sarscov1_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"2618e2790df3c154b7b1711d0667214b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:44:51.857554","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_uniprotkb.csv","filename":"sarscov1_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Information dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000432"}
{"_id":{"$oid":"5e874d4bf5c47b6886a81389"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_info_uniprotkb.stat.csv","filename":"sarscov2_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"96d37d5938c7280773e05f1f501da4d8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:26:50.433523","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_info_uniprotkb.csv","filename":"sarscov2_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Information dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000433"}
{"_id":{"$oid":"5e874f9cf5c47b68e513a4ab"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.stat.csv","filename":"sarscov2_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b80b8cfed2dc7e0fbd256a789e956cfb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:00:44.846784","modified":"2020-04-10T12:27:34.596941","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Proteome Materlist dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000434"}
{"_id":{"$oid":"5e87513af5c47b695a224bc8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_ntdata.stat.csv","filename":"sarscov1_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6a502a2cb1040b4cf838d9d574234f5a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:45:52.634064","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov1_protein_ntdata.nt","filename":"sarscov1_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) EBI-UniProtKB NT file contains proteome data for sarscov1 [taxid:694009] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000435"}
{"_id":{"$oid":"5e875194f5c47b699c71b64b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_ntdata.stat.csv","filename":"sarscov2_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"478e2f4be6e647313757c551412bccc3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"EMBL-EBI-GlyGen-NT File","category_name":"tags"},{"category_value":"nt","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 EBI-UniProtKB NT file","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:27:51.924026","version":"1.7.9"},"description_domain":{"keywords":["NT","proteome","EMBL-EBI"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov2_protein_ntdata.nt","filename":"sarscov2_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProtKB"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-10-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) EBI-UniProtKB NT file contains proteome data for sarscov2 [taxid:2697049] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000436"}
{"_id":{"$oid":"5e875347f5c47b6a73dcbc58"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_proteinnames_refseq.csv","filename":"sarscov1_protein_proteinnames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_proteinnames_refseq.stat.csv","filename":"sarscov1_protein_proteinnames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fe84f01710907b596f1c9d7294be9924","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Names (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2020-04-09T18:47:04.482704","version":"1.7.9"},"description_domain":{"keywords":["protein names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_info_refseq.csv","filename":"sarscov1_protein_info_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Names (NCBI RefSeq) dataset contains sarscov1 [taxid:694009] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database.  The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000437"}
{"_id":{"$oid":"5e86b6eaf5c47b1eb76ea8c7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_refseq.csv","filename":"sarscov1_protein_genenames_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_refseq.stat.csv","filename":"sarscov1_protein_genenames_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ab3eb82e859b94c573bd514ad5d7d988","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Gene Symbols (NCBI RefSeq)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-03-15T13:32:44.009025","modified":"2020-04-09T18:42:13.145095","version":"1.7.9"},"description_domain":{"keywords":["protein gene symbols","protein gene names","NCBI RefSeq"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_viral.gpff","filename":"refseq_protein_all_viral.gpff"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_genenames_refseq.csv","filename":"sarscov1_protein_genenames_refseq.csv"}],"prerequisite":[],"description":"The script parses the NCBI RefSeq gpff files to extract the gene symbols/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Gene Symbols (NCBI RefSeq) dataset contains sarscov1 [taxid:9606] gene symbols/names (primary gene name and gene synonyms)  from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000423"}
{"_id":{"$oid":"5e8754f1f5c47b6b1cf740c0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_recnames.stat.csv","filename":"sarscov1_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e60bdebdaaecc68eb1249d4b3efca995","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:47:42.102784","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_recnames.csv","filename":"sarscov1_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-05T14:40:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov1 [taxid:694009] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000438"}
{"_id":{"$oid":"5e8755f2f5c47b6b7021ee4f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_recnames.stat.csv","filename":"sarscov2_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"205366e83d244f451a7b93b1afd5ddc9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Recommended Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Recommended Names (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:28:14.930673","version":"1.7.9"},"description_domain":{"keywords":["protein recommended name","protein name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_recnames.csv","filename":"sarscov2_protein_recnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000439"}
{"_id":{"$oid":"5e875702f5c47b6be74ac2db"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_sarscov1_sequenceinfo.stat.csv","filename":"sarscov1_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0e5aebbb7010c8f07143b03b91aaa9df","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:48:20.300109","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_sequenceinfo.csv","filename":"sarscov1_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov1 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Sequence Info (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000440"}
{"_id":{"$oid":"5e86a64ef5c47b19a7f0c298"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.stat.csv","filename":"sarscov2_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c451af39ac5507be03d3a89284d12b6e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Canonical Protein fasta Sequences","category_name":"tags"},{"category_value":"fasta","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Canonical sequences (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-02T22:58:22.926672","modified":"2020-04-10T12:50:15.239943","version":"1.7.9"},"description_domain":{"keywords":["protein sequence","fasta","UniProtKB canonical accessions"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta","filename":"sarscov2_protein_canonicalsequences.fasta"}],"prerequisite":[],"description":"The script loads the UniProtKB fasta sequence for all sarscov2 canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Canonical (UniProtKB) Sequences dataset contains sarscov2 [taxid:2697049] canonical protein fasta sequences from the UniProtKB database. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000416"}
{"_id":{"$oid":"5e87583ef5c47b6c70239075"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_sarscov2_sequenceinfo.stat.csv","filename":"sarscov2_protein_sequenceinfo.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a954c9e86c30d325ebfab68a341af9ce","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"All Protein Sequence Info","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Sequence Info (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-10T12:28:34.953517","version":"1.7.9"},"description_domain":{"keywords":["protein sequence info","fasta header","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_sequenceinfo.csv","filename":"sarscov2_protein_sequenceinfo.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB sequence for all sarscov2 isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Sequence Info (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB protein fasta sequence information that includes sequence version and fasta header. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000441"}
{"_id":{"$oid":"5e875a61f5c47b6d4a9e5065"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_annotation.stat.csv","filename":"sarscov1_protein_signalp_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cfa931f794ecd7717326c647812e896a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Signal Peptide","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:46:41.584409","modified":"2020-04-09T18:48:59.189993","version":"1.7.9"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_annotation.csv","filename":"sarscov1_protein_signalp_annotation.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_peptidesequences.fasta","filename":"sarscov1_protein_signalp_peptidesequences.fasta"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_cleavedsequences.fasta","filename":"sarscov1_protein_signalp_cleavedsequences.fasta"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_signalp_fullsequences.fasta","filename":"sarscov1_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Signal Peptide dataset contains sarscov1 [taxid:694009] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000442"}
{"_id":{"$oid":"5e875d46f5c47b6e5b397002"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"aafec22b28193b39a5ed49dc3db54697","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:59:02.009860","modified":"2020-04-10T12:29:18.863153","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_site_annotation_uniprotkb.csv","filename":"sarscov2_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Site Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000444"}
{"_id":{"$oid":"5e8760c3f5c47b70307f7035"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_chembl.stat.csv","filename":"sarscov1_protein_xref_chembl.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"78a6fb2877ac63337638826b00d79949","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Chembl cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB Xref ChEMBL","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:13:55.769499","modified":"2020-04-09T18:50:18.255893","version":"1.7.9"},"description_domain":{"keywords":["bioactivity","ChEMBL","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_chembl.csv","filename":"sarscov1_protein_xref_chembl.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref ChEMBL contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties."],"bco_id":"http://data.glygen.org/GLY_000446"}
{"_id":{"$oid":"5e875e99f5c47b6f190d09c3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_brenda.csv","filename":"sarscov1_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_brenda.stat.csv","filename":"sarscov1_protein_xref_brenda.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d7e330b65ed40130f0a4f79cfdac0359","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Brenda","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref BRENDA","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:04:41.859890","modified":"2020-04-09T18:49:49.830608","version":"1.7.9"},"description_domain":{"keywords":["enzyme","ec number","BRENDA","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_brenda.csv","filename":"sarscov1_protein_xref_brenda.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref BRENDA contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB."],"bco_id":"http://data.glygen.org/GLY_000445"}
{"_id":{"$oid":"5e87616bf5c47b70c1fb8f8d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_intact.stat.csv","filename":"sarscov1_protein_xref_intact.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c5935beb77d3558ce5fd73b368abcf49","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Intact","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 UniProtKB Xref IntAct","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:16:43.851012","modified":"2020-04-09T18:51:46.638840","version":"1.7.9"},"description_domain":{"keywords":["molecular interaction data","protein-protein interaction","IntAct","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_intact.csv","filename":"sarscov1_protein_xref_intact.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref IntAct dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal."],"bco_id":"http://data.glygen.org/GLY_000448"}
{"_id":{"$oid":"5e87635df5c47b717ec5ae15"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_interpro.stat.csv","filename":"sarscov1_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"dc3cf7fc7d61991fe6db3752c0f04f25","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:25:01.015736","modified":"2020-04-09T18:52:21.890260","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_interpro.csv","filename":"sarscov1_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref InterPro contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000449"}
{"_id":{"$oid":"5e876403f5c47b71cad1ce09"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_interpro.stat.csv","filename":"sarscov2_protein_xref_interpro.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"dd1118bfadb9845554f3892c59ba5252","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Interpro cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref InterPro","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:27:47.989476","modified":"2020-04-10T12:29:38.496338","version":"1.7.9"},"description_domain":{"keywords":["protein family","protein domain","protein functional site","InterPro","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_interpro.csv","filename":"sarscov2_protein_xref_interpro.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref InterPro contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them."],"bco_id":"http://data.glygen.org/GLY_000450"}
{"_id":{"$oid":"5e876448f5c47b720cb3244a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-694009-human-sars-coronavirus-2019-05.nt","filename":"uniprot-proteome-694009-human-sars-coronavirus-2019-05.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pdb.stat.csv","filename":"sarscov1_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c3ccea045e8c6c8ade451d29b4590726","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:28:56.594146","modified":"2020-04-09T18:52:57.173557","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pdb.csv","filename":"sarscov1_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref PDB contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000451"}
{"_id":{"$oid":"5e876481f5c47b725a83eda3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-2697049-human-sars-coronavirus-2019-05.nt","filename":"uniprot-proteome-2697049-human-sars-coronavirus-2019-05.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pdb.stat.csv","filename":"sarscov2_protein_xref_pdb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f3de23ded379a08793c08497923536ca","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pdb cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref PDB","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:29:53.528902","modified":"2020-04-10T12:30:10.776118","version":"1.7.9"},"description_domain":{"keywords":["protein 3D structure","RCSB PDB","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pdb.csv","filename":"sarscov2_protein_xref_pdb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref PDB contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids."],"bco_id":"http://data.glygen.org/GLY_000452"}
{"_id":{"$oid":"5e876570f5c47b73012bccd7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pfam.stat.csv","filename":"sarscov2_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d5f13946d5a8267816dfe760b03f8b32","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:33:52.055648","modified":"2020-04-10T12:30:41.344898","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_pfam.csv","filename":"sarscov2_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniProtKB Xref Pfam contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000454"}
{"_id":{"$oid":"5e8764caf5c47b729dd2c4f3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pfam.stat.csv","filename":"sarscov1_protein_xref_pfam.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"286fb792cb317d37b77cee69f470e110","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Pfam cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref Pfam","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:31:06.030781","modified":"2020-04-09T18:53:52.329452","version":"1.7.9"},"description_domain":{"keywords":["protein family","Pfam","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_pfam.csv","filename":"sarscov1_protein_xref_pfam.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref Pfam contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models."],"bco_id":"http://data.glygen.org/GLY_000453"}
{"_id":{"$oid":"5e8765baf5c47b734499c2ad"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.stat.csv","filename":"sarscov1_protein_xref_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cbb6d4212747b552b196b344f9ef29fc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref RefSeq","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:35:06.443973","modified":"2020-04-09T18:54:20.508460","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniprotKB Xref RefSeq contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"bco_id":"http://data.glygen.org/GLY_000455"}
{"_id":{"$oid":"5e8765eaf5c47b73862fc418"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_refseq.stat.csv","filename":"sarscov2_protein_xref_refseq.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5eba042ee3c06a0b8522a414ab843154","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Refseq cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 UniProtKB Xref RefSeq","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:35:54.612692","modified":"2020-04-13T13:49:48.966919","version":"1.7.9"},"description_domain":{"keywords":["protein accessions","RefSeq","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_xref_refseq.csv","filename":"sarscov2_protein_xref_refseq.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) UniprotKB Xref RefSeq contains sarscov2 [taxid:2697049] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is derived from 2020-01 UniProtKB release. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"," NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein."],"bco_id":"http://data.glygen.org/GLY_000456"}
{"_id":{"$oid":"5e876122f5c47b707ae3c004"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_geneid.stat.csv","filename":"sarscov1_protein_xref_geneid.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"15ac3862e8c361cb631ad668aff7da10","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Ncbi Gene cross-references","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 UniProtKB Xref NCBI Gene","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T12:15:30.637510","modified":"2020-04-09T18:50:59.126807","version":"1.7.9"},"description_domain":{"keywords":["gene id","NCBI gene","cross-reference"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_geneid.csv","filename":"sarscov1_protein_xref_geneid.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) UniProtKB Xref NCBI Gene dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers.  The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen","NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide."],"bco_id":"http://data.glygen.org/GLY_000447"}
{"_id":{"$oid":"5e875ac7f5c47b6da3059efe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_annotation.stat.csv","filename":"sarscov2_protein_signalp_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"56a2fb1145448a792dcc447ac5d507e3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Signal Peptide","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T11:48:23.646763","modified":"2020-04-10T12:28:50.758582","version":"1.7.9"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_annotation.csv","filename":"sarscov2_protein_signalp_annotation.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_peptidesequences.fasta","filename":"sarscov2_protein_signalp_peptidesequences.fasta"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_cleavedsequences.fasta","filename":"sarscov2_protein_signalp_cleavedsequences.fasta"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_signalp_fullsequences.fasta","filename":"sarscov2_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Signal Peptide dataset contains sarscov2 [taxid:2697049] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000443"}
{"_id":{"$oid":"5e8793ebf5c47b7f521bb7b0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_annotation.stat.csv","filename":"mouse_protein_signalp_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4bf29e413d1a0d0bb71216918daabc25","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Signal Peptide","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T15:52:11.121013","modified":"2020-04-09T13:19:58.430790","version":"1.7.9"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_annotation.csv","filename":"mouse_protein_signalp_annotation.csv"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_peptidesequences.fasta","filename":"mouse_protein_signalp_peptidesequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_cleavedsequences.fasta","filename":"mouse_protein_signalp_cleavedsequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_signalp_fullsequences.fasta","filename":"mouse_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Mouse Protein Signal Peptide dataset contains mouse [taxid:10090] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000457"}
{"_id":{"$oid":"5e879404f5c47b7f7e6b5bf7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}},{"uri":{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_annotation.stat.csv","filename":"rat_protein_signalp_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"46fe75d6c0d198b0c2cbd29229bc5a00","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Signal Peptide","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Protein Signal Peptide","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T15:52:36.427462","modified":"2020-04-10T12:16:39.713628","version":"1.7.9"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2020-02-05T17:40:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_annotation.csv","filename":"rat_protein_signalp_annotation.csv"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_peptidesequences.fasta","filename":"rat_protein_signalp_peptidesequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_cleavedsequences.fasta","filename":"rat_protein_signalp_cleavedsequences.fasta"},{"access_time":"2020-02-05T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_signalp_fullsequences.fasta","filename":"rat_protein_signalp_fullsequences.fasta"}],"prerequisite":[],"description":"The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Protein Signal Peptide dataset contains rat [taxid:10116] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide  start and end position, cleaved protein sequence, eco ids and pmids. The dataset contains related files in the output subdomain that includes log file containing accessions that do not have signal peptide information and processed protein sequence’s files in fasta format. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000458"}
{"_id":{"$oid":"5e87a7f6f5c47b0e62d111ef"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_germline.csv","filename":"human_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_germline.stat.csv","filename":"human_protein_mutation_germline.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d00ff0fe4695f6bc0c49ad32e6729c71","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Germline Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T17:17:42.572968","modified":"2020-04-03T17:41:28.937559","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_cancer.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Germline Mutation dataset contains human [taxid:9606] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"bco_id":"http://data.glygen.org/GLY_000459"}
{"_id":{"$oid":"5e87a9e4f5c47b1006082a37"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-rattus-norvegicus.tsv","filename":"dbSNP-rattus-norvegicus.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_mutation_germline.csv","filename":"rat_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_mutation_germline.stat.csv","filename":"rat_protein_mutation_germline.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7fc74589ed7ef48262c9dc03ff48c10d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Rat Germline Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T17:25:56.930719","modified":"2020-04-03T17:39:26.052681","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-rattus-norvegicus.tsv","filename":"dbSNP-rattus-norvegicus.tsv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_mutation_cancer.csv","filename":"rat_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Germline Mutation dataset contains rat [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"bco_id":"http://data.glygen.org/GLY_000461"}
{"_id":{"$oid":"5e87a92df5c47b0ea7312a7e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-mus-musculus.tsv","filename":"dbSNP-mus-musculus.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_mutation_germline.stat.csv","filename":"mouse_protein_mutation_germline.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c54df3ef61c5a4aaf5a2e67ff6dbf87d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Mouse Germline Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T17:22:53.520266","modified":"2020-04-03T17:39:49.678055","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","germline mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-mus-musculus.tsv","filename":"dbSNP-mus-musculus.tsv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_mutation_germline.csv","filename":"mouse_protein_mutation_germline.csv"}],"prerequisite":[],"description":"The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Germline Mutation dataset contains mouse [taxid:10090] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"bco_id":"http://data.glygen.org/GLY_000460"}
{"_id":{"$oid":"5e87ac92f5c47b12b553d6e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_literature.csv","filename":"human_protein_mutation_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_literature.stat.csv","filename":"human_protein_mutation_literature.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b6383a0d8f52b159202b1509e62a3f3f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Literature Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Literature Mutations","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T17:37:22.702254","modified":"2020-04-03T17:43:08.293957","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","literature mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_cancer_mutation_literature.csv","filename":"human_cancer_mutation_literature.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer.csv","filename":"human_protein_mutation_literature.csv"}],"prerequisite":[],"description":"The script extracts the mutation data only for the mutations that have amino acid information and position from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Literature Mutation dataset contains human [taxid:9606] mutation data extracted from literature using the DIMEX tool. The dataset contains only the mutations that have amino acid information and position in the mutation mention column.. If you use this dataset provide proper attribution to GlyGen and OncoMX."],"bco_id":"http://data.glygen.org/GLY_000463"}
{"_id":{"$oid":"5e87f166f5c47b1a1a2df9a2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}},{"mediatype":"txt","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/glygen_pharos_xref_mapping.log","filename":"glygen_pharos_xref_mapping.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_pharos_xref_mapping.stat.csv","filename":"protein_glygen_pharos_xref_mapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ec2d94c36c6f386bb1f797dcd623d80d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-Pharos Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"GlyGen-Pharos Crossreferences Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-03T22:31:02.233246","modified":"2020-04-09T13:57:48.669044","version":"1.7.9"},"description_domain":{"keywords":["Pharos","GlyGen","crossreferences","human","mouse","rat"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_xref_pharos.csv","filename":"human_protein_xref_pharos.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_pharos_xref_mapping.csv","filename":"protein_glygen_pharos_xref_mapping.csv"}],"prerequisite":[],"description":"The script loads the human UniProtKB GlyGen accessions that mapped to the Pharos protein accessions along with the GlyGen protein accession URL and extracts it into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The GlyGen-Pharos Crossreferences Mapping dataset contains GlyGen's human [taxid:9606] UniProtKB accessions and correponding GlyGen URLs. The dataset is derived from 2019-09 UniProtKB release.","The dataset is created for Pharos database to crosslink their protein page links to GlyGen protein pages.","The log file contains the Pharos protein accessions that could not be mapped to GlyGen protein accessions"],"bco_id":"http://data.glygen.org/GLY_000464"}
{"_id":{"$oid":"5e8f59c7f5c47b6ccef4fea7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_site_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5fa8ac67327e712702700a826cd24c7f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-09T13:22:15.821413","modified":"2020-04-09T18:54:45.572843","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_site_annotation_uniprotkb.csv","filename":"sarscov1_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Site Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000465"}
{"_id":{"$oid":"5e87aadcf5c47b11935a8d6e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_somatic.stat.csv","filename":"human_protein_mutation_somatic.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7d9ee1aea796e9e9818546e1ceeeebdd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Somatic Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-03T17:17:42.572968","modified":"2020-04-03T17:38:59.074619","version":"1.7.9"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs)","somatic mutations","dbSNP","disease","ClinVar"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/dbSNP-homo-sapiens.tsv","filename":"dbSNP-homo-sapiens.tsv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_somatic.csv","filename":"human_protein_mutation_somatic.csv"}],"prerequisite":[],"description":"The script extracts the somatic (somatic_staus = 1) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Somatic Mutation dataset contains human [taxid:9606] somatic mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) somatic mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB."],"bco_id":"http://data.glygen.org/GLY_000462"}
{"_id":{"$oid":"5e8f5cbcf5c47b6d16c5b495"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_info_uniprotkb.stat.csv","filename":"hcv1b_protein_info_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cd253a16047eb078df365d20e1e132db","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Information","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Information (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-09T13:34:52.248699","modified":"2020-04-09T18:16:05.796327","version":"1.7.9"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_info_uniprotkb.csv","filename":"hcv1b_protein_info_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Information dataset contains hcv1b [taxid:11116] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000466"}
{"_id":{"$oid":"5e8f7c9ef5c47b726ff7a517"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.stat.csv","filename":"sarscov1_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b07fbbf719fd0759dd30067cb3019d56","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV1 Proteome Masterlist (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-09T15:41:15.215497","modified":"2020-04-09T18:57:42.716934","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Proteome Materlist dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000467"}
{"_id":{"$oid":"5e8f7e39f5c47b72e14157f0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_function_uniprotkb.stat.csv","filename":"hcv1a_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5e13d6ca9fc40df80462019dcf5a399b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1a Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-09T15:57:45.462784","modified":"2020-04-09T17:58:23.388650","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_function_uniprotkb.csv","filename":"hcv1a_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1a [taxid:11108] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000468"}
{"_id":{"$oid":"5e8f7ef5f5c47b736683c3b0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_function_uniprotkb.stat.csv","filename":"hcv1b_protein_function_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bae67ed7246570ec3f2a7e48eaf30451","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Function","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Function (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-09T16:00:53.329942","modified":"2020-04-09T18:16:33.116035","version":"1.7.9"},"description_domain":{"keywords":["protein function","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_masterlist.csv","filename":"hcv1b_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-hepatitis-c-virus-1b.nt","filename":"uniprot-proteome-hepatitis-c-virus-1b.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_function_uniprotkb.csv","filename":"hcv1b_protein_function_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Function (UniProtKB) dataset contains biological function annotation for hcv1b [taxid:11116] protein accesions from the UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000469"}
{"_id":{"$oid":"5e9c6f13f5c47b71e92a5c9c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_citations_uniprotkb.stat.csv","filename":"sarscov2_protein_citations_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"11111ebe694e5c09964a89a5e31b642a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 Protein Citations (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T11:32:35.963024","modified":"2020-04-19T11:33:03.867613","version":"1.7.9"},"description_domain":{"keywords":["publications","PMID","journal","citations","authors","UniProtKB","PubMed"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_citations_uniprotkb.csv","filename":"sarscov2_protein_citations_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information for sarscov2 [taxid:2697049] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000470"}
{"_id":{"$oid":"5e9c7135f5c47b727ca5e2b1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a64c3f507d9b047adf96f804daeab4c8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T11:41:41.632491","modified":"2020-04-19T11:48:13.221709","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov1_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein PTM Annotation (UniProtKB) dataset contains sarscov1 [taxid:694009] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000471"}
{"_id":{"$oid":"5e9c7781f5c47b749cfe6c5d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8311599c28381a02ebd39f106296f801","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T12:08:33.749000","modified":"2020-04-19T12:11:27.306204","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Phosphorylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000474"}
{"_id":{"$oid":"5e9c79c6f5c47b750d3db27e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"923e3248ae06fd53d5cc593f5908ad8d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Phosphorylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T12:18:14.955878","modified":"2020-04-19T12:18:28.052367","version":"1.7.9"},"description_domain":{"keywords":["phosphoryation Sites","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Phosphorylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000475"}
{"_id":{"$oid":"5e9de8aef5c47b41b59540b2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycandata.rdf.gz","filename":"glycandata.rdf.gz"}}],"output_subdomain":[{"mediatype":"rdf","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_rdfdata.rdf.stat.csv","filename":"glycan_rdfdata.rdf.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cdee628aa289898fd10e542f5a4527e9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"rdf","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"rdf","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan data (RDF)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-04-20T14:23:42.722024","modified":"2020-05-01T15:27:20.312275","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","rdf"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycandata.rdf.gz","filename":"glycandata.rdf.gz"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/glycan_rdfdata.rdf.gz","filename":"glycan_rdfdata.rdf.gz"}],"prerequisite":[],"description":"The input file was downloaded from the provider and was provided to GlyGen users. (no additional processing is done)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[{"version":"","name":"","uri":{"access_time":"","sha1_chksum":"","uri":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides rdf fomat file for the glycan data. "],"bco_id":"http://data.glygen.org/GLY_000476"}
{"_id":{"$oid":"5e9dedb7f5c47b42599148e4"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images.tsv","filename":"images.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_image_details.csv","filename":"glycan_image_details.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_image_details.stat.csv","filename":"glycan_image_details.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"027d44a5dbc1b46304f3fc52032b7959","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"images","category_name":"tags"},{"category_value":"Retired","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Images Details","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-04-20T14:45:11.902693","modified":"2020-09-30T13:02:41.010742","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","images","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/images.tsv","filename":"images.tsv"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_image_details.csv","filename":"glycan_image_details.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"","name":"","uri":{"access_time":"","sha1_chksum":"","uri":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides details (such as image size, image notation, image style, image format)for the glycan (identified by GlyTouCan accession) images used in GlyGen. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)"],"bco_id":"http://data.glygen.org/GLY_000477"}
{"_id":{"$oid":"5e9c71f1f5c47b72d496fcab"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.stat.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e165c7e62dafc014205bc750ef86586d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"PTM annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein PTM Annotation (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T11:44:49.318101","modified":"2020-04-19T11:48:48.458026","version":"1.7.9"},"description_domain":{"keywords":["ptm annotation","glycosylation","phosphorylation"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_ptm_annotation_uniprotkb.csv","filename":"sarscov2_protein_ptm_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the PTM annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein PTM Annotation (UniProtKB) dataset contains sarscov2 [taxid:2697049] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2020-01 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000472"}
{"_id":{"$oid":"5e9c74c5f5c47b73b43287e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"dfbcb55e4bdab92726a64604b5e17ef2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-04-19T12:02:17.236691","modified":"2020-05-07T18:27:07.105463","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Glycosylation Sites (UniProtKB) dataset contains sarscov2 [taxid:2697049] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000473"}
{"_id":{"$oid":"5e9df95ff5c47b436ca1a5ed"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/subsumption.tsv","filename":"subsumption.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_subsumption.stat.csv","filename":"glycan_subsumption.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"30480e5b9d29bf2b4e7f3a6df00aef23","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"subsumption","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan Subsumption","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-04-20T15:34:55.646138","modified":"2020-05-01T15:28:21.873184","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Subsumption","ID/Accession Mapping"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/subsumption.tsv","filename":"subsumption.tsv"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_subsumption.csv","filename":"glycan_subsumption.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list. Refer to the usability domain for more information on master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"","name":"","uri":{"access_time":"","sha1_chksum":"","uri":""}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides relationship between the glycans (identified by the GlyTouCan accession). The relation is categorized as either Ancestor, Descendant, SubsumedBy or Subsumes. The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281)."],"bco_id":"http://data.glygen.org/GLY_000478"}
{"_id":{"$oid":"5e9e0a69f5c47b468c0163f1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ea59168b4c41e30b4c71ade321adfe2a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [Automatic Literature Mining]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2020-04-20T16:47:37.482643","modified":"2020-04-30T10:37:24.842264","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the uniprotkb accessions to uniprotkb canonical accessions. 2. Validate the \"amino_acid\" and \"glycosylation_site\" with the .fasta sequence. 3. Add new column: Evidence with 2 values: Automatic literature Mining | GLYDS000481  (split into 2 rows)4.change column headers: uniprotkb_ac to uniprotkb_canonical_ac"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of human [taxid:9606] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"bco_id":"http://data.glygen.org/GLY_000481"}
{"_id":{"$oid":"5ea84262f5c47b1fbecc363b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_glyconnect.csv","filename":"human_proteoform_citations_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_glyconnect.stat.csv","filename":"human_proteoform_citations_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b440a223e8691197dc3b190cce9d8ab0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (GlyConnect)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-04-28T10:49:06.505148","modified":"2020-04-28T11:15:58.774004","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_glyconnect.csv","filename":"human_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"bco_id":"http://data.glygen.org/GLY_000483"}
{"_id":{"$oid":"5ea8460df5c47b20cc4c8af0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_glyconnect.csv","filename":"mouse_proteoform_citations_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_glyconnect.stat.csv","filename":"mouse_proteoform_citations_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"add4cac72f651103cd831bb75368367e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteoform Citations (GlyConnect)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-04-28T11:04:45.973121","modified":"2020-04-28T11:06:57.082293","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_citations_glyconnect.csv","filename":"mouse_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"bco_id":"http://data.glygen.org/GLY_000484"}
{"_id":{"$oid":"5e9dffcaf5c47b4424c1e3b6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/crispin_azadi_yang_covid.csv","filename":"crispin_azadi_yang_covid.csv"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}},{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"log","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log"}},{"mediatype":"log","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0ace549b1721c6af7d3f381260833a2c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"UniCarbKB glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycosylation Sites - UniCarbKB [SARS CoV 2 proteins]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2020-04-20T16:02:18.234465","modified":"2020-04-23T10:50:25.427448","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","UniCarbKB","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/crispin_azadi_yang_covid.csv","filename":"crispin_azadi_yang_covid.csv"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_allsequences.fasta","filename":"sarscov2_protein_allsequences.fasta"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"},{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_unicarbkb.csv","filename":"glycan_xref_unicarbkb.csv"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log"},{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log"},{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}],"prerequisite":[],"description":"The input file was received directly from the provider (Matthew Campbell). A python script along with additional inputs was used to process data and generate a final dataset object. The script checks the GlyTouCan accessions against the existing accessions from GlyTouCan. (Input file 3). The missing accessions are added in log 2 file (sarscov2_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. The unicarbkb id's which are glycan compostion strings, are mapped to GlyTouCan accession using input file 7, generated by Nathan Edwards. The script additionally implements 10 QC checks. Any row that fails for one or more checks is eliminated. All eliminated rows can be accessed from the log 1 (sarscov2_proteoform_glycosylation_sites_unicarbkb.1.log) file along the QC tags. QC tags and description: 1) no_canon: The given protein accession cannot be mapped to a canonical accession. (input file 2) 2) bad_pos: The given amino-acid position is invalid or exceeds the length of the protein sequence. 3) aa_mismatch: Bad amino acid reported (input file 6) 4) invalid_aa: The given amino acid is invalid. 5) glycan_without_glytype: glycan is not in the glycan classification file (Glycan classification file is generated by Author Nathan Edwards; input file 3). 6) bad_glytype: A bad glycan type is detected 7) n_glycan_aa_mismatch: An N glycan is associated with a ser/thr residue 8) o_glycan_aa_mismatch: An O glycan is associated with a Asn residue. 9) no_glycan_invalid_aa: row has no glycan and amino acid is invalid."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of SARS coronavirus (SARS-CoV-2 or 2019-nCoV) [taxid:2697049] proteins with information on glycosylation sites and associated glycans (if available) from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000434)"],"bco_id":"http://data.glygen.org/GLY_000479"}
{"_id":{"$oid":"5ea846baf5c47b213b416739"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_glyconnect.csv","filename":"rat_proteoform_citations_glyconnect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_glyconnect.stat.csv","filename":"rat_proteoform_citations_glyconnect.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"403b5b53ba24b1648f6e6ce76c17e48a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Proteoform Citations (GlyConnect)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Frederique Lisacek","email":"frederique.lisacek@sib.swiss"},{"orcid":"","affiliation":"GlyConnect","contribution":["contributedBy"],"name":"Julien Mariethoz","email":"julien.mariethoz@sib.swiss"}],"created":"2020-04-28T11:07:38.533264","modified":"2020-04-28T11:09:38.064805","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","GlyConnect","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_citations_glyconnect.csv","filename":"rat_proteoform_citations_glyconnect.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Rat Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (https://glyconnect.expasy.org/)."],"bco_id":"http://data.glygen.org/GLY_000485"}
{"_id":{"$oid":"5ea9ddeef5c47b0dcac97eda"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/homolog_clusters_compiled.csv","filename":"homolog_clusters.csv"}},{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/homolog_clusters_compiled..stat.csv","filename":"homolog_clusters.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e3673233a52a8f2b45049234005431e3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Homologs","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Homolog Clusters Compiled (Viruses)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-29T16:05:02.861819","modified":"2020-04-30T11:49:39.264263","version":"1.7.9"},"description_domain":{"keywords":["homologs","alignment","virus","UniRef90","UniRef50"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/protein_homolog_clusters.csv","filename":"protein_homolog_clusters.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/homolog_clusters_compiled.csv","filename":"homolog_clusters.csv"}],"prerequisite":[],"description":"The script extracts the virus homologs from the input file for the virus UniProtKB canonical accessions as a dataset in csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Homolog Clusters Compiled Viruses dataset contains homologs of hcv1a [taxid: 9606], hcv1b [taxid:10090], sarscov1 and sarscov2 [taxid:10116] virsuses mapped to UniProtKB canonical accessions. The homologs data is retrieved by using UniProt's UniRef database [PMID:25398609] UniRef90 or UniRef50 clusters for some accessions, whereas for others an pairwise alignment tool by UniProt between two same virus species is done by GlyGen to determine homologs. The dataset contains GlyGen dataset ID as evidence for homologs determined by GlyGen. If you use this dataset please provide proper attribution to UniProtKB, UniRef and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000486"}
{"_id":{"$oid":"5ea9e010f5c47b0ed349bc6a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_disease.stat.csv","filename":"hcv1a_protein_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"48bcf6d9f2dc6f54def9107d0f3dfba4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Protein Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-29T16:14:08.766000","modified":"2020-04-29T21:53:36.212672","version":"1.7.9"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_disease.csv","filename":"hcv1a_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Diseases dataset contains disease caused by hcv1a virus [taxid:11108] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"bco_id":"http://data.glygen.org/GLY_000487"}
{"_id":{"$oid":"5e9e0f61f5c47b483a9a1408"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov2_protein_citations_unicarbkb_literature.csv","filename":"sarscov2_protein_citations_unicarbkb_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_citations_unicarbkb.csv","filename":"sarscov2_proteoform_citations_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_citations_unicarbkb.stat.csv","filename":"sarscov2_proteoform_citations_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8e54836ca10b37648299b57b8b03a64c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Citation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV 2 Proteoform Citations (UniCarbKB)","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"}],"created":"2020-04-20T17:08:49.084209","modified":"2020-06-25T12:29:07.279705","version":"1.7.9"},"description_domain":{"keywords":["Proteins","DOI (Digital Object Identifier)"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/sarscov2_protein_citations_unicarbkb_literature.csv","filename":"sarscov2_protein_citations_unicarbkb_literature.csv"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_citations_unicarbkb.csv","filename":"sarscov2_proteoform_citations_unicarbkb.csv"}],"prerequisite":[],"description":"The DOI(s) were extracted from dataset https://data.glygen.org/GLYDS000479. The corresponding details were manually compiled by the provider. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Citation details (such as title, journal_name, publication_date, authors) corresponding to the Digital Object Identifiers (DOI)/PMID present in dataset https://data.glygen.org/GLYDS000479"],"bco_id":"http://data.glygen.org/GLY_000482"}
{"_id":{"$oid":"5ea9e043f5c47b0eff49f885"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_disease.stat.csv","filename":"hcv1b_protein_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e8009a949728eaeb39bfb84f6fb0b187","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1b, isolate Japanese)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"disease","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1b Protein Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-29T16:14:59.174043","modified":"2020-04-29T21:51:34.143059","version":"1.7.9"},"description_domain":{"keywords":["Hepatitis C","Liver Cirrhosis","Hepatocellular Carcinoma","disease","HCV"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1b_protein_disease.csv","filename":"hcv1b_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Hepatitis C virus (genotype 1b, isolate Japanese) Protein Diseases dataset contains disease caused by hcv1b virus [taxid:11116] which is Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma and is mapped to all UniProtKB canonical accessions. The dataset contains Hepatitis C, Liver Cirrhosis and Hepatocellular carcinoma disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to GlyGen."],"bco_id":"http://data.glygen.org/GLY_000488"}
{"_id":{"$oid":"5ea9e062f5c47b0f2b01bcb0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}},{"mediatype":"","uri":{"access_time":"csv","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_disease.stat.csv","filename":"sarscov1_protein_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"54e32f41e802ad1811d11662dbcfb703","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Protein Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-29T16:15:30.138920","modified":"2020-04-29T21:49:33.078025","version":"1.7.9"},"description_domain":{"keywords":["SARS (Severe Acute Respiratory Syndrome) ","DOID","SARS-CoV-1","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_disease.csv","filename":"sarscov1_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Protein Diseases dataset contains disease caused by sarscov1 virus [taxid:694009] which is SARS and is mapped to all UniProtKB canonical accessions. The dataset contains SARS (Severe Acute Respiratory Syndrome) disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000489"}
{"_id":{"$oid":"5ea9e081f5c47b0f574bbcf3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_disease.stat.csv","filename":"sarscov2_protein_disease.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"66966a6eb42521a4915ed8804be65b42","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"diseases","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Diseases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-04-29T16:16:01.099167","modified":"2020-04-29T21:47:59.417091","version":"1.7.9"},"description_domain":{"keywords":["COVID-19","DOID","SARS-CoV-2","disease"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/compiled/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_disease.csv","filename":"sarscov2_protein_disease.csv"}],"prerequisite":[],"description":"The script extracts the UniProtKB canonical accessions, database name, database ID and DOID from the input file as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCov) Protein Diseases dataset contains disease caused by sarscov2 virus [taxid:2697049] which is COVID-19 mapped to all UniProtKB canonical accessions. The dataset contains COVID-19 disease ontology ID and GlyGen dataset ID. The input file for this dataset is compiled by GlyGen. If you use this dataset please give proper attribution to UniProtKB and GlyGen."],"bco_id":"http://data.glygen.org/GLY_000490"}
{"_id":{"$oid":"5ea9e23ff5c47b0fc8427b7c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-29T15:02:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-svg.tbz.00","filename":"images-snfg-extended-svg.tbz.00"}},{"uri":{"access_time":"2020-04-29T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-svg.tbz.01","filename":"images-snfg-extended-svg.tbz.01"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-29T15:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images_snfg_extended_svg.tar.stat.csv","filename":"glycan_images_snfg_extended_svg.tar.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"875ead33113c0fc0aaec961c62c11b5e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"SNFG images","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Glycan SNFG images (SVG format)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-04-29T16:23:27.495534","modified":"2020-04-29T16:30:05.972556","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","SNFG images","Cross-references","ID/Accession Mapping","svg"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-29T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-svg.tbz.00","filename":"images-snfg-extended-svg.tbz.00"},{"access_time":"2020-04-29T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/images-snfg-extended-svg.tbz.01","filename":"images-snfg-extended-svg.tbz.01"}],"output_list":[{"access_time":"2020-04-29T15:02:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_images_snfg_extended_svg.tar.gz","filename":"glycan_images_snfg_extended_svg.tar.gz"}],"prerequisite":[],"description":"The input file was directly downloaded and processed through following commands 1. cat images-snfg-extended-svg.tbz.?? > images-snfg-extended-svg.tbz 2. tar xvf images-snfg-extended-svg.tbz. The folder was tar and zipped again to generate the final output files."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-03-02T16:00:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides SNFG images for the associated glycan (GlyTouCan Accession). The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000491"}
{"_id":{"$oid":"5eaae046f5c47b69a7343e87"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"ba0f9333d5454e6ca741b46df493ef67","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Mus musculus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites [Automatic Literature Mining]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2020-04-30T10:27:18.537975","modified":"2020-06-22T10:50:51.726268","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv","filename":"mouse_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the uniprotkb accessions to uniprotkb canonical accessions. 2. Validate the \"amino_acid\" and \"glycosylation_site\" with the .fasta sequence. 3. Add new column: Evidence with 2 values: Automatic literature Mining | GLYDS000481  (split into 2 rows)4.change column headers: uniprotkb_ac to uniprotkb_canonical_ac"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of mouse [taxid:10090] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"bco_id":"http://data.glygen.org/GLY_000492"}
{"_id":{"$oid":"5eaae1fef5c47b6a44322fa5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_literature_mining.stat.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1cbc063d02fcb6206ee19f58f804d9ba","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Rat Glycosylation Sites [Automatic Literature Mining]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy","contributedBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"University of Delaware","contribution":["contributedBy"],"name":"Vijay Shanker","email":"vijay@udel.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Karen Ross","email":"ker25@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2020-04-30T10:34:38.124446","modified":"2020-06-22T10:51:28.325950","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","GlyTouCan","Automatic Literature Mining"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-30T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/proteoform_glycosylation_sites_literature_mining.csv","filename":"proteoform_glycosylation_sites_literature_mining.csv"}],"output_list":[{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv","filename":"rat_proteoform_glycosylation_sites_literature_mining.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the uniprotkb accessions to uniprotkb canonical accessions. 2. Validate the \"amino_acid\" and \"glycosylation_site\" with the .fasta sequence. 3. Add new column: Evidence with 2 values: Automatic literature Mining | GLYDS000481  (split into 2 rows)4.change column headers: uniprotkb_ac to uniprotkb_canonical_ac"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-30T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of rat [taxid:10116] proteins with information on glycosylation sites detected from PubMed database(abstracts-only) through Automatic mining tool developed by Dr. Vijay Shanker (University of Delaware). The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"bco_id":"http://data.glygen.org/GLY_000493"}
{"_id":{"$oid":"5e9e06fef5c47b45f30ad2fa"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosites.csv","filename":"glycosites.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_gptwiki.stat.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4818eee530b3da40bc41f93121c7d9a1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Reviewed","category_name":"status"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"glycosylation sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites [GPTwiki]","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"Georgetown University"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Radoslav Goldman","email":"rg26@georgetown.edu"}],"created":"2020-04-20T16:33:02.961632","modified":"2020-05-06T10:23:26.957306","version":"1.7.9"},"description_domain":{"keywords":["proteins","canonical","glycosylation sites","glycan","GPTwiki","GlyTouCan"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-04-23T09:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycosites.csv","filename":"glycosites.csv"}],"output_list":[{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}],"prerequisite":[],"description":"The input file was downloaded from the provider(s). Following QC steps were done using a python script: 1. Map the first column (UniProt) to UniProtKB canonical accession 2. Validate the Site and AminoAcid column with the canonical .fasta sequences. 3. Split the rows if the last column (Glycopeptides) has multiple values (separated by | ) 4. Add a new column for \"database\" with value \"GPTwiki\""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-04-23T09:02:18-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Human Glycosylation Sites [GPTwiki], provided by the Clinical and Translational Glycoscience Research Center (CTGRC), Georgetown University. The database contains list of human [taxid:9606] proteins with information on glycosylation sites and associated glycans from GPTwiki database [https://edwardslab.bmcb.georgetown.edu/gptwiki/Main_Page]. The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)"],"bco_id":"http://data.glygen.org/GLY_000480"}
{"_id":{"$oid":"5eb487a3f5c47b067dcac0fa"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"}},{"uri":{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_site_annotation_uniprotkb.stat.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"59d5c5f6190dca998b3f4461dc76805c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"site annotation","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1a Protein Site Annotation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-05-07T18:11:47.601071","modified":"2020-05-07T18:12:20.019621","version":"1.7.9"},"description_domain":{"keywords":["site annotation","amino acid range","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-hepatitis-c-virus-1a.nt","filename":"uniprot-proteome-hepatitis-c-virus-1a.nt"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_masterlist.csv","filename":"hcv1a_protein_masterlist.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_protein_site_annotation_uniprotkb.csv","filename":"hcv1a_protein_site_annotation_uniprotkb.csv"}],"prerequisite":[],"description":"The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Hepatitis C virus (genotype 1a, isolate H) Protein Site Annotation (UniProtKB) dataset contains hcv1a [taxid:11108] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000494"}
{"_id":{"$oid":"5eb48949f5c47b070e16e0b7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4a3abd5687ba37d29206515993cacc97","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV1 Glycosylation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-05-07T18:18:49.168950","modified":"2020-05-07T18:19:55.454009","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv","filename":"sarscov1_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt","filename":"uniprot-proteome-human-sars-coronavirus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-1) Glycosylation Sites (UniProtKB) dataset contains sarscov1 [taxid:694009] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000495"}
{"_id":{"$oid":"5eb48accf5c47b079f26f043"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_altnames.stat.csv","filename":"sarscov2_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"387a7630c2f9d09041acf67f95916063","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Alternative Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS-CoV2 Protein Alternative Name (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-05-07T18:25:16.830914","modified":"2020-05-07T18:25:28.238809","version":"1.7.9"},"description_domain":{"keywords":["protein alternative name","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv","filename":"sarscov2_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt","filename":"uniprot-proteome-sars-cov-2.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_altnames.csv","filename":"sarscov2_protein_altnames.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for sarscov2 [taxid:2697049] proteins. The dataset is derived from 2020-01 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000496"}
{"_id":{"$oid":"5ebb281af5c47b6a3f73af03"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-05-12T18:50:00.969226","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/type_n_linked_byonic.tsv","filename":"type_n_linked_byonic.tsv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-05-12T18:50:02.969226","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_type_n_linked_byonic.stat.csv","filename":"glycan_type_n_linked_byonic.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f53f1cc9c940f97e43ca322119596239","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Byonic","category_name":"tags"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"csv","category_name":"file_type"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"N-linked Byonic Glycan [Human]","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2020-05-12T18:50:02.969226","modified":"2020-05-27T09:56:36.844075","version":"1.7.9"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Byonic"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-05-12T18:50:02.969226","uri":"https://data.glygen.org/ln2wwwdata/source/type_n_linked_byonic.tsv","filename":"type_n_linked_byonic.tsv"}],"output_list":[{"access_time":"2020-05-12T18:52:02.969226","uri":"https://data.glygen.org/ln2wwwdata/reviewed/glycan_type_n_linked_byonic.csv","filename":"glycan_type_n_linked_byonic.csv"}],"prerequisite":[],"description":"The input file was downloaded from the author and a python script is used to extract the data for the GlyTouCan accessions based on the acession master list."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-05-12T18:50:02.969226","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-05-12T18:50:02.969226","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py","filename":"make-species-agnostic-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides the byonic format of n-linked human glycans (identified by GlyTouCan Ac.).The listed GlyTouCan Accessions are derived from the GlyTouCan accession master list (https://data.glygen.org/GLYDS000281). Source database: https://glytoucan.org/"],"bco_id":"http://data.glygen.org/GLY_000497"}
{"_id":{"$oid":"5ed8faa8f5c47b623d109759"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_unique_sources.csv","filename":"human_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_unique_sources.stat.csv","filename":"human_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6c0b15f327f441bb6c049fd5e41bcf7d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T09:44:08.947606","modified":"2020-06-04T10:09:49.041370","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000500"}
{"_id":{"$oid":"5ebc0683f5c47b716492b28c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-05-13T10:38:59.901723","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-05-13T10:38:59.901723","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_pro_annotation.stat.csv","filename":"human_protein_pro_annotation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f305e8e73d20f4d5a4243222005ef490","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein Resource Ontology [Human]","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Darren Natale","email":"dan5@georgetown.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["contributedBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"}],"created":"2020-05-13T10:38:59.901723","modified":"2020-05-27T10:04:33.171131","version":"1.7.9"},"description_domain":{"keywords":["Proteoforms","PRO","UniCarbKB"],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"2020-05-13T10:38:59.901723","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/GlyGen_table_to_PRO.obo","filename":"GlyGen_table_to_PRO.obo"}],"output_list":[{"access_time":"2020-05-13T10:40:59.901723","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_pro_annotation.csv","filename":"human_protein_pro_annotation.csv"}],"prerequisite":[],"description":"The source file was downloaded from the contributors (Darren Natale)  and a python script was used to convert the source file into a csv format."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information retrieved from the UniCarbKB database for human [taxid:9606] proteins (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019)Source- PRO: https://proconsortium.org/pro.shtml, UniCarbKB: https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128. Please note that this dataset refers to the previous version of the UniCarbKB human glycoprotein dataset (https://data.glygen.org/GLYDS000040: v-1.4.5 09/13/2019)"],"bco_id":"http://data.glygen.org/GLY_000498"}
{"_id":{"$oid":"5ed8fd1cf5c47b62fe35d859"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_proteoform_glycosylation_unique_sources.csv","filename":"mouse_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_proteoform_glycosylation_unique_sources.stat.csv","filename":"mouse_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f4e89849bcd4f32aef29f7c519f060ac","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Mouse Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T09:54:36.278581","modified":"2020-06-04T10:03:55.070473","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000501"}
{"_id":{"$oid":"5ed8fe42f5c47b6b3ac67895"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/rat_proteoform_glycosylation_unique_sources.csv","filename":"rat_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/rat_proteoform_glycosylation_unique_sources.stat.csv","filename":"rat_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c5261a9f5413286dd880846f64b05652","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Rat Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T09:59:30.611514","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000502"}
{"_id":{"$oid":"5ed90094f5c47b6c39e36031"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1a_proteoform_glycosylation_unique_sources.csv","filename":"hcv1a_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1a_proteoform_glycosylation_unique_sources.stat.csv","filename":"hcv1a_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"feb24ee49ea133eda1007d6388f16c13","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1a Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T10:09:24.619941","modified":"2020-06-04T10:13:46.722376","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000503"}
{"_id":{"$oid":"5ed90325f5c47b0afebf28be"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1b_proteoform_glycosylation_unique_sources.csv","filename":"hcv1b_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/hcv1b_proteoform_glycosylation_unique_sources.stat.csv","filename":"hcv1b_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"7c86855a8ed85f1861306e8228e7708c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"HCV1b Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T10:20:21.644672","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000504"}
{"_id":{"$oid":"5ed906a9f5c47b0cb08e9a80"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_unique_sources.csv","filename":"sarscov1_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov1_proteoform_glycosylation_unique_sources.stat.csv","filename":"sarscov1_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e886f0516ff7d9e0b533f8e3bc5b166c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV1 Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T10:35:21.577758","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000505"}
{"_id":{"$oid":"5ed90931f5c47b0dd46eb537"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov2_proteoform_glycosylation_unique_sources.csv","filename":"sarscov2_proteoform_glycosylation_unique_sources.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/sarscov2_proteoform_glycosylation_unique_sources.stat.csv","filename":"sarscov2_proteoform_glycosylation_unique_sources.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cd20d533c5c6072e1116e4c51c047617","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-2 or 2019-nCoV)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Unique Glycosylation Sites","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"SARS-CoV2 Glycosylation Unique to Data sources","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-04T10:46:09.954822","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000506"}
{"_id":{"$oid":"5ef4ded2f5c47b466ed59dc8"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer_glycoeffect.csv","filename":"human_protein_mutation_cancer_glycoeffect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_cancer_glycoeffect.stat.csv","filename":"human_protein_mutation_cancer_glycoeffect.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"98307fa073fd02a5b824ca51a5034d50","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Cancer Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Cancer Mutation LOG and GOG effect","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-25T13:28:50.371628","modified":"2020-06-25T13:44:35.587930","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000507"}
{"_id":{"$oid":"5ef4dfcef5c47b46ded175bd"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_germline_glycoeffect.csv","filename":"human_protein_mutation_germline_glycoeffect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_germline_glycoeffect.stat.csv","filename":"human_protein_mutation_germline_glycoeffect.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"4c60bae4a234bbf413f04f4d45089070","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Germline Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Germline Mutation LOG and GOG effect","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-25T13:33:02.009109","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000508"}
{"_id":{"$oid":"5ef4e0ddf5c47b47008dae58"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_somatic_glycoeffect.csv","filename":"human_protein_mutation_somatic_glycoeffect.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation_somatic_glycoeffect.stat.csv","filename":"human_protein_mutation_somatic_glycoeffect.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"0a3e75d21c3fb53f2362c42657cd6713","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Somatic Mutations LOG-GOG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Somatic Mutations LOG and GOG effect","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-25T13:37:33.727471","modified":"2020-06-25T13:38:03.228765","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000509"}
{"_id":{"$oid":"5ef4e511f5c47b48a0ea9a0b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/compiled/sarcov1_proteoform_glycosylation_sites_literature.csv","filename":"sarcov1_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarcov1_proteoform_glycosylation_sites_literature.csv","filename":"sarcov1_proteoform_glycosylation_sites_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarcov1_proteoform_glycosylation_sites_literature.stat.csv","filename":"sarcov1_proteoform_glycosylation_sites_literature.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"1c135e0e7ddd85d5e82bcc4fe5724204","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycosylation Sites (Literature)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-06-25T13:55:29.887349","modified":"2020-07-20T16:53:16.362076","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"","filename":""}],"output_list":[],"prerequisite":[],"description":""}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["This dataset contains sarscov1 glycosylation sites from literature. PMID - 16442106"],"bco_id":"http://data.glygen.org/GLY_000510"}
{"_id":{"$oid":"5ef62866f5c47b6c0d3c859b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature.csv","filename":"human_proteoform_citations_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature.stat.csv","filename":"human_proteoform_citations_literature.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"2d32dcc1cf91bd39a6e60650726dc911","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Literature)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T12:55:02.653766","modified":"2020-06-26T13:00:05.105080","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature.csv","filename":"human_proteoform_citations_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-28T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Proteoform Citations (Literature) dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000143. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000511"}
{"_id":{"$oid":"5ef64c24f5c47b70cc547fa0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_citations_literature.csv","filename":"sarscov1_proteoform_citations_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_citations_literature.csv","filename":"sarscov1_proteoform_citations_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_citations_literature.stat.csv","filename":"sarscov1_proteoform_citations_literature.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"0c1b8dc7d9ef76ceaa42b7bf81755ae9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"SARS coronavirus (SARS-CoV-1)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"SARS CoV1 Proteoform Citations (Literature)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T15:27:32.833475","modified":"2020-06-26T15:56:47.194026","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-06-26T15:15:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv","filename":"sarscov1_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"access_time":"2020-06-26T15:17:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/","filename":""}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file sarscov1_proteoform_glycosylation_sites_literature.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000515"}
{"_id":{"$oid":"5ef64bb6f5c47b708aebf617"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_tyr_o_linked.csv","filename":"human_proteoform_citations_tyr_o_linked.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_tyr_o_linked.csv","filename":"human_proteoform_citations_tyr_o_linked.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_tyr_o_linked.stat.csv","filename":"human_proteoform_citations_tyr_o_linked.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"796e153db81db4d34206602850be3e4e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations (Tyr O-linked)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Tyr O-linked)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T15:25:42.130665","modified":"2020-08-19T14:16:32.023794","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-06-26T15:15:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}],"output_list":[{"access_time":"2020-06-26T15:17:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_tyr_o-linked.csv","filename":"human_proteoform_citations_tyr_o-linked.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file human_proteoform_glycosylation_sites_tyr_o_linked.csv. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000514"}
{"_id":{"$oid":"5ef64c97f5c47b711d05e324"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_glycosylation_sites_literature_mining.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature_mining.csv","filename":"human_proteoform_citations_literature_mining.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature_mining.stat.csv","filename":"human_proteoform_citations_literature_mining.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"cdb01e956709a79ce8b1f04a2b5b1f1a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Literature Mining)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T15:29:27.375356","modified":"2020-06-26T15:51:32.207997","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-06-26T15:15:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv","filename":"human_proteoform_citations_literature_mining.csv"}],"output_list":[{"access_time":"2020-06-26T15:17:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_literature_mining.csv","filename":"human_proteoform_citations_literature_mining.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000481. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000516"}
{"_id":{"$oid":"5ef64770f5c47b6e9cf76ded"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_citations_literature.csv","filename":"hcv1a_proteoform_citations_literature.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_citations_literature.stat.csv","filename":"hcv1a_proteoform_citations_literature.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"257707d4a6ff6ff28e70b2a5d117ccc9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Hepatitis C virus (genotype 1a, isolate H)","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"HCV1a Proteoform Citations (Literature)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T15:07:28.950575","modified":"2020-06-26T15:37:27.660430","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-06-26T15:15:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}],"output_list":[{"access_time":"2020-06-26T15:17:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_citations_literature.csv","filename":"hcv1a_proteoform_citations_literature.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000335. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000512"}
{"_id":{"$oid":"5ef64a3bf5c47b7034f5a395"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-06-26T15:17:19-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_harvard.csv","filename":"human_proteoform_citations_harvard.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_harvard.stat.csv","filename":"human_proteoform_citations_harvard.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"7f4f9f961c4af53befbf63a364258f56","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteoform Citations (Harvard)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-26T15:19:23.571116","modified":"2020-06-26T15:40:19.846620","version":"1.7.9"},"description_domain":{"keywords":["PMID","journal","citations","authors","Literature","PubMed"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2020-06-26T15:15:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}],"output_list":[{"access_time":"2020-06-26T15:17:19-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_harvard.csv","filename":"human_proteoform_citations_harvard.csv"}],"prerequisite":[],"description":"The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2020-06-26T15:15:19-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset provides citation details corresponding to the PubMed ID (PMID) from file https://data.glygen.org/GLYDS000142. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID."],"bco_id":"http://data.glygen.org/GLY_000513"}
{"_id":{"$oid":"5f3aebe2f5c47b5a6a6ad870"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_iptmnet.csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_iptmnet.stat,csv","filename":"human_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"87555949fcf330b9e163901ff63301ae","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Phosphorylation Sites (iPTMNet)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-08-17T16:43:14.212000","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000519"}
{"_id":{"$oid":"5ed8f638f5c47b6196d34914"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_gptwiki.csv","filename":"human_proteoform_glycosylation_sites_gptwiki.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"sarscov2_proteoform_citations_unicarbkb_literature.csv","filename":"sarscov2_proteoform_citations_unicarbkb_literature.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_pubchem_xref_mapping.csv","filename":"protein_glygen_pubchem_xref_mapping.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_pubchem_xref_mapping.stat.csv","filename":"protein_glygen_pubchem_xref_mapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8fe7b0efbbb6edd12413b5db16a37659","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"GlyGen-PubChem Protein Crossreferences","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"\"https://creativecommons.org/licenses/by/4.0/\"","name":"GlyGen-PubChem Protein Crossreferences Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-06-04T09:25:12.224023","modified":"2020-06-04T13:29:28.212206","version":"1.7.9"},"description_domain":{"keywords":["PubChem Protein","GlyGen","crossreferences","human","mouse","rat","hcv1a","hcv1b","sarscov1","sarscov2","NCBI RefSeq"],"pipeline_steps":[{"name":"make-species-agnostic-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv","filename":"human_proteoform_glycosylation_sites_glyconnect.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv","filename":"http://data.glygen.org/ln2wwwdata/reviewed/"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_harvard.csv","filename":"human_proteoform_glycosylation_sites_harvard.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_literature.csv","filename":"human_proteoform_glycosylation_sites_literature.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv","filename":"human_proteoform_glycosylation_sites_tyr_o_linked.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv","filename":"mouse_proteoform_glycosylation_sites_glyconnect.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv","filename":"rat_proteoform_glycosylation_sites_glyconnect.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv","filename":"rat_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_citations_unicarbkb_literature.csv","filename":"sarscov2_proteoform_citations_unicarbkb_literature.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv","filename":"sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv","filename":"hcv1a_proteoform_glycosylation_sites_literature.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv","filename":"hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"},{"access_time":"","sha1_chksum":"","uri":"mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_refseq.csv","filename":"rat_protein_xref_refseq.csv"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_xref_refseq.csv","filename":"sarscov1_protein_xref_refseq.csv"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv","filename":"protein_glygen_uniprotkb_xref_mapping.tsv"}],"prerequisite":[],"description":"The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, hcv1a, hcv1b, sarscov1 and sarscov2 species and maps it to the refseq accessions and adds the corresponding glycosylation annotation to extract it into a csv dataset file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The GlyGen-PubChem Protein Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of PubChem Protein to GlyGen crossreferences. In the dataset, the UniProtKB glycoprotein accessions are mapped to the RefSeq accesions and glycosylation annotation corresponding to glycoprotein have been added. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000499"}
{"_id":{"$oid":"5f0f66e5f5c47b178a4949ab"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"\"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_o_glcnac_mcw.csv","filename":"human_proteoform_citations_o_glcnac_mcw.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"\"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_citations_o_glcnac_mcw.stat.csv","filename":"human_proteoform_citations_o_glcnac_mcw.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"de298c2058837b809c9e70c3c8b021d0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Protein Citations O-GlcNAc (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human O-GlcNAc Glycosylation Citations (MCW)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-07-15T16:28:21.779974","modified":"2020-07-17T11:54:09.706452","version":"1.7.9"},"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000518"}
{"_id":{"$oid":"5f3aef8af5c47b5b0a264539"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"rat_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"aaeff02fb4bdd57893c18ca37f451353","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Rat Phosphorylation Sites (iPTMnet)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-08-17T16:58:50.536651","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000521"}
{"_id":{"$oid":"5f0758f3f5c47b2c6cff7384"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_o-glcnacome_mcw.csv","filename":"human_o-glcnacome_mcw.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"}},{"mediatype":"txt","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"17a7cae2436e6114886b0015f025a8de","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"O-GlcNAc Glycosylation Sites (MCW)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human O-GlcNAc Glycosylation Sites (MCW)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"Medical College of Wisconsin","contribution":["contributedBy"],"name":"Stephanie Olivier-Van Stichelen","email":"solivier@mcw.edu"}],"created":"2020-07-09T13:50:43.000375","modified":"2020-10-01T13:17:11.746019","version":"1.7.9"},"description_domain":{"keywords":["O-GlcNAc"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_o-glcnacome_mcw.csv","filename":"human_o-glcnacome_mcw.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log","filename":"human_proteoform_glycosylation_sites_o_glcnac_mcw.log"}],"prerequisite":[],"description":"The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Human O-GlcNAc Glycosylation Sites (MCW) contains human (taxid:9606) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techiniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.","The dataset is contributed from the Stephanie Olivier's lab","DISCLAIMER - Most of the modifications have been verified and discovered as 100% O-GlcNAc modifications and the O-GlcNAc score helps in determining the probability. However, we cannot be certain for every single modification to be O-GlcNAc modification","QC check -  The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen’s human protein master list of UniProtKB canonical accessions to ensure all of the proteins belong to human species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen’s fasta sequence for the corresponding human UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.","The log file - https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_o_glcnac_mcw.log contains the entries that were excluded from the output file along with the reason for exclusion.","The orginal unprocessed dataset in excel format can be found at https://figshare.com/articles/The_human_O-GlcNAcome_database/12443495/4"],"bco_id":"http://data.glygen.org/GLY_000517"}
{"_id":{"$oid":"5f3aed0cf5c47b5aaea5fcc6"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv","filename":"mouse_proteoform_phosphorylation_sites_iptmnet.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"5da8bd1f0d0dda5ad73a2b8bfd72d4d8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Phosphorylation Sites (iPTMnet)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Mouse Phosphorylation Sites (iPTMNet)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-08-17T16:48:12.211710","modified":"2020-08-17T16:48:31.185924","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000520"}
{"_id":{"$oid":"5f3af05af5c47b5b94764b21"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"human_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycation_sites_uniprotkb.csv","filename":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"human_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"8c86d1c682279eec29f9a0eddf717216","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Human Glycation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-08-17T17:02:18.395740","modified":"2020-08-17T17:05:39.113816","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000522"}
{"_id":{"$oid":"5f3afab0f5c47b5c345509c0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}},{"uri":{"access_time":"2019-10-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"a807a9fa518b58ce906cef7b39807e8d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Mus musculus","category_name":"species"},{"category_value":"Proteoform","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Mouse Glycation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-08-17T17:46:24.854615","modified":"","version":"1.7.9"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation","UniProtKB","PubMed","Evidence and conclusion Ontology"],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt","filename":"uniprot-proteome-mus-musculus.nt"}],"output_list":[{"access_time":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse Glycosylation Sites (UniProtKB) dataset contains mouse [taxid:10090] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000523"}
{"_id":{"$oid":"5f6cd88bf5c47b0de0793525"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3","checksum":"675acaebb3dd84e45e8f75f1d59393ed","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"","name":"Mouse Glycosylation Proteins (Patel Lab)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"rsn13@gwu.edu"}],"created":"2020-09-24T13:34:03.947890","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/GLY_000529"}
{"_id":{"$oid":"5f3d6a34f5c47b3514fffc60"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_disease_idmap.csv","filename":"protein_disease_idmap.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_domap.stat.csv","filename":"protein_disease_idmap.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"ba6a42ef3a3c0d0b52eb77ff8b2a1fbb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease ID Mapping","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease ID Mapping","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-08-19T14:06:44.941024","modified":"2020-08-19T14:13:47.923664","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Disease Ontology Mapping dataset contains human [taxid:9606] UniProtKB canonical accession cross-reference mappings to the Disease Ontology Ids (DOID)","If you use this dataset please provide proper attribution to GlyGen and Disease ontology, Monarch Disease Ontology and EMBL-EBI-UniProt"],"bco_id":"http://data.glygen.org/GLY_000525"}
{"_id":{"$oid":"5f3d6bb3f5c47b3584a5dffd"},"io_domain":{"input_subdomain":[],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_disease_names.csv","filename":"protein_disease_names.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/protein_disease_names.stat.csv","filename":"protein_disease_names.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"5c91e0079ab50b812755ed04aed1104d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Disease Names","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Disease Names","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2020-08-19T14:13:07.626533","modified":"2020-08-19T14:15:31.389234","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["",""],"bco_id":"http://data.glygen.org/GLY_000526"}
{"_id":{"$oid":"5f3afb3af5c47b5ca32292d8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-10-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycation_sites_uniprotkb.stat.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"7d5e9cd99df4cc9e92a6a0d0e184f7c4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Rattus norvegicus","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Glycation Sites (UniProtKB)","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Reviewed","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"","name":"Rat Glycation Sites (UniProtKB)","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2020-08-17T17:48:42.126261","modified":"","version":"1.7.9"},"description_domain":{"keywords":[],"pipeline_steps":[{"name":"make-proteoform-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt","filename":"uniprot-proteome-rattus-norvegicus.nt"}],"output_list":[{"access_time":"2019-10-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycation_sites_uniprotkb.csv","filename":"rat_proteoform_glycation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script loads the glycation information from the triplestore conatining triples from the nt file and extracts as a csv dataset"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py","filename":"make-proteoform-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"parametric_domain":[],"usability_domain":["The Rat Glycation Sites (UniProtKB) dataset contains mouse [taxid:10116] UniProtKB canonical accessions with information on reported and predicted glycation sites in UniProtKB database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000524"}
{"_id":{"$oid":"5f5a7e4bf5c47b361cb33342"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/sandbox_accessions.csv","filename":"sandbox_accessions.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_sandbox_accessions.csv","filename":"glycan_xref_sandbox_accessions.csv"}}]},"bco_spec_version":"1.3","checksum":"34a8e5dd3ce3ed926df351dd985de158","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Sanbox Glycan accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Sandbox accessions (GlyTouCan Accession)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["providedBy"],"name":"Will York","email":"will@ccrc.uga.edu"}],"created":"2020-09-10T15:28:11.224030","modified":"2020-09-10T15:46:50.083006","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan accessions","Glycans","Sandbox"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"access_time":"2020-09-10T15:28:11.224030","uri":"https://data.glygen.org/ln2wwwdata/source/sandbox_accessions.csv","filename":"sandbox_accessions.csv"}],"output_list":[{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_xref_sandbox_accessions.csv","filename":"glycan_xref_sandbox_accessions.csv"}],"prerequisite":[],"description":"The dataset was directly downloaded from the provider and a script was used to check if the GlyTouCan Ac is included in the glycan masterlist (https://data.glygen.org/GLY_000281)"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset includes GlyTouCan accessions included in Sandbox application."],"bco_id":"http://data.glygen.org/GLY_000527"}
{"_id":{"$oid":"5f5a83def5c47b386508bf29"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}}]},"bco_spec_version":"1.3","checksum":"b7a7a0148fc0d84042db243a1ba093c4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"Glycan","category_name":"molecule"},{"category_value":"Glycan citations NCFG","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Asparagine-Linked Glycans (PMID30745240)","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"NCFG- Harvard University","contribution":["providedBy","createdBy"],"name":"Akul Mehta","email":"aymehta@bidmc.harvard.edu"},{"orcid":"","affiliation":"NCFG- Harvard University","contribution":["authoredBy"],"name":"Richard D. Cummings","email":"rcummin1@bidmc.harvard.edu"},{"orcid":"","affiliation":"NCFG- Harvard University","contribution":["authoredBy"],"name":"Chao Gao","email":"cgao3@bidmc.harvard.edu"}],"created":"2020-09-10T15:51:58.182517","modified":"2020-09-30T13:40:14.091609","version":"1.7.9"},"description_domain":{"keywords":["GlyTouCan accessions","Glycans","Citations NCFG","Synthesized Glycan","ID/Accession Mapping"],"pipeline_steps":[{"name":"","step_number":1,"version":"","input_list":[{"access_time":"2020-09-10T15:28:11.224030","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_evidence_ncfg.csv","filename":"glycan_evidence_ncfg.csv"}],"output_list":[{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_citations_ncfg.csv","filename":"glycan_citations_ncfg.csv"}],"prerequisite":[],"description":"Authors provided a list of sequences in CFG linear nomenclature format (modified IUPAC condensed) along with the PubMed ID. The sequences were entered into GlycoGlyph to retrieve GlyTouCan accession numbers manually. For those sequences not present in GlyTouCan, the GlycoCT produced in GlycoGlyph was used to register the structures and the GlyTouCan accession numbers were then added to the list.This dataset was directly downloaded from the provider and a script was used to check if the GlyTouCan Ac is included in the glycan masterlist (https://data.glygen.org/GLY_000281). The script also added additional information such as title,journal_name,publication_date,authors based on the PMID."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2020-09-10T15:28:11.224030","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/","filename":""}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The dataset lists the synthesized glycans which are identified by their GlyTouCan accessions. Source:- Richard Cummings Laboratory (NCFG BIDMC Harvard Medical School)"],"bco_id":"http://data.glygen.org/GLY_000528"}
{"_id":{"$oid":"5f6cd900f5c47b0e2607ebbd"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-23T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-10-23T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.stat.csv","filename":"human_protein_masterlist.stat.csv"}}]},"bco_spec_version":"1.3","checksum":"2a23a3189ff89ed5c5be0e7991647056","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Homo sapiens","category_name":"species"},{"category_value":"Protein","category_name":"molecule"},{"category_value":"Protein Canonical Accessions","category_name":"tags"},{"category_value":"csv","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Test BCO - Glycosylation sites on Mouse proteins","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2020-09-24T13:36:00.724463","modified":"2020-09-24T15:31:02.538423","version":"1.7.9"},"description_domain":{"keywords":["canonical accessions","gene name","protein isoforms","complete proteome","UniProtKB"],"pipeline_steps":[{"name":"make-protein-dataset.py","step_number":1,"version":"","input_list":[{"access_time":"2019-10-24T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt","filename":"uniprot-proteome-homo-sapiens.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py","filename":"make-protein-dataset.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human Proteome Materlist dataset contains human [taxid:9606] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is derived from 2019_09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/GLY_000530"}