{"_id":{"$oid":"5c48e7f8f5c47b65811b022d"},"provenance_domain":{"version":"1.0.5"}}
{"_id":{"$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":"3bdc67aec812ef2f709c2ed7b5abdfea","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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":"2019-11-25T15:37:13.840029","version":"1.5.10"},"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/DSBCO_000001"}
{"_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":"4dae3a23a416b57aec02e3b84b73e43b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T16:01:15.319504","version":"1.5.10"},"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/DSBCO_000002"}
{"_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":"87d1682011e007451035cedc45421783","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T16:05:24.642954","version":"1.5.10"},"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/DSBCO_000003"}
{"_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":"42e7c98729bec0d8e01eb15d6d10c860","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:15:07.206906","version":"1.5.10"},"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. If you use this dataset please provide proper attribution to UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000004"}
{"_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":"1.5.10"},"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/DSBCO_000005"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.872734","modified":"2019-02-19T14:44:52.840281","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000006"}
{"_id":{"$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":"bdcd992e3121a59e3239c18408d040e0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T15:43:52.751584","version":"1.5.10"},"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/DSBCO_000007"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.874820","modified":"2019-02-19T14:45:28.514598","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000008"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000009"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.876875","modified":"2019-02-19T14:46:18.887967","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000010"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000011"}
{"_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":"b2086fce35f8714dc45e573754b85cbb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T15:56:20.584433","version":"1.5.10"},"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/DSBCO_000012"}
{"_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":"9324605ddd8d1e414a629f842683c073","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-05T16:18:30.273531","version":"1.5.10"},"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/DSBCO_000013"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.880988","modified":"2019-02-19T14:47:39.354378","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000014"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000017"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cfe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.886120","modified":"2019-02-19T14:48:24.630823","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000019"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000020"}
{"_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":"5e3d2f57c8def969b975fd386b40300f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-03T10:10:53.391808","version":"1.5.10"},"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. 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/DSBCO_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":"68706a279abd83230fd459471123d37c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:47:15.419745","version":"1.5.10"},"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. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000022"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.890267","modified":"2019-02-19T13:44:51.567646","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000023"}
{"_id":{"$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":"2019-02-08T13:11:15-0500","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":"2019-02-08T13:15:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation.csv","filename":"human_protein_mutation.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation.stat.csv","filename":"human_protein_mutation.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b3c0990e45f4c00e7f0d06f0975e7737","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.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":"2019-11-28T10:58:39.643598","version":"1.5.10"},"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":"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/mutid-map.final.csv","filename":"mutid-map.final.csv"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_mutation.csv","filename":"human_protein_mutation.csv"}],"prerequisite":[],"description":"The script extracts the mutation data that has cancer mutation frequency of greater than of 0.01(1%) 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 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 GlyGen only integrates and displays the data that has cancer mutation frequency of greater than of 0.01(1%)"],"bco_id":"http://data.glygen.org/DSBCO_000024"}
{"_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":"c14348ec428eb2f5687d47244b9c83f6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:17:42.275857","version":"1.5.10"},"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/DSBCO_000025"}
{"_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":"5c0646ee90b346a2259e1645f3bdfa4b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:20:10.605457","version":"1.5.10"},"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/DSBCO_000026"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d06"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.894406","modified":"2019-02-19T13:47:11.999143","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000027"}
{"_id":{"$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":"6009eb68e0b015c6b22fc17b9dc0b920","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:01:07.049126","version":"1.5.10"},"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/DSBCO_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":"c41019b147a684e090d55af56f84de62","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T10:59:29.016010","version":"1.5.10"},"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/DSBCO_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":"577235cf408ad7534a5c48e0c47e8587","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:13:56.913765","version":"1.5.10"},"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/DSBCO_000030"}
{"_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":"6d337773a90deabffbca5425ea442d25","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:27:45.006148","version":"1.5.10"},"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/DSBCO_000031"}
{"_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":"f29fd6d9f2645e38f7d9b040b2da30c3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:30:29.090948","version":"1.5.10"},"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/DSBCO_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":"0e5d2b08fc8d813443d4d16b7da9f86e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T15:43:02.674250","version":"1.5.10"},"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/DSBCO_000033"}
{"_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":"1663dfb6c87b20c32e1381e4ab8eafe3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T15:46:07.055049","version":"1.5.10"},"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/DSBCO_000034"}
{"_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":"276e42ef4bf271e9666f29526ebcd325","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T15:56:50.453778","version":"1.5.10"},"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 2019-05 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000035"}
{"_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":"d892ccf73eaf5d006c94de3318c656d8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T16:08:32.957129","version":"1.5.10"},"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/DSBCO_000036"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d10"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.904697","modified":"2019-02-19T13:51:17.764255","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000037"}
{"_id":{"$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":"50dc10b230be30c67b6b76f15fe67569","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T17:07:57.744044","version":"1.5.10"},"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/DSBCO_000038"}
{"_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":"be3d8f8b11f2f3ae910be977af942152","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T17:08:41.033470","version":"1.5.10"},"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/DSBCO_000039"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d13"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_2019_08_23_02_49_01.csv","filename":"human_2019_08_23_02_49_01.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"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"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.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_unicarbkb.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb.csv"}},{"mediatype":"log","uri":{"access_time":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"","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":"c7ea77f079b3f554ed4b7de7d5bf5319","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"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":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-01-23T17:21:05.907769","modified":"2019-12-02T15:55:00.055104","version":"1.5.10"},"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":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_2019_08_23_02_49_01.csv","filename":"human_2019_08_23_02_49_01.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv","filename":"human_protein_masterlist.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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 (human_2019_08_23_02_49_01.csv) ;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 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":"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":{},"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/DSBCO_000040"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d14"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_2019_08_23_02_49_14.csv","filename":"mouse_2019_08_23_02_49_14.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"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"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"","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":"3805626f0918f30b0f2e1559adcf3577","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"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":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-01-23T17:21:05.908793","modified":"2019-12-02T15:54:00.319246","version":"1.5.10"},"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":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_2019_08_23_02_49_14.csv","filename":"mouse_2019_08_23_02_49_14.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv","filename":"mouse_protein_masterlist.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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 (mouse_2019_08_23_02_49_14.csv ;for script:mouse_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 (mouse_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. 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 (mouse_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":"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":{},"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/DSBCO_000041"}
{"_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","filename":"N-linked-ARG"}},{"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/O-linked-ASP","filename":"O-linked-ASP"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"}},{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"}},{"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_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":"1295b1328593004f195026e46468bc12","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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":"2019-01-23T17:21:05.909814","modified":"2019-11-26T16:30:40.904331","version":"1.5.10"},"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"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN","filename":"N-linked-ASN"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP","filename":"O-linked-ASP"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"},{"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_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs from the N-linked and O-linked files and extract the PDB files containing the glycosylation information from RCSB PDB using their API. The script using also checks the position of UniProtKB aa position in the file with the current sequences and finally maps the UniProtKB accession to the UniProtKB canonical accessions for the given organism."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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 with RCSB PDB Id's and with the information of glycosylation sites which are also mapped to the UniProtKB accession's sequence position glycosylation and RCSB PDB Id's [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"bco_id":"http://data.glygen.org/DSBCO_000042"}
{"_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","filename":"N-linked-ARG"}},{"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/O-linked-ASP","filename":"O-linked-ASP"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"}},{"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":"2019-10-26T17:43:17-0500","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":"611abab08714fc92a8efd21b1148c52e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T16:33:30.123655","version":"1.5.10"},"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"},{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN","filename":"N-linked-ASN"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP","filename":"O-linked-ASP"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"},{"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_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 from the N-linked and O-linked files and extract the PDB files containing the glycosylation information from RCSB PDB using their API. The script using also checks the position of UniProtKB aa position in the file with the current sequences and finally maps the UniProtKB accession to the UniProtKB canonical accessions for the given organism."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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 with RCSB PDB Id's and with the information of glycosylation sites which are also mapped to the UniProtKB accession's sequence position glycosylation and RCSB PDB Id's [www.rcsb.org, Nucleic Acids Research, 28: 235-242.(https://www.ncbi.nlm.nih.gov/pmc/articles/PMC102472/)]."],"bco_id":"http://data.glygen.org/DSBCO_000043"}
{"_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":"1.5.10"},"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/DSBCO_000044"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d18"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.912928","modified":"2019-02-19T13:52:21.318112","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000045"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000046"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.914987","modified":"2019-02-19T13:53:09.793765","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000047"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000048"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.917039","modified":"2019-02-19T13:53:59.703677","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000049"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000050"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.919138","modified":"2019-02-19T13:55:00.615875","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000051"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000052"}
{"_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":"78326371eb100797e45901cdbddce4b5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T16:38:42.337232","version":"1.5.10"},"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/DSBCO_000053"}
{"_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":"be5c9f964900a1492a4d6517fd72b68c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T16:41:48.314632","version":"1.5.10"},"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/DSBCO_000054"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d22"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.923235","modified":"2019-02-19T14:01:46.926371","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000055"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000056"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d24"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.925284","modified":"2019-02-19T14:02:54.659774","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000057"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000058"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d26"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.927329","modified":"2019-02-19T14:03:56.869077","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000059"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_000063"}
{"_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":"1.5.10"},"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/DSBCO_000064"}
{"_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":"1.5.10"},"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/DSBCO_000065"}
{"_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":"1.5.10"},"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/DSBCO_000066"}
{"_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":"1.5.10"},"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/DSBCO_000067"}
{"_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":"1.5.10"},"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/DSBCO_000068"}
{"_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":"1.5.10"},"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/DSBCO_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.zip","filename":"images.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.tar.gz","filename":"glycan_images.tar.gz"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_images.tar.stat.csv","filename":"glycan_images.tar.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"64f7de7a6ad5532f9cdd37bab80171ca","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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 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":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.938796","modified":"2019-11-13T13:17:28.793654","version":"1.5.10"},"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.zip","filename":"images.zip"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_images.tar.gz","filename":"glycan_images.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/DSBCO_000070"}
{"_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":"1.5.10"},"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/DSBCO_000071"}
{"_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":"1.5.10"},"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/DSBCO_000072"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d34"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.941909","modified":"2019-02-19T14:05:10.307734","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000073"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000074"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d36"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.943995","modified":"2019-02-19T14:08:33.746059","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000075"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000076"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d38"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.946079","modified":"2019-02-19T14:09:57.295655","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000077"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_000079"}
{"_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":"1.5.10"},"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/DSBCO_000080"}
{"_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":"3c479c3e949677b414d22f1282eabb38","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-26T16:49:21.670366","version":"1.5.10"},"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/DSBCO_000081"}
{"_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":"33fe59362ea9f463ff2505f3a3561065","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-05T16:07:02.838360","version":"1.5.10"},"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/DSBCO_000082"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.952378","modified":"2019-02-19T14:12:30.636705","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000083"}
{"_id":{"$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/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"}},{"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"}}],"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":"d9aece6df1a2f61a7476fd4f47685707","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-01-23T17:21:05.953432","modified":"2019-12-02T18:35:54.503213","version":"1.5.10"},"description_domain":{"keywords":["disease","HPO","OMIM","Genomics England","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"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/congenital_disorders_of_glycosylation.tsv","filename":"congenital_disorders_of_glycosylation.tsv"},{"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"}],"output_list":[{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/compiled/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.","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/DSBCO_000084"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d40"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"dataset_categories":[{"category_value":"","category_name":"species"},{"category_value":"","category_name":"molecule"},{"category_value":"","category_name":"tags"},{"category_value":"","category_name":"file_type"},{"category_value":"Retired","category_name":"status"},{"category_value":"internal","category_name":"scope"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.954630","modified":"2019-02-19T14:13:24.932675","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","param":"","value":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000085"}
{"_id":{"$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":"1.5.10"},"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/DSBCO_000086"}
{"_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":"773ac37932e57ff0eebcf59ad8bd5dba","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T11:42:10.985895","version":"1.5.10"},"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_idmapping.csv","filename":"human_protein_idmapping.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/DSBCO_000087"}
{"_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":"e7852a34d46a55b0020b74ea9148645b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T11:44:23.917671","version":"1.5.10"},"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/DSBCO_000088"}
{"_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":"f5e0883117d6376fea25dd7712b929f6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"Reviewed","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":"2019-12-02T15:17:09.595267","version":"1.5.10"},"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 Diease ontology"],"bco_id":"http://data.glygen.org/DSBCO_000089"}
{"_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":"83fb9c64fbd9c32d2ed251bbefef0450","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:03:56.378959","version":"1.5.10"},"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/DSBCO_000090"}
{"_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":"38a3518198287bf44a6fbf64e77cae37","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:12:56.435448","version":"1.5.10"},"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/DSBCO_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":"ea85a728caede0de2fe9e37224c64392","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:14:53.662040","version":"1.5.10"},"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/DSBCO_000092"}
{"_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":"0593fe8295128a58c88d1cb35ec2b1d9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:22:31.123854","version":"1.5.10"},"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/DSBCO_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":"ebb3fa5d6492b736ec0b9db4fe0747b9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:21:12.343493","version":"1.5.10"},"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/DSBCO_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":"62b04276f74a5659680ceb49dc0e2635","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:25:02.872646","version":"1.5.10"},"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/DSBCO_000095"}
{"_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":"f77ca41266c7d958c5cd6c068e09d7c5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:28:12.678950","version":"1.5.10"},"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/DSBCO_000096"}
{"_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":"81a270be81a7576010161fa4e6d7d347","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:30:50.294660","version":"1.5.10"},"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/DSBCO_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":"833b1acc8124538c767d9d3f3377af79","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:33:47.025491","version":"1.5.10"},"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/DSBCO_000098"}
{"_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":"88697ac3e0a8fc41fd18efcc72ed2aff","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:36:29.113874","version":"1.5.10"},"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/DSBCO_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":"d529666fd932540a6bddde67d4412a14","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:40:06.081600","version":"1.5.10"},"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/DSBCO_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":"d4918ee36048087ae51aa34f9ac5c1de","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:00:04.135602","version":"1.5.10"},"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/DSBCO_000101"}
{"_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":"a8b1e8d2f0eecc4f640f3458e88a17ea","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T12:46:53.857927","version":"1.5.10"},"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/DSBCO_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":"d649e60f8f8ea138c1fb8b98baa0a6d6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:00:23.311222","version":"1.5.10"},"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/DSBCO_000103"}
{"_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":"6b52e3c08c09a454fc8e5f52047bf986","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T13:49:47.916764","version":"1.5.10"},"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/DSBCO_000104"}
{"_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":"eecefd3e6774b806cbeb01992247a5d0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T13:52:10.686061","version":"1.5.10"},"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/DSBCO_000105"}
{"_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":"73915371bc0f0acb006c681eed450d5f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T13:59:05.861009","version":"1.5.10"},"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/DSBCO_000106"}
{"_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":"592e7b1bb695f509003f5631689d1fb4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T13:58:40.314911","version":"1.5.10"},"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/DSBCO_000107"}
{"_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":"35f0e355332a03e000a275b89df2f73c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:05:11.216827","version":"1.5.10"},"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/DSBCO_000108"}
{"_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":"47e7432ce0e6b9a551d71b0e5251b1d4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:09:16.748708","version":"1.5.10"},"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/DSBCO_000109"}
{"_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":"2226398b9d6821425e77b259a4a85d1b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:11:31.809633","version":"1.5.10"},"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/DSBCO_000110"}
{"_id":{"$oid":"5c8bce48f5c47b4d41044d46"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[],"created":"","modified":"2019-03-15T14:41:43.658687","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000111"}
{"_id":{"$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":"7bb27b5352c0e1c6dd42bf8aced839a8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:14:12.087701","version":"1.5.10"},"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/DSBCO_000112"}
{"_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":"c33db2874a55ecf912f11b73f0b53f7f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:17:09.481122","version":"1.5.10"},"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/DSBCO_000113"}
{"_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":"ed15a62945ae5e08abbe1ee6c65f80b7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:24:48.279435","version":"1.5.10"},"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/DSBCO_000114"}
{"_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":"63f1be8c48ac3e25e450a7fdbf2437f2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:27:56.240995","version":"1.5.10"},"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/DSBCO_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":"0b88339df08cef820ff9b04d17c977bb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:30:09.874385","version":"1.5.10"},"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/DSBCO_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":"a8c96165d08c8c20d0d2cf015f089543","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:38:30.173510","version":"1.5.10"},"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/DSBCO_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":"9bad4b4c4182af3c915f637d5affec01","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:40:49.239670","version":"1.5.10"},"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/DSBCO_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":"8ee7acaf503a5b3545c36cc04088f36d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:42:52.188807","version":"1.5.10"},"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/DSBCO_000119"}
{"_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":"65a4865b89106b6613a060167525d8a9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:47:25.023665","version":"1.5.10"},"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/DSBCO_000120"}
{"_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":"dee8bc1e3c0bb686139dab08f5038285","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:49:26.914547","version":"1.5.10"},"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/DSBCO_000121"}
{"_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":"1f8c19135befdbbe4d44980930170829","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:52:37.585698","version":"1.5.10"},"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/DSBCO_000122"}
{"_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":"f7fe7468474a371e4dd0a0ad287f873e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:54:56.293869","version":"1.5.10"},"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/DSBCO_000123"}
{"_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":"0b82cef1566f7a49a122a8e6b368ead1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T14:57:45.322841","version":"1.5.10"},"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/DSBCO_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":"7e454422002a996b6346b6ab3165bc8d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:00:12.305784","version":"1.5.10"},"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/DSBCO_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":"a22591400d64f4b88ade78056bb7fd6c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:02:19.660485","version":"1.5.10"},"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/DSBCO_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":"22725f86a58baeb65b6e6e41a6a328bf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:49:10.623669","version":"1.5.10"},"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/DSBCO_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":"65af599808520adc5e56981be0558589","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:49:41.336963","version":"1.5.10"},"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/DSBCO_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":"de5ef28182e78d5679ff4f60ff2d02de","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:12:17.799098","version":"1.5.10"},"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/DSBCO_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":"0434e79ec042a362f62b34859ac0b3e7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:14:10.405978","version":"1.5.10"},"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/DSBCO_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":"0f309f08e29c27f6cd752af7c9b0e9fd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:52:17.077924","version":"1.5.10"},"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/DSBCO_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":"af4c1c36c6d064deebe4071021de84a1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-28T11:52:48.018872","version":"1.5.10"},"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/DSBCO_000132"}
{"_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":"16a35558ebb4fc570d8095ead8a37b8f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:30:45.385729","version":"1.5.10"},"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/DSBCO_000133"}
{"_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":"28488f4d0265b6ef6749335ccc0864d7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:34:09.163629","version":"1.5.10"},"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/DSBCO_000134"}
{"_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":"18e025057f7a91926739ca1b5843582b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:40:19.988202","version":"1.5.10"},"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/DSBCO_000135"}
{"_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":"c1bfb0840fe914693550c0753d5ed89a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:39:39.610423","version":"1.5.10"},"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/DSBCO_000136"}
{"_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":"1.5.10"},"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/DSBCO_000137"}
{"_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":"bcced2355d7f2bdcfff017a519afb48e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-27T15:46:19.767029","version":"1.5.10"},"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/DSBCO_000138"}
{"_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":"bfff1a6c19f162a364767f9e6e37f596","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"Retired","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":"2019-11-27T15:48:23.325747","version":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_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":"b63f9c52a651dc2bcd3723a88c434149","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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"],"name":"Christina Woo","email":"cwoo@chemistry.harvard.edu"}],"created":"2019-06-06T17:51:22.706056","modified":"2019-12-02T16:06:36.662343","version":"1.5.10"},"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 Christina Woo from Department of Chemistry and Chemical Biology, Harvard University. (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).  The listed protein (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLYDS000001)."],"bco_id":"http://data.glygen.org/DSBCO_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":"1.5.10"},"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., \u0026 Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular \u0026 Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Wi?niewski, J. R., \u0026 Mann, M. (2012). Quantification of theN-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular \u0026 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/DSBCO_000143"}
{"_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":"1.5.10"},"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/DSBCO_000144"}
{"_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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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-\u003cPUBCHEM_COMPOUND_CID\u003e , \u003cPUBCHEM_IUPAC_INCHI\u003e, \u003cPUBCHEM_IUPAC_INCHIKEY\u003e  from the sdf files to generate the final output file."}]},"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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-\u003cPUBCHEM_COMPOUND_CID\u003e , \u003cPUBCHEM_IUPAC_INCHI\u003e, \u003cPUBCHEM_IUPAC_INCHIKEY\u003e  from the sdf files to generate the final output file."}]},"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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-\u003cPUBCHEM_COMPOUND_CID\u003e , \u003cPUBCHEM_IUPAC_INCHI\u003e, \u003cPUBCHEM_IUPAC_INCHIKEY\u003e  from the sdf files to generate the final output file."}]},"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"1.5.10"},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_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/DSBCO_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":"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":"1.5.10"},"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/DSBCO_000220"}
{"_id":{"$oid":"5d715553f5c47b18c064d651"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_2019_08_23_02_49_25.csv","filename":"rat_2019_08_23_02_49_25.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_idmapping.csv","filename":"rat_protein_idmapping.csv"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"}},{"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"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"}},{"uri":{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"2019-08-28T17:45:17-0500","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":"","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":"46028f62edfcdd23b8b7102c2fe63aca","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["authoredBy"],"name":"Nathan Edwards","email":"Georgetown University"}],"created":"2019-09-05T14:34:59.005886","modified":"2019-12-02T15:57:18.974787","version":"1.5.10"},"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":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/rat_2019_08_23_02_49_25.csv","filename":"rat_2019_08_23_02_49_25.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv","filename":"rat_protein_masterlist.csv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/classification.tsv","filename":"classification.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_properties.tsv","filename":"glycan_properties.tsv"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_allsequences.fasta","filename":"rat_protein_allsequences.fasta"},{"access_time":"2019-08-28T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/aadict.csv","filename":"aadict.csv"}],"output_list":[{"access_time":"2019-08-28T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv","filename":"rat_proteoform_glycosylation_sites_unicarbkb.csv"},{"access_time":"2019-08-28T17:45:17-0500","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 (rat_2019_08_23_02_49_25.csv ;for script:rat_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 (rat_proteoform_glycosylation_sites_unicarbkb.2.log) for validation purposes but are not eliminated during the processing. 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 (rat_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":"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":{},"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/DSBCO_000221"}
{"_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":"2019-11-27T11:47:18.826372","version":"1.5.10"},"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/DSBCO_000222","checksum":"34e8563866b913cf58a7d6f0b98f29d9"}
{"_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":"2019-11-27T15:56:29.798569","version":"1.5.10"},"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/DSBCO_000223","checksum":"a413bc0160ba4bc9f37a5df9fe339e59"}
{"_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":"2019-12-04T17:09:19.549493","version":"1.5.10"},"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/DSBCO_000224","checksum":"36ee12ae26bdcae4bfda7103a92c1c71"}
{"_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":"Retired human_protein_glyco_disease.csv","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"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 \u0026 Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health \u0026 Science University","contribution":["contributedBy"],"name":"Melissa Haendel","email":"haendel@ohsu.edu"}],"created":"2019-09-06T14:06:38.953629","modified":"2019-12-02T18:23:59.311692","version":"1.5.10"},"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/DSBCO_000225","checksum":"c8ae815d6bcf659b4f789ff5a2e35f6e"}
{"_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":"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":"2019-09-06T14:06:38.954510","modified":"2019-11-26T16:36:08.184339","version":"1.5.10"},"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","filename":"N-linked-ARG"},{"access_time":"2019-07-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN","filename":"N-linked-ASN"},{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-ASP","filename":"O-linked-ASP"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"},{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"},{"access_time":"2019-07-26T17:43:17-0500","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_proteoform_glycosylation_sites_pdb.csv","filename":"rat_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"The script extracts the PDB IDs from the N-linked and O-linked files and extract the PDB files containing the glycosylation information from RCSB PDB using their API. The script using also checks the position of UniProtKB aa position in the file with the current sequences and finally maps the UniProtKB accession to the UniProtKB canonical accessions for the given organism."}]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-10-26T17:43:17-0500","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ARG","filename":"N-linked-ARG"}},{"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/O-linked-ASP","filename":"O-linked-ASP"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-GLU","filename":"O-linked-GLU"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER","filename":"O-linked-SER"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR","filename":"O-linked-THR"}},{"uri":{"access_time":"2019-10-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-TYR","filename":"O-linked-TYR"}},{"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":"2019-10-26T17:43:17-0500","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:10116] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in RCSB PDB database. If you use this dataset please provide proper attribution to RCSB PDB and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000226","checksum":"43b7cc2fe8ed801ba73404a6a97b7a5c"}
{"_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":"2019-11-28T01:52:55.479167","version":"1.5.10"},"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/DSBCO_000227","checksum":"84bedb2e277f2256b0a9a7a750805ce6"}
{"_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":"external","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":"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":"2019-09-06T14:06:38.956292","modified":"2019-12-05T15:08:46.646501","version":"1.5.10"},"description_domain":{"keywords":["signal peptide","ptm processing","UniProtKB"],"pipeline_steps":[{"name":"human_protein_proteinwoutsignalp.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/source/uniprot-proteome-9606-homo-sapiens-2019-05.nt","filename":"uniprot-proteome-9606-homo-sapiens-2019-05.nt"}],"output_list":[{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_signal_peptide_sequence.fasta","filename":"human_protein_signal_peptide_sequence.fasta"},{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinwoutsignalp.csv","filename":"human_protein_proteinwoutsignalp.csv"},{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/logs/human_protein_proteinwoutsignalp.log","filename":"human_protein_proteinwoutsignalp.log"},{"access_time":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_cleaved_signal_peptide_sequence.fasta","filename":"human_protein_cleaved_signal_peptide_sequence.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":"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_proteinwoutsignalp.csv","filename":"human_protein_proteinwoutsignalp.csv"}},{"mediatype":"fasta","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_signal_peptide_sequence.fasta","filename":"human_protein_signal_peptide_sequence.fasta"}},{"mediatype":"fasta","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_cleaved_signal_peptide_sequence.fasta","filename":"human_protein_cleaved_signal_peptide_sequence.fasta"}},{"mediatype":"txt","uri":{"access_time":"2019-07-26T17:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinwoutsignalp.log","filename":"human_protein_proteinwoutsignalp.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinwoutsignalp.stat.csv","filename":"human_protein_proteinwoutsignalp.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/human_protein_proteinwoutsignalp.py","filename":"human_protein_proteinwoutsignalp.py"}}]},"parametric_domain":[],"usability_domain":["The Human Protein Signal Peptide dataset contains human [taxid:9606] signal peptide information for the UniProtKB accessions. The dataset contains signal peptide sequence, signal peptide length, start and end position, cleaved protein sequence. The dataset is derived from 2019-05 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000228","checksum":"b214fc8b58265e47326413e8152c65b2"}
{"_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":"2019-11-28T01:55:20.600541","version":"1.5.10"},"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/DSBCO_000229","checksum":"30c910c1f0a74f2ea979e80b925ffb1a"}
{"_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 \u0026 Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"},{"orcid":"","affiliation":"Monarch Initiative - Oregon Health \u0026 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":"2019-12-01T15:03:31.922824","version":"1.5.10"},"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/DSBCO_000230","checksum":"ed05fda210268f4ee962baf8893be435"}
{"_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":"2019-12-01T15:04:40.336769","version":"1.5.10"},"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/DSBCO_000231","checksum":"313d12215a756a172edbfd317b09ec34"}
{"_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":"2019-11-28T01:58:29.733404","version":"1.5.10"},"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/DSBCO_000232","checksum":"067efa64cbed0a4d346b2caa26f21cea"}
{"_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":"2019-11-28T10:53:45.356680","version":"1.5.10"},"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/DSBCO_000233","checksum":"7662886e3b5d39c79fd3bf987ccdada4"}
{"_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":"2019-11-28T02:02:05.418854","version":"1.5.10"},"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/DSBCO_000234","checksum":"bec13dc398e4cb619ca30adb2496eaa7"}
{"_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":"2019-12-01T15:07:18.213629","version":"1.5.10"},"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/DSBCO_000235","checksum":"841b2d07c3bf71a132121679ade1e2b2"}
{"_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":"2019-11-28T10:57:08.743372","version":"1.5.10"},"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/DSBCO_000236","checksum":"0102f43a192f8ad18c774c3665226f4b"}
{"_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":"2019-11-27T15:41:42.417391","version":"1.5.10"},"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/DSBCO_000237","checksum":"f9687a82509b94ac7c9b1393be5133f7"}
{"_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":"2019-11-28T02:05:32.423925","version":"1.5.10"},"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/DSBCO_000238","checksum":"b9ca726c609572182f5343fcb396818e"}
{"_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":"2019-12-01T15:11:43.623994","version":"1.5.10"},"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/DSBCO_000239","checksum":"99751ac6e953c58768e19b2df96cbfaf"}
{"_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":"2019-11-25T16:00:18.886155","version":"1.5.10"},"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/DSBCO_000240","checksum":"057e2eb9a4b14e25157c8702376d89c2"}
{"_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":"2019-11-26T15:51:38.969334","version":"1.5.10"},"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/DSBCO_000241","checksum":"566de5b6657ed28b4ffefa2d10f285d9"}
{"_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":"2019-11-27T15:58:53.399004","version":"1.5.10"},"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/DSBCO_000242","checksum":"b0a388677719804332b67abc44a43494"}
{"_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":"2019-11-28T02:08:29.690112","version":"1.5.10"},"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/DSBCO_000243","checksum":"1406ee1296a7a83eaf2b35300e866c8c"}
{"_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":"2019-11-25T15:52:02.057464","version":"1.5.10"},"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/DSBCO_000244","checksum":"93526aba8a516690675a045ecf0c2f3a"}
{"_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":"2019-11-28T09:22:46.165689","version":"1.5.10"},"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/DSBCO_000245","checksum":"63fb87fbcac39e5098b12b78764957a2"}
{"_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":"1.5.10"},"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/DSBCO_000246","checksum":""}
{"_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":"2019-11-28T11:53:06.863079","version":"1.5.10"},"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/DSBCO_000247","checksum":"37fb6cf3103f9ffbf8418111e06f332e"}
{"_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":"2019-11-28T10:22:31.542730","version":"1.5.10"},"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/DSBCO_000248","checksum":"82f22d1fbe97e61864262c2c7c79a185"}
{"_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":"2019-11-27T15:33:18.957114","version":"1.5.10"},"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/DSBCO_000249","checksum":"2a859ddef9fa75182b0874e5e510e9a3"}
{"_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":"2019-11-28T10:25:47.854666","version":"1.5.10"},"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/DSBCO_000250","checksum":"ff69352eccf118ee21be80893dc31108"}
{"_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":"2019-11-27T15:49:57.814636","version":"1.5.10"},"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/DSBCO_000251","checksum":"679070f47ab4723d54dfa49caa0274d9"}
{"_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":"2019-11-27T16:01:07.933679","version":"1.5.10"},"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/DSBCO_000252","checksum":"55f434859914d8751c9ba84911fee7c9"}
{"_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":"2019-11-26T16:12:32.400522","version":"1.5.10"},"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/DSBCO_000253","checksum":"ba56d57c4b844e9b27bb45c43bca08bd"}
{"_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":"2019-12-01T15:05:12.220623","version":"1.5.10"},"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/DSBCO_000254","checksum":"440f71110cf793484cf1cf28a586deec"}
{"_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":"2019-11-26T16:44:35.271453","version":"1.5.10"},"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/DSBCO_000255","checksum":"52deb5ca372d672fa824029347872238"}
{"_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":"2019-12-01T15:08:14.010693","version":"1.5.10"},"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/DSBCO_000256","checksum":"e3580a2ca08fcb863b9810c39e44be23"}
{"_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":"2019-11-28T10:28:03.381426","version":"1.5.10"},"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/DSBCO_000257","checksum":"929d0dacc86834d6c2902ec2dc298d36"}
{"_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"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Xavier Holmes","email":"xavierh@email.gwu.edu"}],"created":"2019-09-06T14:06:38.985197","modified":"2019-12-02T15:18:16.853702","version":"1.5.10"},"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/DSBCO_000258","checksum":"25b0732acd8ce31b0f28f5a641163fc9"}
{"_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":"2019-11-28T10:30:37.160827","version":"1.5.10"},"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/DSBCO_000259","checksum":"97c189f99d31c865c24a0f96ddefe27f"}
{"_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":"2019-11-28T10:34:59.042180","version":"1.5.10"},"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/DSBCO_000260","checksum":"aefa2dc5366f411cd891a6b2ec792b23"}
{"_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":"2019-11-28T10:37:09.026509","version":"1.5.10"},"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/DSBCO_000261","checksum":"1e16fc725547f5c6d64a359b69712ff6"}
{"_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":"2019-11-28T10:39:43.732739","version":"1.5.10"},"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/DSBCO_000262","checksum":"7fb2b844078583419afdcf29995aa9ff"}
{"_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":"2019-11-28T10:41:55.393127","version":"1.5.10"},"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/DSBCO_000263","checksum":"bb4fbe7a10b72b08c475322fc53056bc"}
{"_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":"2019-12-01T15:07:50.725476","version":"1.5.10"},"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/DSBCO_000264","checksum":"ded17e63a34c5f4ecc330c1ee62f01e6"}
{"_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":"2019-11-25T17:34:09.128864","version":"1.5.10"},"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/DSBCO_000265","checksum":"b6b330ae90d9b765523e875db616ba4f"}
{"_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":"2019-11-28T10:42:51.611094","version":"1.5.10"},"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/DSBCO_000266","checksum":"cd61ccc34ba7930e276b98af16e8b596"}
{"_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":"2019-11-27T11:35:17.779249","version":"1.5.10"},"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/DSBCO_000267","checksum":"1a7dcd936ea4850f13eae8cbbe3622f6"}
{"_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"},{"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":"2019-09-06T14:06:38.994596","modified":"2019-12-02T15:21:06.433983","version":"1.5.10"},"description_domain":{"keywords":["tyrosine","o-linked glycosylation","glycosylation sites"],"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":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_phosphorylation_sites_uniprotkb.csv","filename":"human_proteoform_phosphorylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"The script 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/DSBCO_000268","checksum":"9cfb7c4f61438dbaf343103b6d72344e"}
{"_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":"2019-12-01T15:11:21.774987","version":"1.5.10"},"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/DSBCO_000269","checksum":"eeb1937331a64b08090061dcfe0feea3"}
{"_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":"2019-11-28T10:44:51.631234","version":"1.5.10"},"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/DSBCO_000270","checksum":"dab99af0d943b5d363c366ce800060e5"}
{"_id":{"$oid":"5d72a02ef5c47b0f43423380"},"error_domain":{"empirical_error":{},"algorithmic_error":{}},"extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""},"dataset_categories":[{"category_value":"Retired","category_name":"status"}]},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Retired","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-09-06T14:06:38.997376","modified":"2019-09-12T17:07:16.377677","version":"1.5.10"},"description_domain":{"keywords":[],"pipeline_steps":[]},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-07-26T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2019-05.nt","filename":"uniprot-proteome-10090-mus-musculus-2019-05.nt"}}],"output_subdomain":[]},"bco_spec_version":"1.3.0","execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[]},"parametric_domain":[],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000271","checksum":""}
{"_id":{"$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":"2019-12-01T15:12:13.008977","version":"1.5.10"},"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/DSBCO_000272","checksum":"209a3f244ccedd986a7e7f7ce024aebf"}
{"_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":"2019-11-28T10:48:54.833440","version":"1.5.10"},"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/DSBCO_000273","checksum":"baa9c5646cd4ebd67eaf4c89840b5588"}
{"_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":"2019-12-01T15:05:34.350651","version":"1.5.10"},"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/DSBCO_000274","checksum":"02181c1243e588e49d81364b57ec5987"}
{"_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":"2019-11-28T11:47:38.577404","version":"1.5.10"},"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/DSBCO_000275","checksum":"5683a32fca18f0e5c49603e8c2c7d8f1"}
{"_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":"2019-11-28T11:50:44.817717","version":"1.5.10"},"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/DSBCO_000276","checksum":"79ed634c51da325de599e403dec58b6d"}
{"_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":"http://data.glygen.org/ln2wwwdata/reviewed/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}},{"mediatype":"csv","uri":{"access_time":"","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","checksum":"5cf2e5760cbcc4c5c8d570bd41bb660b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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 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 \u0026 Science University","contribution":["authoredBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"}],"created":"2019-09-06T16:21:59.896067","modified":"2019-11-27T16:25:12.433939","version":"1.5.10"},"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":"2019-07-26T17:45:17-0500","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glyco_disease.csv","filename":"human_protein_glyco_disease.csv"}],"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/DSBCO_000277"}
{"_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":"af952a43117074bd86bcc60853d6d18c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T16:11:11.786326","version":"1.5.10"},"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/DSBCO_000278"}
{"_id":{"$oid":"5d78134925f6e85f83ba0d10"},"bco_id":"http://data.glygen.org/bco_id","extension_domain":{"dataset_categories":[{"category_value":"internal","category_name":"scope"}],"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"}},"bco_spec_version":"1.3.0","checksum":"","execution_domain":{"software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script_driver":"manual"},"provenance_domain":{"version":"1.5.10","license":"https://creativecommons.org/licenses/by/4.0/"}}
{"_id":{"$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":"bffe548a0fe0846cb59f408f30574ade","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:16:15.322389","version":"1.5.10"},"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/DSBCO_000279"}
{"_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":"c0bbd5a66550254195fd979bf53e2693","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-25T17:24:16.976029","version":"1.5.10"},"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/DSBCO_000280"}
{"_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":"94082d9397d774af05610a04129b0af3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T12:43:51.676216","modified":"2019-11-14T16:25:23.636320","version":"1.5.10"},"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/DSBCO_000281"}
{"_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":"2525f15d81e39be44963f38207e75efd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T12:59:46.920689","modified":"2019-11-14T16:26:42.010161","version":"1.5.10"},"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/DSBCO_000282"}
{"_id":{"$oid":"5dcc45f1f5c47b1f6cac300f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","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/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":"e91bcbbb796ae1e5131f96233b273a30","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:05:37.256972","modified":"2019-11-13T13:17:54.733495","version":"1.5.10"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Motif"],"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/allmotif.tsv","filename":"allmotif.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","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."}]},"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":{},"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/DSBCO_000283"}
{"_id":{"$oid":"5dcc491cf5c47b20a5acac95"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}},{"uri":{"access_time":"2019-11-12T15:00:18-0500","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":"2019-11-12T15:04:18-0500","sha1_chksum":"","uri":"http://data.glygen.org/ln2wwwdata/reviewed/glycan_enzyme.csv","filename":"glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","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":"efa52d8d038b4becd3239706164d757e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["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":"2019-11-13T13:19:08.883378","modified":"2019-11-14T16:27:18.709811","version":"1.5.10"},"description_domain":{"keywords":["Glycan","GlyTouCan Accession","Enzyme"],"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/mapped_n_glycans.csv","filename":"mapped_n_glycans.csv"},{"access_time":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/enz.tsv","filename":"enz.tsv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_enzyme.csv","filename":"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 or Taxid=10090"}]},"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 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/DSBCO_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":"106530266891fd3ade3c6bdbab802754","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:26:29.074237","modified":"2019-11-14T16:28:39.088269","version":"1.5.10"},"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/DSBCO_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":"15fe5a49c2fb8986ec6cb7995b7c7735","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T13:36:02.199874","modified":"2019-11-14T16:29:32.270682","version":"1.5.10"},"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/DSBCO_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":"433c2e1174b3290e08ec6c8feeb20b55","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:15:24.688189","modified":"2019-11-14T16:30:00.057399","version":"1.5.10"},"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/DSBCO_000287"}
{"_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":"b92c7e087aabf90f716a6e7fe108c84d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:21:17.865259","modified":"2019-11-14T16:30:45.401957","version":"1.5.10"},"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/DSBCO_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":"8c1fbabd2c5d5427f5570f30d5ba2650","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-14T16:31:46.105652","version":"1.5.10"},"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-\u003cPUBCHEM_COMPOUND_CID\u003e , \u003cPUBCHEM_IUPAC_INCHI\u003e, \u003cPUBCHEM_IUPAC_INCHIKEY\u003e  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/DSBCO_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":"a2a0210a0ae8b8bf41e177d223fcb27b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:31:31.525156","modified":"2019-11-14T16:32:17.794922","version":"1.5.10"},"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/DSBCO_000290"}
{"_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_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}}],"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":"87acdcb7c18fba1bbdac8b4fe7a32636","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-13T16:42:27.365235","version":"1.5.10"},"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_2019_05_06_10_23_08","filename":"CID-SMILES_2019_05_06_10_23_08"}],"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/DSBCO_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":"42c7dba4eb13bb6dbb89b703f716b186","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:43:04.029210","modified":"2019-11-13T16:47:00.343573","version":"1.5.10"},"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/DSBCO_000292"}
{"_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":"f0812e46105c53bfcda15744ab97f1bb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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 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":"2019-11-13T16:50:50.658337","version":"1.5.10"},"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/DSBCO_000293"}
{"_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":"c51e9ac58d86c55960457185ab992402","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:51:37.145018","modified":"2019-11-13T16:54:31.373967","version":"1.5.10"},"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/DSBCO_000294"}
{"_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":"5764e6dac9d4c8985de7f8d1e17eaade","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T16:55:11.149043","modified":"2019-11-13T16:58:13.769066","version":"1.5.10"},"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/DSBCO_000295"}
{"_id":{"$oid":"5dcc7c9cf5c47b2ed3a146f5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-11-12T15:00:18-0500","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":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/chebiId_inchi.tsv","filename":"chebiId_inchi.tsv"}},{"uri":{"access_time":"2019-11-12T15:00:18-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.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.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":"84fea0f04258fac895f8bdb22309a37c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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"}],"created":"2019-11-13T16:58:52.830892","modified":"2019-11-13T17:03:07.036800","version":"1.5.10"},"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":"2019-11-12T15:00:18-0500","uri":"https://data.glygen.org/ln2wwwdata/source/cid2inchi.csv","filename":"cid2inchi.csv"}],"output_list":[{"access_time":"2019-11-12T15:04:18-0500","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."}]},"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 PubChem CID mapping .  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/DSBCO_000296"}
{"_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_2019_02_07_03_58_16.tsv","filename":"database_accession_2019_02_07_03_58_16.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":"de7136255738a49d246765e1c27afed0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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":"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":"2019-11-13T17:21:46.590334","version":"1.5.10"},"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"}],"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/DSBCO_000297"}
{"_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":"40ce0f2f66634c4e4701afef1eccd1a5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-13T17:22:49.976947","modified":"2019-11-13T17:29:31.991036","version":"1.5.10"},"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/DSBCO_000298"}
{"_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":"c2071d61487e4a3887eb7b850fc92e0f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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 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":"2019-11-13T17:36:45.010458","version":"1.5.10"},"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/DSBCO_000299"}
{"_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":"4285a745edef3cc486440c97bef9c41c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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 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":"2019-11-14T16:32:53.190767","version":"1.5.10"},"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/DSBCO_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":"d6642fbd8db21c768e40eafeb77faff2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:18:37.879581","modified":"2019-11-14T16:33:17.092031","version":"1.5.10"},"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/DSBCO_000301"}
{"_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":"abbf71966ae99a8d778d63edc2d8a277","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:26:24.134158","modified":"2019-11-14T16:34:11.133653","version":"1.5.10"},"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/DSBCO_000302"}
{"_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":"a74dc920f4858751d6a8193230c318a6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:31:22.083466","modified":"2019-11-14T16:34:38.706190","version":"1.5.10"},"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/DSBCO_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":"946900c483018261e6f2d543b4134b08","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:38:02.465398","modified":"2019-11-14T16:35:14.516984","version":"1.5.10"},"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/DSBCO_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":"8f888fc58128c42f6f47db3a740387f2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T11:47:20.058924","modified":"2019-11-14T11:57:03.668947","version":"1.5.10"},"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/DSBCO_000305"}
{"_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"}}]},"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":"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 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":"1.5.10"},"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/DSBCO_000306"}
{"_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":"b41615b7371ac360abcd015b7d745552","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-11-14T12:09:00.597068","modified":"2019-11-14T12:13:12.958288","version":"1.5.10"},"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/DSBCO_000307"}
{"_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":"1.5.10"},"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 \u0026 Ellen M. McDonagh. Nat Genet (2019) doi:10.1038/s41588-019-0528-2)"],"bco_id":"http://data.glygen.org/DSBCO_000308"}
{"_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":"1.5.10"},"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/DSBCO_000309"}
{"_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":"93091315b4fd8d37635ae2ac87d83fbe","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-01T14:59:29.623448","version":"1.5.10"},"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/DSBCO_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":"797ff64fcd57b63cf1a4898c6dd1cce2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-02T18:07:55.159596","version":"1.5.10"},"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/DSBCO_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":"c615bdfc3a836ad58c4e9c55b8b2a055","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-01T14:59:55.478759","version":"1.5.10"},"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/DSBCO_000312"}
{"_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":"7e742af00d9ef980873a106e392d3aae","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:51:08.048169","version":"1.5.10"},"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/DSBCO_000313"}
{"_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":"4649235c3891411c48121f64f569c118","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:51:37.859766","version":"1.5.10"},"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/DSBCO_000314"}
{"_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":"d360a43c8446cded2ef65fd05e35dec8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:51:56.060675","version":"1.5.10"},"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/DSBCO_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":"b10f8c81b82712fe43a95ba92678858b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:52:54.884993","version":"1.5.10"},"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/DSBCO_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":"ab9ac8322a5d122a2d92e9af1286f61c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:53:22.333515","version":"1.5.10"},"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/DSBCO_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":"7c1872d6f3331393444a2d0eeddf15e8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-11-30T14:54:32.664727","version":"1.5.10"},"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/DSBCO_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":"7199557d539a63af8dbf2dd2343e1bc1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T12:04:31.501854","version":"1.5.10"},"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/DSBCO_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":"eb460e173092f2b9779ad41604cdf2c2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T12:05:50.017041","version":"1.5.10"},"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/DSBCO_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":"ebe33c4e2bb80ed0c1820acd883731cd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T12:07:27.977684","version":"1.5.10"},"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/DSBCO_000321"}
{"_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":"eb3f13828f236f761fee340030990659","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-01T15:49:31.921346","version":"1.5.10"},"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/DSBCO_000322"}
{"_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":"74a4ff077b1298dd806d58c7c72352a7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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":"2019-12-01T15:54:04.720467","modified":"2019-12-01T15:57:23.449190","version":"1.5.10"},"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 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/DSBCO_000323"}
{"_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":"c2cf7fab06dce5573be53976a9f64f11","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T12:08:55.447878","version":"1.5.10"},"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 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/DSBCO_000324"}
{"_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":"1a27d9e2e750c74c603dfba359297481","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T12:08:16.427724","version":"1.5.10"},"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 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/DSBCO_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":"6e18cf09a54c218458b7495c8a25b53f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"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":["authoredBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-12-02T15:34:41.971945","modified":"2019-12-02T15:38:46.393951","version":"1.5.10"},"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/DSBCO_000326"}
{"_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":"0f9a4fce12ef1dea02454aeee1a60724","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"","contribution":["createdBy"],"name":"","email":"jeetvora@gwu.edu"}],"created":"2019-12-04T12:16:57.929402","modified":"2019-12-04T15:29:41.705953","version":"1.5.10"},"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/DSBCO_000327"}
{"_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":"b04f37495cc0af479f8de5ded37c650c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","script_license":"https://www.gnu.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":"2019-12-04T15:29:29.874520","version":"1.5.10"},"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/DSBCO_000328"}