{"_id":{"$oid":"5c48e7f8f5c47b65811b022d"},"provenance_domain":{"version":"1.0.5"}}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cec"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.stat.csv","filename":"human_protein_idmapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"905176c5d411d5198d847cd7e4e1a871","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Proteome Accessions","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:00:09.742420","version":"1.0.13"},"description_domain":{"keywords":["canonical accessions","gene name","isoforms","complete proteome"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.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":"2019-01-07T17:43:17-0500","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 Proteome 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000001","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-25T16:54:06.944837","name":"Human Proteome Accessions","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5ced"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.fasta","filename":"human_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_canonicalsequences.stat.csv","filename":"human_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"64c89c6d5ac2a8442c084d0856f51dcb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Canonical sequences","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:04:37.625777","version":"1.0.13"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","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":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","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 UniProtKB Canonical sequences dataset contains human [taxid:9606] protein fasta sequences sequences for the human canonical sequences from UniProtKB database.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000002","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:37:39.149749","name":"Human UniProtKB Canonical sequences","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cee"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-01-07T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ntdata.stat.csv","filename":"human_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8f0cdf3679399f3f09c66409e5adfe7d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:04:03.686847","version":"1.0.13"},"description_domain":{"keywords":["NT","proteome"],"pipeline_steps":[{"name":"","step_number":0,"version":"1","input_list":[{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_ntdata.nt","filename":"human_protein_ntdata.nt"}],"prerequisite":[],"description":"The NT file requires no processing after it is recieved from EMBL-EBI-UniProt"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000003","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:17:25.570824","name":"Human EBI-UniProtKB NT file","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cef"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_glycosyltransferase_2018_11.csv","filename":"human_protein_glycosyltransferase_2018_11.csv"}},{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","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":"628f14d3529b50c7d47d3006a6b6bee2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosyltransferases","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["authoredBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.870634","modified":"2019-04-23T13:23:32.976952","version":"1.0.13"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","GO"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_glycosyltransferase_2018_11.csv","filename":"human_protein_glycosyltransferase_2018_11.csv"},{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosyltransferase.csv","filename":"human_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the columns from source file that contains the list of GTs and maps the UniProtKB accessions to current UniprotKB canonical accessions. Creating the source file - All reviewed human proteins with UniProt keyword [KW] “Glycosyltransferase” [KW-0328] were retrieved from UniProtKB/Swiss-Prot using the following query: “keyword:\"Glycosyltransferase [KW-0328]\" keyword:\"Complete proteome [KW-0181]\" AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\"” (UniProtKB/Swiss-Prot 2018_02, accessed 3/21/18).  For each entry, the UniProtKB Accession (AC), recommended protein name, and recommended gene name were retrieved. Human proteins with Gene Ontology (GO) annotations for molecular function term “transferase activity, transferring glycosyl groups” [GO:0016757] and descendants with relationship “enables” were exported using QuickGO GO annotations service (accessed 3/21/18). Proteins with GO annotations were limited to those 20,303 accessions belonging to the complete reference proteome in UniProtKB/Swiss-Prot (UniProtKB/Swiss-Prot 2018_02, accessed 3/21/18). CAZY GT families were retrieved by first searching the database for families in human by entering “9606” into the search bar corresponding to “Tax_id.” For each family with human enzymes, the list of UniProt accessions was retrieved from CAZY and filtered for accessions associated with the complete human reference proteome. InterPro annotations were retrieved through UniProt for currently existing proteins in the list, then cross-referenced directly in InterPro to retrieve all protein accessions with any of the relevant terms. Terms were curated for inclusion, and filtered for those proteins with reviewed accessions. Terms were then mapped to accessions already in the GT list, and accessions not yet in the GT list were added."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T16:40:17-0500","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 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 GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000004","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.870634","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:39:49.590409","name":"Human Glycosyltransferases","version":"1.0.5"}
{"_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":"80cacb864719dbb5cd94c9a498d8a977","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000005","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:44:27.899703","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"62fcd0c1eb978cd9d283f2ba38ea5bb2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.872734","modified":"2019-02-19T14:44:52.840281","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000006","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.872734","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:44:52.840281","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf2"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-17T11:11:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-17T11:14:27-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-17T11:14:27-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.stat.csv","filename":"mouse_protein_idmapping.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a4823d5c4f327367ccf8f3e119ea88e0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Proteome Accessions","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T13:25:39.468404","version":"1.0.13"},"description_domain":{"keywords":["canonical accessions","gene name","isoforms","complete proteome"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-17T11:11:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-01-17T11:14:27-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.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":"2019-01-07T17:43:17-0500","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 Proteome Accessions 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 2018-11 UniProt release. The dataset is contributed by EMBL-EBI-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000007","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-25T16:53:17.012941","name":"Mouse Proteome Accessions","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf3"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"d2e95f1c8287c5578c7af69988f8516b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.874820","modified":"2019-02-19T14:45:28.514598","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000008","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.874820","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:45:28.514598","name":"","version":"1.0.5"}
{"_id":{"$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":"33dc1737b5dc08b52bd386cdc5f6c460","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000009","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:46:01.499854","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"edf03af5d5ab5be271c9a6c21aa2eb91","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.876875","modified":"2019-02-19T14:46:18.887967","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000010","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.876875","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:46:18.887967","name":"","version":"1.0.5"}
{"_id":{"$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":"5790e4850662691908621b4b3968f36d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000011","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:46:36.830310","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf7"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"fasta","uri":{"access_time":"2019-02-08T13:19:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.fasta","filename":"mouse_protein_canonicalsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:19:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_canonicalsequences.stat.csv","filename":"mouse_protein_canonicalsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a90e3de369a25a55d95577bb02351a9a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Canonical sequences","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:05:19.668303","version":"1.0.13"},"description_domain":{"keywords":["protein sequence","fasta","canonical accessions"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-02-08T13:19:15-0500","sha1_chksum":"","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":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:17:15-0500","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 UniProtKB Canonical sequences dataset contains mouse [taxid:10090] protein fasta sequences sequences for the mouse canonical sequences from UniProtKB database","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000012","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:42:30.117462","name":"Mouse UniProtKB canonical sequences","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf8"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"nt","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_ntdata.nt","filename":"mouse_protein_ntdata.nt"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_ntdata.stat.csv","filename":"mouse_protein_ntdata.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e67b37c08f0112d2284eb8951073e49e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:04:20.145906","version":"1.0.13"},"description_domain":{"keywords":["NT","proteome"],"pipeline_steps":[{"name":"","step_number":0,"version":"1","input_list":[{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","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":[],"script":[]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse EBI-UniProtKB NT file contains protein data for mouse [taxid:10090] as per the GlyGen specifications.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000013","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:21:57.636067","name":"Mouse EBI-UniProtKB NT file","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cf9"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"7399252e1c607e91adf943edf7edd07a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.880988","modified":"2019-02-19T14:47:39.354378","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000014","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.880988","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:47:39.354378","name":"","version":"1.0.5"}
{"_id":{"$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":"4850b76fd3eb089d59df3a97dd3ba24b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000017","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:48:14.596827","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cfe"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"1a69c7bbbd5725d0a38b27b2dc95958a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.886120","modified":"2019-02-19T14:48:24.630823","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000019","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.886120","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:48:24.630823","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5cff"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"0fb2086efaa0e111364217b80696f228","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000020","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:25:17.851719","name":"Human RefSeq Mapping","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d00"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.csv","filename":"human_protein_refseq_protein_info.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.stat.csv","filename":"human_protein_refseq_protein_info.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d562fc28279074c14b3a3438fcf0f001","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human RefSeq Protein Information","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","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":"2019-01-23T17:21:05.888176","modified":"2019-04-23T13:57:53.499636","version":"1.0.13"},"description_domain":{"keywords":["protein information","protein length"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"},{"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"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_refseq_protein_info.csv","filename":"human_protein_refseq_protein_info.csv"}],"prerequisite":[],"description":"This 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":"2019-03-05T14:40:17-0500","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-gp.py","filename":"extract-from-gp.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human RefSeq Protein Information dataset contains human [taxid:9606] protein information such as protein accession, name, length and protein function summmary 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_000021","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.888176","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:43:16.094584","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d01"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpffhttps://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-gp.py","filename":"refseq_protein_all_10090.gpff"}},{"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":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed//mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8b918a8c9389df4a9e9f0826cdd68dc6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse RefSeq Protein Information","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","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":"2019-01-23T17:21:05.888176","modified":"2019-04-23T14:00:59.185361","version":"1.0.13"},"description_domain":{"keywords":["protein information","protein length"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_refseq_protein_info.csv","filename":"mouse_protein_refseq_protein_info.csv"}],"prerequisite":[],"description":"This 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":"2019-03-05T14:40:17-0500","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-gp.py","filename":"extract-from-gp.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Mouse RefSeq Protein Information dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summmary 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","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.889242","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:43:43.010516","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"6a70126c4e4f96d61d2ed5ee92bb884d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.890267","modified":"2019-02-19T13:44:51.567646","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000023","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.890267","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:44:51.567646","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d03"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/biomuta-4.0-oct-25-2018-master.csv","filename":"biomuta-4.0-oct-25-2018-master.csv"}},{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.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":"0e80a4894209477b69ccb9eee94e35d4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Cancer Mutation","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"BioMuta - The George Washington University","contribution":["importedFrom"],"name":"BioMuta (Robel Kahsay) [https://hive.biochemistry.gwu.edu/biomuta]","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.891293","modified":"2019-04-23T14:17:07.198030","version":"1.0.13"},"description_domain":{"keywords":["single-nucleotide variations (nsSNVs) ","cancer mutations","BioMuta"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/biomuta-4.0-oct-25-2018-master.csv","filename":"biomuta-4.0-oct-25-2018-master.csv"},{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"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"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the mutations with frequency \u003c10 and maps 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":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","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 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 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 imported and contributed by BioMuta and processed by GlyGen. If you use this dataset please provide proper attribution to BioMuta and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000024","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.891293","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:44:42.943242","name":"Mutation ","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d04"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}},{"mediatype":"csv","uri":{"access_time":"","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":"7dc8563a2f9ed69311a5417700519cbc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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"}],"created":"2019-01-23T17:21:05.892318","modified":"2019-04-24T12:29:07.770672","version":"1.0.13"},"description_domain":{"keywords":["glycohydrolase","glycosidase","CAZy"],"pipeline_steps":[{"name":"-","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-08T17:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycohydrolase.csv","filename":"human_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"Using UniProt advanced search infrastructure three searches were performed UniProtKB/Swiss-Prot (accessed 07/15/2018) using the query “keyword:Glycosidase [KW-0326]” AND reviewed:yes AND organism: “Homo sapiens (Human) [9606]”, “glycosyl hydrolase” AND reviewed:yes AND organism: “Homo sapiens (Human) [9606]” and “glycoside hydrolase” AND reviewed:yes AND organism: “Homo sapiens (Human) [9606]”, to obtain the list of all reviewed human glycosidase enzymes. For each entry, the UniProtKB Accession, protein name, and gene name (primary) and e.c number were retrieved. The protein entries retrieved from these three queries were reviewed in CAZy, Pfam, InterPro and Brenda. Entries that did not have any association to be glycohydrolase were filtered out. Subunits or inactive proteins were filtered out. The entries from the three lists were merged to get a comprehensive list of glycohydrolases. The UniProtKB accessions were finally mapped to UniProtKB canonicals"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"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 EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000025","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.892318","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:46:03.541450","name":"Human Glycohydrolases","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d05"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-08T17:40:17-0500","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":"2019-01-08T17:45:17-0500","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":"6f2adf50f7ed2ad27b95bf202d0ffe18","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.893381","modified":"2019-04-24T12:03:54.193860","version":"1.0.13"},"description_domain":{"keywords":["glycohydrolase","glycosidase","CAZy"],"pipeline_steps":[{"name":"-","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-08T17:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-08T17:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycohydrolase.csv","filename":"mouse_protein_glycohydrolase.csv"}],"prerequisite":[],"description":"  \"description\": \"Using UniProt advanced search infrastructure three searches were performed UniProtKB/Swiss-Prot (accessed 07/15/2018) using the query “keyword:Glycosidase [KW-0326]” AND reviewed:yes AND organism: “Mus musculus (Mouse) [10090]”, “glycosyl hydrolase” AND reviewed:yes AND organism: “Mus musculus (Mouse) [10090]” and “glycoside hydrolase” AND reviewed:yes AND organism: “Mus musculus (Mouse) [10090]”, to obtain the list of all reviewed human glycosidase enzymes. For each entry, the UniProtKB Accession, protein name, and gene name (primary) and e.c number were retrieved. The protein entries retrieved from these three queries were reviewed in CAZy, Pfam, InterPro and Brenda. Entries that did not have any association to be glycohydrolase were filtered out. Subunits or inactive proteins were filtered out. The entries from the three lists were merged to get a comprehensive list of glycohydrolases. The UniProtKB accessions were finally mapped to UniProtKB canonicals\","}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"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 EMBL-EBI_UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000026","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.893381","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:47:04.771631","name":"Mouse Glycohydrolases","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d06"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"bbfd0679f6491a57a4d5ac454c8d70a6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.894406","modified":"2019-02-19T13:47:11.999143","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000027","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.894406","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:47:11.999143","name":"","version":"1.0.5"}
{"_id":{"$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_idmapping.csv","filename":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.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":"4c9cd5003fdf8bab3c0041e9830beb29","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"BioXpress - The George Washington University","contribution":["contributedBy"],"name":"BioXpress - Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.895453","modified":"2019-04-23T14:29:35.985132","version":"1.0.13"},"description_domain":{"keywords":["normal gene expression","BioXpress","UBERON"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"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"},{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"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"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the expression information and maps the UniProtKB accession/ gene name 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":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-csv.py","filename":"extractor/extract-from-csv.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","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.895453","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:48:47.500173","name":"Gene Expression (Normal)","version":"1.0.5"}
{"_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/bioxpress-3.0-oct-25-2018-master-with-sampleid.csv","filename":"bioxpress-3.0-oct-25-2018-master-with-sampleid.csv"}},{"uri":{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.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":"a51fc88ed36d2ffba6cf8fffd7c7c802","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"BioXpress - The George Washington University","contribution":["importedFrom"],"name":"BioXpress - Hayley Dingerdissen","email":"hmhamilt@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.896478","modified":"2019-04-23T14:30:05.533559","version":"1.0.13"},"description_domain":{"keywords":["gene expression (cancer)","Disease Ontology"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/bioxpress-3.0-oct-25-2018-master-with-sampleid.csv","filename":"bioxpress-3.0-oct-25-2018-master-with-sampleid.csv"},{"access_time":"2019-01-07T17:43:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"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"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the expression information and maps the UniProtKB accession/ gene name 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":"2019-01-07T17:43:17-0500","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":["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","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.896478","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:49:53.228099","name":"Gene Expression (Cancer)","version":"1.0.5"}
{"_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":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"}},{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","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":"8072d59338ac9c2e3466aad22df0d2c0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosyltransferase","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","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":"2019-01-23T17:21:05.897519","modified":"2019-04-23T14:40:45.888291","version":"1.0.13"},"description_domain":{"keywords":["GT","glycosyltransferase","CAZy","CFG","GO"],"pipeline_steps":[{"name":"extract-from-csv.py","step_number":1,"version":"1.0","input_list":[{"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"},{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"},{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_glycosyltransferase.csv","filename":"mouse_protein_glycosyltransferase.csv"}],"prerequisite":[],"description":"The script extract-from-csv.py extracts the columns from source file that contains the list of GTs and maps the UniProtKB accessions to current UniprotKB canonical accessions. Creating the source file - The mouse orthologs for human glycosyltransferases were retrieved from protein_ortholog.csv https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv using the vlookup function in the Excel spreadsheet.  The retrieved mouse UniProtKB accessions were searched in Quick GO, CAZY database, Brenda for evidence of glycosyltransferase activity. The accessions that did not have requisite evidence were filtered out. The UniProt accessions for keyword glycosyltransferase[UniProt KW-0328] were searched in UniProt but that resulted in fewer accessions than above step."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T16:42:17-0500","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 Mouse Glycosyltransferase dataset contains list of mouse [taxid:10090] glycosyltransferases enzymes","If you use this dataset please provide proper attribution to GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000030","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.897519","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:52:15.668750","name":"Mouse Glycosyltransferase","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_altnames.csv","filename":"human_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_altnames.stat.csv","filename":"human_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"e64709066df4b237baa2f11c47bc982b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:01:10.318494","version":"1.0.13"},"description_domain":{"keywords":["protein alternative name"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-03-05T14:42:17-0500","sha1_chksum":"","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":"2019-03-05T14:40:17-0500","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 Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for human [taxid:9606] proteins","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000031","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:56:43.378298","name":"Human Protein Alternative Name (UniProtKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-03-05T14:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_altnames.csv","filename":"mouse_protein_altnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:44:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_altnames.stat.csv","filename":"mouse_protein_altnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f84b5f9dcc91284b6bbc9e3c66a46de9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:01:29.750545","version":"1.0.13"},"description_domain":{"keywords":["protein alternative name"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-03-05T14:41:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"access_time":"2019-03-05T14:41:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-03-05T14:44:17-0500","sha1_chksum":"","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":"2019-03-05T14:41:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-03-05T14:41:17-0500","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 Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for mouse [taxid:10090] proteins.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000032","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.899575","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:54:59.896055","name":"Mouse Protein Alternative Name (UniProtKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:13:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_information.csv","filename":"human_protein_information.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/human_protein_information.stat.csv","filename":"human_protein_information.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"d0fefdc2dd4c575e256f7af865f06b28","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:06:06.720868","version":"1.0.13"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-02-08T13:13:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_information.csv","filename":"human_protein_information.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":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000033","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:01:27.131457","name":"Human Protein Information","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"uri":{"access_time":"2019-02-08T13:11:15-0500","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":"2019-02-08T13:15:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_information.csv","filename":"mouse_protein_information.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_information.stat.csv","filename":"mouse_protein_information.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"15e16f599df9148baca1cd3ee1c7e3ef","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:11:28.135010","version":"1.0.13"},"description_domain":{"keywords":["UniProtKB entry id","UniProtKB mnemonic name","protein length","protein mass"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-02-08T13:15:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_information.csv","filename":"mouse_protein_information.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:15:15-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000034","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:02:58.393366","name":"Mouse Protein Information (UniProtKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_blacklisted_pmids.csv","filename":"human_protein_blacklisted_pmids.csv"}},{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:02:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations.csv","filename":"human_protein_citations.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:02:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations.stat.csv","filename":"human_protein_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6050e29a09e9b669ec18385d5b994da9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:01:56.591862","version":"1.0.13"},"description_domain":{"keywords":["publications","PMID","journal","citations"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_blacklisted_pmids.csv","filename":"human_protein_blacklisted_pmids.csv"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:02:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations.csv","filename":"human_protein_citations.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 filter out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","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 Citations dataset contains publication information for human [taxid:9606] UniProtKB accessions that includes PMID, journal name 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/reviewed/human_protein_blacklisted_pmids.csv","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000035","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-25T16:52:04.119358","name":"Human Protein Citations","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d0f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_blacklisted_pmids.csv","filename":"mouse_protein_blacklisted_pmids.csv"}},{"uri":{"access_time":"2019-01-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations.csv","filename":"human_protein_citations.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_citations.stat.csv","filename":"mouse_protein_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"b0ffe50a450c3acf92330d314e229445","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-25T19:02:35.243588","version":"1.0.13"},"description_domain":{"keywords":["publications","PMID","journal","citations"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1","input_list":[{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_blacklisted_pmids.csv","filename":"mouse_protein_blacklisted_pmids.csv"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_citations.csv","filename":"human_protein_citations.csv"}],"prerequisite":[],"description":"The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","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 Citations dataset contains publication information for mouse [taxid:10090] UniProtKB accessions that includes PMID, journal name 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/reviewed/mouse_protein_blacklisted_pmids.csv","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000036","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T11:57:57.705723","name":"Mouse Protein Citations","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d10"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"ded09164e660ab0695f85c7296678d5c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.904697","modified":"2019-02-19T13:51:17.764255","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000037","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.904697","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:51:17.764255","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d11"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:00:17-0500","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":"","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":"2055371504c0222e9cf63f1b6f030b62","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (UniProtKB)","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":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Maria Martin ","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Leyla Garcia ","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Preethi Vasudev ","email":"preethi.vasudev@ebi.ac.uk"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.905721","modified":"2019-04-25T19:02:55.748795","version":"1.0.13"},"description_domain":{"keywords":["glycosylation","reported glycosylation ","predicted glycosylation"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv","filename":"human_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"This 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":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000038","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Maria Martin ","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Leyla Garcia ","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Preethi Vasudev ","email":"preethi.vasudev@ebi.ac.uk"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.905721","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-25T12:18:20.512211","name":"Human Glycosylation Sites (UniProtKB)","version":"1.0.5"}
{"_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-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:00:17-0500","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":"2019-01-07T16:03:17-0500","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":"2019-01-07T16:03:17-0500","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":"8c9035feed9ed933e20c4ebab4ac37d7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (UniProtKB)","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":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Maria Martin ","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Leyla Garcia ","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Preethi Vasudev ","email":"preethi.vasudev@ebi.ac.uk"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"}],"created":"2019-01-23T17:21:05.906744","modified":"2019-04-25T19:03:23.612214","version":"1.0.13"},"description_domain":{"keywords":["glycosylation","reported glycosylation","predicted glycosylation"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"access_time":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:03:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv","filename":"mouse_proteoform_glycosylation_sites_uniprotkb.csv"}],"prerequisite":[],"description":"This 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":"2019-01-07T16:00:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:00:17-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000039","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Maria Martin ","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Leyla Garcia ","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["authoredBy"],"name":"Preethi Vasudev ","email":"preethi.vasudev@ebi.ac.uk"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.906744","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-25T12:18:36.840676","name":"Mouse Glycosylation Sites (UniProtKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d13"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb_human_2018_10_31_02_22_23.clean.csv","filename":"unicarbkb_human_2018_10_31_02_22_23.clean.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glytoucan_140918_2018_10_31_02_17_32.txt","filename":"human_glytoucan_140918_2018_10_31_02_17_32.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_all.fasta","filename":"human_protein_all.fasta"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"f855ae287e93fee3ccb429ce2af9721f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (UniCarbKB)","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"}],"created":"2019-01-23T17:21:05.907769","modified":"2019-04-11T13:36:49.822332","version":"1.0.13"},"description_domain":{"keywords":["proteins","canonical","glycosylation","glycan"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb_human_2018_10_31_02_22_23.clean.csv","filename":"unicarbkb_human_2018_10_31_02_22_23.clean.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glytoucan_140918_2018_10_31_02_17_32.txt","filename":"human_glytoucan_140918_2018_10_31_02_17_32.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glycosylation_types.csv","filename":"human_glycosylation_types.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_glycosylation_types.log","filename":"human_glycosylation_types.log"}],"prerequisite":[],"description":"The input file was retrieved directly from source was \"cleaned\" for further processing and the glycosylation type (linkage type) was assigned using a python script [make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py] based on motif label provided by the author. "},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glytoucan_140918_2018_10_31_02_17_32.txt","filename":"human_glytoucan_140918_2018_10_31_02_17_32.txt"},{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/GLYDS00053","filename":"human_protein_all.fasta"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/GLYDS00040","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.log","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.log"}],"prerequisite":[],"description":"The UniProtKB protein accessions were mapped to canonical accessions and the final data was processed for quality check using a python script[make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.py] and the records which fall under one or more following criteria's were flagged and eliminated (eliminated records can be accessed using the log file through Output subdomain): a. If the protein accession is not included in UniProt protein list [UniProt Nov-2017 Release] b. If the amino acid position does not match to the amino acid on the associated position on fasta sequence [UniProt Nov-2017 Release] c. If the id (UnicarbKB structure id) is not present in input file. d. If the glycosylation type (linkage type) is not retrieved through step 2. e. If a serine or threonine is reported for an N-linked glycan structure.  f. If an asparagine is reported for an O-linked glycan structure. g. If the glycosylation type (linkage type) has both \"N-linked;O-linked\" assignment through step 2"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py, "}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":" make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.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 from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/DSBCO_000040","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"}],"created":"2019-01-23T17:21:05.907769","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-20T11:12:41.665051","name":"Human Glycosylation Sites (UniCarbKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d14"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb_mouse_2018_10_31_02_16_31.clean.csv","filename":"unicarbkb_mouse_2018_10_31_02_16_31.clean.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt","filename":"mouse_glytoucan_140918_2018_10_31_02_18_55.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_all.fasta","filename":"mouse_protein_all.fasta"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1996b783b78e53755a752b595e130df2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (UniCarbKB)","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"}],"created":"2019-01-23T17:21:05.908793","modified":"2019-04-11T13:45:56.393647","version":"1.0.13"},"description_domain":{"keywords":["proteins","canonical","glycosylation","glycan"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/unicarbkb_mouse_2018_10_31_02_16_31.clean.csv","filename":"unicarbkb_mouse_2018_10_31_02_16_31.clean.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt","filename":"mouse_glytoucan_140918_2018_10_31_02_18_55.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glycosylation_types.csv","filename":"mouse_glycosylation_types.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_glycosylation_types.log","filename":"mouse_glycosylation_types.log"}],"prerequisite":[],"description":"The input file was retrieved directly from source was \"cleaned\" for further processing and the glycosylation type (linkage type) was assigned using a python script [make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py] based on motif label provided by the author. "},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_glytoucan_140918_2018_10_31_02_18_55.txt","filename":"mouse_glytoucan_140918_2018_10_31_02_18_55.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_all.fasta","filename":"mouse_protein_all.fasta"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.log"}],"prerequisite":[],"description":"The UniProtKB protein accessions were mapped to canonical accessions and the final data was processed for quality check using a python script[make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.py] and the records which fall under one or more following criteria's were flagged and eliminated (eliminated records can be accessed using the log file through Output subdomain): a. If the protein accession is not included in UniProt protein list [UniProt Nov-2017 Release] b. If the amino acid position does not match to the amino acid on the associated position on fasta sequence [UniProt Nov-2017 Release] c. If the id (UnicarbKB structure id) is not present in input file. d. If the glycosylation type (linkage type) is not retrieved through step 2. e. If a serine or threonine is reported for an N-linked glycan structure.  f. If an asparagine is reported for an O-linked glycan structure. g. If the glycosylation type (linkage type) has both \"N-linked;O-linked\" assignment through step 2"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step2.py, "}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":" make-proteoform_glycosylation_sites_unicarbkb_glytoucan-csv-step3.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 from UniCarbKB database [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/DSBCO_000041","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"UniCarbKB","contribution":["authoredBy"],"name":"Matthew Campbell ","email":"m.campbell2@griffith.edu.au"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Robel Kahsay","email":"rykahsay@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"}],"created":"2019-01-23T17:21:05.908793","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-20T11:18:49.050326","name":"Mouse Glycosylation Sites (UniCarbKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d15"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN.txt","filename":"N-linked-ASN.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER.txt","filename":"O-linked-SER.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt","filename":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_all.fasta","filename":"human_protein_all.fasta"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://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":"0cddb1a458d9bd642805fd171559b7b3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycosylation Sites (RCSB PDB)","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":"RCSB PDB","contribution":["authoredBy"],"name":"Jasmine Young ","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Chenghua Shao ","email":"chenghua@rcsb.rutgers.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Nagarajan Pattabiraman","email":"pattabir@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.909814","modified":"2019-04-11T13:51:44.162252","version":"1.0.13"},"description_domain":{"keywords":["proteins","canonical","glycosylation"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN.txt","filename":"N-linked-ASN.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER.txt","filename":"O-linked-SER.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt","filename":"O-linked-THR.txt"}],"output_list":[],"prerequisite":[],"description":"The list of PDB Id's was retrieved from the source and their PDB header files were downloaded on september 27, 2018 and the header files were parsed to extract information on glycosylation positions for PDB Id's and UniProt accessions using headers 'DBREF', 'LINK' and 'MODRES' using a script [make-proteoform-glycosylation_sites_pdb_step1-csv.py]."},{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/proteoform_glycosylation_sites_pdb.log","filename":"proteoform_glycosylation_sites_pdb.log"}],"prerequisite":[],"description":"PDB Ids where information in the header files was either not available or was incorrect were eliminated. [The eliminated PDB Id's can be accessed through log file- proteoform_glycosylation_sites_pdb.log in output subdomain]."},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_all.fasta","filename":"human_protein_all.fasta"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/proteoform_glycosylation_sites_pdb.log","filename":"proteoform_glycosylation_sites_pdb.log"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_pdb.log","filename":"human_proteoform_glycosylation_sites_pdb.log"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_pdb.csv","filename":"human_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"Records which fall under one or more following conditions were flagged and eliminated. [The eliminated records can be accessed through log file- mouse_proteoform_glycosylation_sites_pdb.log in output subdomain]:  a. A mismatch between 'amino_acid_pdb' and 'amino_acid_uniprotkb' is observed. b. A mismatch between 'amino_acid_uniprotkb' and amino acid retrieved from fasta sequences (UniProtKB NOV-17 version) is observed. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform-glycosylation_sites_pdb_step1-csv.py"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"ac2canonical.py"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform-glycosylation_sites_pdb-csv.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 on sequences from UniProt accessions 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","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Jasmine Young ","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Chenghua Shao ","email":"chenghua@rcsb.rutgers.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Nagarajan Pattabiraman","email":"pattabir@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.909814","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-20T11:24:53.908111","name":"Human Glycosylation Sites (RCSB PDB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d16"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"source/N-linked-ASN.txt","filename":"N-linked-ASN.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER.txt","filename":"O-linked-SER.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt","filename":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_all.fasta","filename":"mouse_protein_all.fasta"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://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":"32901127e1c86c234aa3614085a2b38a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycosylation Sites (RCSB PDB)","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":"RCSB PDB","contribution":["authoredBy"],"name":"Jasmine Young ","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Chenghua Shao ","email":"chenghua@rcsb.rutgers.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Nagarajan Pattabiraman","email":"pattabir@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.910839","modified":"2019-04-11T13:56:50.790064","version":"1.0.13"},"description_domain":{"keywords":["proteins","canonical","glycosylation"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/N-linked-ASN.txt","filename":"N-linked-ASN.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-SER.txt","filename":"O-linked-SER.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/O-linked-THR.txt","filename":"O-linked-THR.txt"}],"output_list":[],"prerequisite":[],"description":"The list of PDB Id's was retrieved from the source and their PDB header files were downloaded on september 27, 2018 and the header files were parsed to extract information on glycosylation positions for PDB Id's and UniProt accessions using headers 'DBREF', 'LINK' and 'MODRES' using a script [make-proteoform-glycosylation_sites_pdb_step1-csv.py]."},{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/proteoform_glycosylation_sites_pdb.log","filename":"proteoform_glycosylation_sites_pdb.log"}],"prerequisite":[],"description":"PDB Ids where information in the header files was either not available or was incorrect were eliminated. [The eliminated PDB Id's can be accessed through log file- proteoform_glycosylation_sites_pdb.log in output subdomain]."},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_all.fasta","filename":"mouse_protein_all.fasta"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_pdb.log","filename":"mouse_proteoform_glycosylation_sites_pdb.log"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv","filename":"mouse_proteoform_glycosylation_sites_pdb.csv"}],"prerequisite":[],"description":"Records which fall under one or more following conditions were flagged and eliminated. [The eliminated records can be accessed through log file- mouse_proteoform_glycosylation_sites_pdb.log in output subdomain]:  a. A mismatch between 'amino_acid_pdb' and 'amino_acid_uniprotkb' is observed. b. A mismatch between 'amino_acid_uniprotkb' and amino acid retrieved from fasta sequences (UniProtKB NOV-17 version) is observed. "}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform-glycosylation_sites_pdb_step1-csv.py"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"ac2canonical.py"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/","filename":"make-proteoform-glycosylation_sites_pdb-csv.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 from UniCarbKB database. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]"],"bco_id":"http://data.glygen.org/DSBCO_000043","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Jasmine Young ","email":"jasmine@rcsb.rutgers.edu"},{"orcid":"","affiliation":"RCSB PDB","contribution":["authoredBy"],"name":"Chenghua Shao ","email":"chenghua@rcsb.rutgers.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Nagarajan Pattabiraman","email":"pattabir@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi ","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.910839","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-20T11:26:26.174289","name":"Mouse Glycosylation Sites (RCSB PDB)","version":"1.0.5"}
{"_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":"6e399906a74c46d8ecaffe0eb4ed020e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000044","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:51:50.903415","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d18"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"bf14b28513bc159d8409984fcc582a01","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.912928","modified":"2019-02-19T13:52:21.318112","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000045","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.912928","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:52:21.318112","name":"","version":"1.0.5"}
{"_id":{"$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":"5f3ab234377d3c06ada0ffd143e47937","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000046","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:52:44.339053","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"d36f03c3d182f21262f30ff66bb483fd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.914987","modified":"2019-02-19T13:53:09.793765","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000047","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.914987","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:53:09.793765","name":"","version":"1.0.5"}
{"_id":{"$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":"9e3cd4c1db58f89848b303a2dddfc54c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000048","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:53:31.852084","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"c3fddb3e27f779853ff274894e93692f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.917039","modified":"2019-02-19T13:53:59.703677","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000049","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.917039","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:53:59.703677","name":"","version":"1.0.5"}
{"_id":{"$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":"8adbee338cff6e0a0d58eb73356e7d4d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000050","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:54:27.678707","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d1e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"f84392d0348d198b9f7330c119d8265f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.919138","modified":"2019-02-19T13:55:00.615875","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000051","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.919138","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:55:00.615875","name":"","version":"1.0.5"}
{"_id":{"$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":"1d09010bc507c864d8770e4b21da965d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000052","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:55:53.482435","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d20"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.fasta","filename":"human_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_allsequences.stat.csv","filename":"human_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cdc5536f99d795a72433f8d74b2e6baa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Isoform sequences","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:30:43.900232","version":"1.0.13"},"description_domain":{"keywords":["isoform","fasta","protein sequences"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","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":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","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 UniProtKB Isofrom sequences dataset contains human [taxid:9606] protein fasta sequences for the human isoform accessions from the UniProtKB database,","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000053","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.921192","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T13:56:27.580757","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d21"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.fasta","filename":"mouse_protein_allsequences.fasta"}},{"mediatype":"csv","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_allsequences.stat.csv","filename":"mouse_protein_allsequences.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"198f581351e04fae2dc903359de10219","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Isoform sequences","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:32:28.218534","version":"1.0.13"},"description_domain":{"keywords":["isoform","fasta","protein sequences"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-02-08T13:11:15-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","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 as fasta format"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-02-08T13:17:15-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-02-08T13:11:15-0500","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 UniProtKB Isofrom sequences dataset contains mouse [taxid:10090] protein fasta sequences for the mouse isoform accessions from the UniProtKB database.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000054","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.922212","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:01:15.704821","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d22"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"ff16210ccfaf4a93cdba26dd3d876008","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.923235","modified":"2019-02-19T14:01:46.926371","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000055","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.923235","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:01:46.926371","name":"","version":"1.0.5"}
{"_id":{"$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":"5308eacb89d375e5ace129e5e3332ffa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000056","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:02:17.421800","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d24"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"2aaf74e1abfd6b8d45ebedfc2631f52d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.925284","modified":"2019-02-19T14:02:54.659774","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000057","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.925284","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:02:54.659774","name":"","version":"1.0.5"}
{"_id":{"$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":"5587c6d9f4680de719e0eda6dad33975","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000058","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:03:25.953144","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d26"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"df29156a3d8b50eafa58dbd108e19da5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.927329","modified":"2019-02-19T14:03:56.869077","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000059","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.927329","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:03:56.869077","name":"","version":"1.0.5"}
{"_id":{"$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":"a8f64f8e05264b7c714539848c215c23","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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_000060","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:37:48.755178","name":"Human Glycome Accessions","version":"1.0.5"}
{"_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":"e191e4a506536a8625e342626a16d339","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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 and their sequences in IUPAC, WURCS, GlycoCT format."],"bco_id":"http://data.glygen.org/DSBCO_000061","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:38:49.623122","name":"Human Glycan Sequences","version":"1.0.5"}
{"_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":"bde11dd895a6a424ec656f4ad79683aa","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse 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":"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":"2019-04-12T13:57:36.819312","version":"1.0.13"},"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":"","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","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:39:23.400652","name":"Mouse Glycome Accessions","version":"1.0.5"}
{"_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":"36caa548948ea750181218a57c59c893","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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 and their sequences in IUPAC, WURCS, GlycoCT format. "],"bco_id":"http://data.glygen.org/DSBCO_000063","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:40:06.340994","name":"Mouse Glycan Sequences","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gtc2enz.txt","filename":"gtc2enz.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_protein_ortholog.csv","filename":"mouse_protein_ortholog.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"Homo_sapiens.gene_info","filename":"https://data.glygen.org/ln2wwwdata/source/Homo_sapiens.gene_info.gz"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_enzyme.stat.csv","filename":"human_glycan_enzyme.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"bc662701ca84dc019caf0a21c8861ac3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Enzyme Mapping (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":"University of Georgia","contribution":["authoredBy"],"name":"William York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Alison V Nairn","email":"avnairn@ccrc.uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Rahul Sethi","email":"rahulsethi80@gwu.edu"}],"created":"2019-01-23T17:21:05.928353","modified":"2019-04-25T17:17:08.999021","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Enzyme","Synthesis","Ortholog"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The input file was downloaded from the source link and the 'Enzyme:UniProtAccession' column was mapped to canonical accessions using a python script [ac2canonical.py]"},{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/protein_ortholog.csv","filename":"protein_ortholog.csv"}],"output_list":[],"prerequisite":[],"description":"The mouse protein accessions (UniProt) were mapped to human protein accessions(UniProt) using ortholog file (protein_ortholog.csv)"},{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","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/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}],"output_list":[],"prerequisite":[],"description":"The mouse protein accessions (UniProt) were mapped to the NCBI Gene Id's and HGNC label using input files."},{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gtc2enz.txt","filename":"gtc2enz.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_ortholog.csv","filename":" mouse_protein_ortholog.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/Homo_sapiens.gene_info.gz","filename":"Homo_sapiens.gene_info"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/human_glycan_enzyme.csv","filename":"human_glycan_enzyme.csv"}],"prerequisite":[],"description":"The gene id's were mapped to 'Full_name_from_nomenclature_authority' (Enzyme:Description) from input file (Homo_sapiens.gene_info)."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"ac2canonical.py"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan_enzyme-csv.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions with information on the human[taxid:9606] proteins involved in the synthesis of the glycan (inferred via orthology)."],"bco_id":"http://data.glygen.org/DSBCO_000064","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"William York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Alison V Nairn","email":"avnairn@ccrc.uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Rahul Sethi","email":"rahulsethi80@gwu.edu"}],"created":"2019-01-23T17:21:05.928353","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:40:18.945705","name":"Enzyme Mapping (Human Proteins)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gtc2enz.txt","filename":"gtc2enz.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_enzyme.stat.csv","filename":"mouse_glycan_enzyme.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"83b09574d53afd867d20ec6caf6ba337","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Enzyme Mapping (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":"University of Georgia","contribution":["authoredBy"],"name":"William York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Alison V Nairn","email":"avnairn@ccrc.uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.933570","modified":"2019-04-12T14:11:17.771364","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Enzyme","Synthesis","Ortholog"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/gtc2enz.txt","filename":"gtc2enz.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_enzyme.csv","filename":"mouse_glycan_enzyme.csv"}],"prerequisite":[],"description":"The input file was downloaded from the source link and the 'Enzyme:UniProtAccession' column was mapped to canonical accession using a python script [ac2canonical.py]."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"ac2canonical.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["List of Glycans identified by GlyTouCan Accessions with infomation on the mouse[taxid:10090] proteins involved in the synthesis of the glycan."],"bco_id":"http://data.glygen.org/DSBCO_000065","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"William York","email":"will@ccrc.uga.edu"},{"orcid":"","affiliation":"University of Georgia","contribution":["authoredBy"],"name":"Alison V Nairn","email":"avnairn@ccrc.uga.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"}],"created":"2019-01-23T17:21:05.933570","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:40:40.519759","name":"Enzyme Mapping (Mouse Proteins)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/comp.txt ","filename":"comp.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mass.txt","filename":"mass.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glytoucan_type.txt","filename":"glytoucan_type.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_mass.txt","filename":"pbch.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/basecomposition.txt","filename":"taxa.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/compos.txt","filename":"uckb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/topology.txt","filename":"topology.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monosaccharides.txt","filename":"ucdb.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_properties.csv","filename":"mouse_glycan_properties.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_properties.stat.csv","filename":"mouse_glycan_properties.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8a23307709fd94a5cdd4ef70c8696f52","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Properties","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":"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"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.934602","modified":"2019-04-12T14:15:33.628740","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Glycan mass","properties"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/comp.txt","filename":"comp.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mass.txt","filename":"mass.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glytoucan_type.txt","filename":"glytoucan_type.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_mass.txt","filename":"glycan_mass"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/basecomposition.txt","filename":"basecomposition"},{"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/compos.txt","filename":"compos.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/topology.txt","filename":"topology.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monosaccharides.txt","filename":"monosaccharides.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_properties.csv","filename":"mouse_glycan_properties.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were separated into individual 2 column input files (glytoucan_acc, attribute) 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":"","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 and their different properties."],"bco_id":"http://data.glygen.org/DSBCO_000066","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.934602","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:41:05.966868","name":"Mouse Glycan Properties","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/comp.txt ","filename":"comp.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mass.txt","filename":"mass.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glytoucan_type.txt","filename":"glytoucan_type.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_mass.txt","filename":"pbch.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/basecomposition.txt","filename":"taxa.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/compos.txt","filename":"uckb.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/topology.txt","filename":"humanprot.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monosaccharides.txt","filename":"ucdb.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_properties.csv","filename":"human_glycan_properties.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_properties.stat.csv","filename":"human_glycan_properties.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"6effdc8f4f351db061a8607c6a49678d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Properties","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"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.935676","modified":"2019-04-12T14:20:00.578356","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Glycan mass","properties"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/comp.txt","filename":"comp.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mass.txt","filename":"mass.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glytoucan_type.txt","filename":"glytoucan_type.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_mass.txt","filename":"glycan_mass"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/basecomposition.txt","filename":"basecomposition"},{"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/compos.txt","filename":"compos.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/topology.txt","filename":"topology.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/monosaccharides.txt","filename":"monosaccharides.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/human_glycan_properties.csv","filename":"human_glycan_properties.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were separated into individual 2 column input files (glytoucan_acc, attributes) 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: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":"","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 and their different properties."],"bco_id":"http://data.glygen.org/DSBCO_000067","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@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"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.935676","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:41:34.165314","name":"Human Glycan Properties","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d2f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_type.txt","filename":"glycan_type.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_subtype.txt","filename":"glycan_subtype.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_classification.csv","filename":"human_glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_classification.stat.csv","filename":"human_glycan_classification.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"35ee2827bf4b2ec4e03602a687ca6c1c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Classification","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":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.936736","modified":"2019-04-12T14:22:16.241444","version":"1.0.13"},"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/allmotif.txt","filename":"allmotif.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_type.txt","filename":"glycan_type.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_subtype.txt","filename":"glycan_subtype.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/human_glycan_classification.csv","filename":"human_glycan_classification.csv"}],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"The input file was downloaded from the source link and the column 'Label' was filtered for specific values. (N-Glycan complex, N-Glycan core basic ,N-Glycan high mannose ,N-Glycan hybrid,N-Glycan truncated motif. First GlcpNAC cut off, O-Glycan core 1, O-Glycan core 1 fuzzy, O-Glycan core 2, O-Glycan core 2 fuzzy, O-Glycan core 3, O-Glycan core 3 fuzzy,             O-Glycan core 4, O-Glycan core 4 fuzzy, O-Glycan core 5, O-Glycan core 5 fuzzy, O-Glycan core 6, O-Glycan core 6 Fuzzy, O-Glycan core 7, O-Glycan core 7 fuzzy)"},{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The values were separated into two column individual input text files (glytoucan_acc|glycan_type/glycan_subtype) using a python script [make-glycan_classification-txt.py]. Following rules were applied to GlyTouCan accessions which had one of the following scenarios for subtypes: a) high mannose |hybrid = hybrid b) complex | hybrid = hybrid c) core basic = no subtype d) core x | core x fuzzy = core x  [where x= 1-7]  e) core x fuzzy = no subtype [where x= 1-7] f) core 1| core 2| core 6 = core 2  g) core 3| core 4 | core 6 = core 6"},{"name":"","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"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."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan_classification-txt.py"}},{"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 with infomation on the the glycan type and glycan sub-type."],"bco_id":"http://data.glygen.org/DSBCO_000068","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.936736","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:44:34.677598","name":"Human Glycan Classification","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d30"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_type.txt","filename":"glycan_type.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_subtype.txt","filename":"glycan_subtype.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_classification.csv","filename":"mouse_glycan_classification.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_classification.stat.csv","filename":"mouse_glycan_classification.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c0ff846fb4feab9c9353681335dd436a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Classification","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":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.937775","modified":"2019-04-12T14:24:31.754518","version":"1.0.13"},"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/glycan_type.txt","filename":"glycan_type.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/glycan_subtype.txt","filename":"glycan_subtype.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_classification.csv","filename":"mouse_glycan_classification.csv"}],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"The input file was downloaded from the source link and the column 'Label' was filtered for specific values. (N-Glycan complex, N-Glycan core basic ,N-Glycan high mannose ,N-Glycan hybrid,N-Glycan truncated motif. First GlcpNAC cut off, O-Glycan core 1, O-Glycan core 1 fuzzy, O-Glycan core 2, O-Glycan core 2 fuzzy, O-Glycan core 3, O-Glycan core 3 fuzzy,             O-Glycan core 4, O-Glycan core 4 fuzzy, O-Glycan core 5, O-Glycan core 5 fuzzy, O-Glycan core 6, O-Glycan core 6 Fuzzy, O-Glycan core 7, O-Glycan core 7 fuzzy)"},{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"The values were separated into two column individual input text files (glytoucan_acc|glycan_type/glycan_subtype) using a python script [make-glycan_classification-txt.py]. Following rules were applied to GlyTouCan accessions which had one of the following scenarios for subtypes: a) high mannose |hybrid = hybrid b) complex | hybrid = hybrid c) core basic = no subtype d) core x | core x fuzzy = core x  [where x= 1-7]  e) core x fuzzy = no subtype [where x= 1-7] f) core 1| core 2| core 6 = core 2  g) core 3| core 4 | core 6 = core 6"},{"name":"","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[],"description":"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."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/blob/master/integration/ ","filename":"make-glycan_classification-txt.py"}},{"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 with infomation on the the glycan type and glycan sub-type."],"bco_id":"http://data.glygen.org/DSBCO_000069","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.937775","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:45:05.629309","name":"Mouse Glycan Classification","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d31"},"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/human_glycan_images.csv","filename":"human_glycan_images.csv"}}]},"bco_spec_version":"1.3.0","checksum":"54ac42b8be43a056389e44efdda7400c","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Images","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":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.938796","modified":"2019-04-12T14:25:46.064459","version":"1.0.13"},"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/human_glycan_images.csv","filename":"human_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: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]. 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":"","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_images-directory.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_000070","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.938796","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-28T14:37:37.900868","name":"Human Glycan Images","version":"1.0.5"}
{"_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":"3a5c317d40ec7f21ae821258166de3c1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Images","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":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.939826","modified":"2019-04-12T14:28:20.449199","version":"1.0.13"},"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":"","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_images-directory.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","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["authoredBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.939826","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-28T14:41:24.187554","name":"Mouse Glycan Images","version":"1.0.5"}
{"_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":"8f836e7b295f0ee71337805a802ff40d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000072","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:04:43.787061","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d34"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"64dd04d33edea6d33fb2e2b19decdf08","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.941909","modified":"2019-02-19T14:05:10.307734","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000073","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.941909","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:05:10.307734","name":"","version":"1.0.5"}
{"_id":{"$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":"d48f349e231ebf334f3afed5c5d60854","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000074","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:06:27.134501","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d36"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"787c742b7f7602bf45db73e037cd1f46","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.943995","modified":"2019-02-19T14:08:33.746059","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000075","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.943995","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:08:33.746059","name":"","version":"1.0.5"}
{"_id":{"$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":"e50a0aa0a44119d31a5c7d42cf6f0d90","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000076","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:09:15.747085","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d38"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"694344f32a36c4084a25d54be2aa50b1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.946079","modified":"2019-02-19T14:09:57.295655","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000077","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.946079","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:09:57.295655","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d39"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_acc.txt","filename":"motif_acc.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_name.txt","filename":"motif_name.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_motif.csv","filename":"human_glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_glycan_motif.stat.csv","filename":"human_glycan_motif.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"8c03eab27f6cb92272d6f8a01d0700fe","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Glycan Motifs","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":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.947104","modified":"2019-04-12T14:30:46.291499","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Classification","Motifs"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"This file contains GlyTouCan accessions with information on motif accession and motif name. 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: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 "},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_acc.txt","filename":"motif_acc.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_name.txt","filename":"motif_name.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/human_glycan_motif.csv","filename":"human_glycan_motif.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were seperated into individual 2 column input text 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-dataset.py] to generate the final output csv file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/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 with motif information."],"bco_id":"http://data.glygen.org/DSBCO_000078","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.947104","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:43:45.371437","name":"Human Glycan Motifs","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_acc.txt","filename":"motif_acc.txt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_name.txt","filename":"motif_name.txt"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_motif.csv","filename":"mouse_glycan_motif.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_glycan_motif.stat.csv","filename":"mouse_glycan_motif.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"fe2cd220a873c7b68eec9ecb6d3e1c2d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Glycan Motifs","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"George Wahington 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":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.948124","modified":"2019-04-12T14:34:09.315197","version":"1.0.13"},"description_domain":{"keywords":["GlyTouCan","Glycan","Classification","Motifs"],"pipeline_steps":[{"name":"python","step_number":1,"version":"","input_list":[],"output_list":[],"prerequisite":[{"name":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"description":"This file contains GlyTouCan accessions with information on motif accession and motif name. he 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] f) If the glycan is a motif of the glycan mentioned under criteria a-f "},{"name":"python","step_number":2,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/allmotif.txt","filename":"allmotif.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_acc.txt","filename":"motif_acc.txt"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/motif_name.txt","filename":"motif_name.txt"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/mouse_glycan_motif.csv","filename":"mouse_glycan_motif.csv"}],"prerequisite":[],"description":"The input file(s) were downloaded from the source link and were seperated into individual 2 column input text 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-dataset.py] to generate the final output csv file."}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend/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 with motif information."],"bco_id":"http://data.glygen.org/DSBCO_000079","contributors":[{"orcid":"","affiliation":"George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"Georgetown University","contribution":["contributedBy"],"name":"Nathan Edwards","email":"nje5@georgetown.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Brian Fochtman ","email":"bfochtman@email.gwu.edu"},{"orcid":"","affiliation":"George Washington University","contribution":["contributedBy"],"name":"Reza Mousavi","email":"rezamousavi@gwmail.gwu.edu"}],"created":"2019-01-23T17:21:05.948124","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-01-30T14:44:09.706664","name":"Mouse Glycan Motifs","version":"1.0.5"}
{"_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":"86902be94989bcd071670d9d558027d5","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000080","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:10:41.602225","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_genelocus.csv","filename":"human_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_genelocus.stat.csv","filename":"human_protein_genelocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"9f32cb1a4aa5adfbf73ecfe5083455b6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Gene Locus","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-03-16T17:06:24.097514","version":"1.0.13"},"description_domain":{"keywords":["species: homo sapiens","dataset: genelocus","category: protein","gene locus"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/GLYDS000081","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":"2019-01-07T16:40:17-0500","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":"XXXXXXXXXXXXXXXXXXX","filename":"extract-from-endpoint.py"}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Human (taxid:9606) Gene Locus contains 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 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000081","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:10:34.108618","name":"Human Gene Locus","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_genelocus.csv","filename":"mouse_protein_genelocus.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_genelocus.stat.csv","filename":"mouse_protein_genelocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c46e92a9c854bd42c90d7fdc2c3e30e3","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Gene Locus","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-03-16T15:54:59.970402","version":"1.0.13"},"description_domain":{"keywords":["species: mus musculus","dataset: genelocus","category: protein","gene locus"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/GLYDS000082","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":"2019-01-07T16:40:17-0500","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":"XXXXXXXXXXXXXXXXXXX","filename":"extract-from-endpoint.py"}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["Mouse (taxid:10090) Gene Locus contains 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 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000082","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Preethi Vasudev","email":"pvasudev@ebi.ac.uk"}],"created":"2019-01-23T17:21:05.951268","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:11:57.674985","name":"Mouse Gene Locus","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"9cc4200fafcf9a33ff758f69fa6b1668","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.952378","modified":"2019-02-19T14:12:30.636705","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000083","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.952378","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:12:30.636705","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d3f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glyco-phenotype_disease_curation_list_v12-18-74.csv","filename":"human_glyco-phenotype_disease_curation_list_v12-18-74.csv"}},{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:46:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.csv","filename":"human_protein_disease.csv"}}]},"bco_spec_version":"1.3.0","checksum":"1d9146bfe0b94e6ef372957592402ec6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human 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":"Monarch Initiative - Oregon Health \u0026 Science University","contribution":["contributedBy"],"name":"Jean-Philippe Gourdine","email":"gourdine@ohsu.edu"}],"created":"2019-01-23T17:21:05.953432","modified":"2019-04-23T15:37:06.441631","version":"1.0.13"},"description_domain":{"keywords":["disease","HPO","OMIM","Congenital Disorders of Glycosylation (CDG)","Monarch Initiative"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_glyco-phenotype_disease_curation_list_v12-18-74.csv","filename":"human_glyco-phenotype_disease_curation_list_v12-18-74.csv"},{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:46:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_disease.csv","filename":"human_protein_disease.csv"}],"prerequisite":[],"description":"The script maps the mondo ids and omim phenotype ids to UniProtKB canonical accession to finally produce a csv file"}]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 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_000084","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.953432","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:12:58.828327","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d40"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"bco_spec_version":"1.3.0","checksum":"bee3ffd1e90ba0dfc8faa9b2362f9da4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.954630","modified":"2019-02-19T14:13:24.932675","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"manual","software_prerequisites":[{"version":"2.7.5","name":"Python","uri":{"access_time":"","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000085","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.954630","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:13:24.932675","name":"","version":"1.0.5"}
{"_id":{"$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":"0555485c9f6bba4fec90f9a7b18ab90d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"1.0.13"},"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":"","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":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000086","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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:13:50.053333","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d42"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_recnames.csv","filename":"human_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_recnames.stat.csv","filename":"human_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"5ebb0e5e5f02ad0652d4ab715090dc5a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Recommeded Protein 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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T15:14:22.226476","version":"1.0.13"},"description_domain":{"keywords":["protein recommended name"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.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":"2019-03-05T14:40:17-0500","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 Recommended Protein Name (UniProtKB) dataset contains UniProtKB recommended names for human [taxid:9606] proteins","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000087","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:13:45.906760","name":"Human Recommeded Protein Names (UniProtKB)","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d43"},"io_domain":{"input_subdomain":[{"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"}},{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_recnames.csv","filename":"mouse_protein_recnames.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_recnames.stat.csv","filename":"mouse_protein_recnames.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"76186e366275cc90a66cbe425886099b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Protein Recommended 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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T12:40:20.308630","version":"1.0.13"},"description_domain":{"keywords":["protein recommended name"],"pipeline_steps":[{"name":"extract-from-endpoint.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/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"},{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","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":"2019-03-05T14:40:17-0500","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 Mouse Recommended Protein Name (UniProtKB) dataset contains UniProtKB recommended names for mouse [taxid:10090] proteins","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000088","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-21T12:15:22.917727","name":"Mouse Protein Recommended Name (UniProtKB)","version":"1.0.5"}
{"_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/HumanDO_2018_12_20.owl","filename":"HumanDO_2018_12_20.owl"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}]},"bco_spec_version":"1.3.0","checksum":"4edf175af898594b16d5778a7d3927bb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"2019-04-23T15:41:52.073065","version":"1.0.13"},"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":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/HumanDO_2018_12_20.owl","filename":"HumanDO_2018_12_20.owl"},{"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"}],"output_list":[{"access_time":"2019-03-05T14:45:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.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":"2019-03-05T14:45:17-0500","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","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.958718","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:33:59.674294","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d45"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_xref_bgee.csv","filename":"human_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_protein_xref_bgee.stat.csv","filename":"human_protein_xref_bgee.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"793e6d3e5e46c92160c513a0c3fd4c5e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:51:47.557635","version":"1.0.13"},"description_domain":{"keywords":["gene expression","Bgee"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref Bgee dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000090","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.959744","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:34:23.571912","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d46"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_bgee.csv","filename":"mouse_protein_xref_bgee.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"55e56e8f6b7c34c0ef3d22d06797543a","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:52:18.466009","version":"1.0.13"},"description_domain":{"keywords":["gene expression","Bgee"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref Bgee contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000091","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.960771","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:34:52.533010","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d47"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_biomuta.csv","filename":"human_protein_xref_biomuta.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"563e3f9f02105e9806652ca034a3154e","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:59:33.990992","version":"1.0.13"},"description_domain":{"keywords":["mutation","BioMuta"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-03-05T14:40:17-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000092","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.961796","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:35:24.658162","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d48"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_brenda.csv","filename":"human_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"8c0a7a250a5ec79d248e89f0220966dd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T15:58:09.360145","version":"1.0.13"},"description_domain":{"keywords":["enzyme","ec number","BRENDA"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref BRENDA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000093","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.962821","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:35:49.488751","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d49"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_brenda.csv","filename":"mouse_protein_xref_brenda.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"41a5080b3d2a1dd0257dd96329e6d3bd","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:01:58.880087","version":"1.0.13"},"description_domain":{"keywords":["enzyme","ec number","BRENDA"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniProtKB Xref BRENDA contains mouse [taxid:10090]  UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000094","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.963848","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:36:14.276374","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cazy.csv","filename":"human_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"87073b4b53c045bbc4ead9c441ee8ba9","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:05:50.285171","version":"1.0.13"},"description_domain":{"keywords":["protein family","carbohydrate","CAZy"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref CAZy contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000095","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.964872","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:36:38.350107","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cazy.csv","filename":"mouse_protein_xref_cazy.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"2c3ba494cd448e067568c64a058e2747","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:09:21.021649","version":"1.0.13"},"description_domain":{"keywords":["carbohydrate","protein family","CAZy"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref CAZy contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000096","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.965897","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:37:06.149079","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_cdd.csv","filename":"human_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"facd4ebb818d393465c18fb0ca642b12","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:10:44.042410","version":"1.0.13"},"description_domain":{"keywords":["protein domains","CDD"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref CDD contains human  [taxid:9606] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000097","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.966922","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:38:06.287763","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_cdd.csv","filename":"mouse_protein_xref_cdd.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"104046a825fa8d4d1931c4f0be6a7235","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:12:56.479894","version":"1.0.13"},"description_domain":{"keywords":["protein domains","CDD"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref CDD contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000098","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.967951","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:37:29.041926","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":" https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_chembl.csv","filename":"human_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":" https://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":"c458fcf29f043778ffa4591dbf597efb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:17:09.427134","version":"1.0.13"},"description_domain":{"keywords":["bioactivity","ChEMBL"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref ChEMBL contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000099","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.968978","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:38:33.282854","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d4f"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_chembl.csv","filename":"mouse_protein_xref_chembl.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"17005709fb74ca3c7c87118ee0117e20","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:19:31.877547","version":"1.0.13"},"description_domain":{"keywords":["bioactivity","ChEMBL"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref ChEMBL contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers","ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000100","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.970018","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:39:01.797077","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d50"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_genecards.csv","filename":"human_protein_xref_genecards.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"a731c850f2ae31c1f0528af121c43522","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:35:43.739534","version":"1.0.13"},"description_domain":{"keywords":["gene","gene cards"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref GeneCards contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to GeneCards database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000101","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.971041","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:39:37.487745","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d51"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv","filename":"human_protein_xref_hgnc.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"58ada504c2e67d68c74da6bf4f4433e2","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:38:07.406622","version":"1.0.13"},"description_domain":{"keywords":["gene name","HGNC"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.py","filename":"extract-from-endpoint.py"}},{"uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human UniprotKB Xref HGNC contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to HGNC database accessions/identifiers","The HGNC is responsible for approving unique symbols and names for human loci, including protein coding genes, ncRNA genes and pseudogenes, to allow unambiguous scientific communication","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000102","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.972065","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:40:02.888005","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d52"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_mgi.csv","filename":"mouse_protein_xref_mgi.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"0eab1f3041d075cfdf4d534d7c9faec0","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:42:07.857940","version":"1.0.13"},"description_domain":{"keywords":["gene name","MGI"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref MGI contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to MGI database accessions/identifiers","MGI is the international database resource for the laboratory mouse, providing integrated genetic, genomic, and biological data to facilitate the study of human health and disease.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000103","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.973088","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:40:54.174482","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d53"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_geneid.csv","filename":"human_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"d7c1ee5cf49998a7d854e10ba180d9b7","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T11:54:35.134519","version":"1.0.13"},"description_domain":{"keywords":["gene","NCBI Gene"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniProtKB Xref NCBI Gene dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000104","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.974113","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:41:26.029109","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d54"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_geneid.csv","filename":"mouse_protein_xref_geneid.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"19db952fc5df3263f3b0acefb0b4a1d4","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T11:54:12.443649","version":"1.0.13"},"description_domain":{"keywords":["gene","NCBI Gene"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniProtKB Xref NCBI Gene dataset contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000105","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.975139","license":"https://creativecommons.org/licenses/by/4.0/","modified":"2019-02-19T14:41:49.607865","name":"","version":"1.0.5"}
{"_id":{"$oid":"5c48e8d1f5c47b65ae4b5d55"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_interpro.csv","filename":"human_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"730b82e31774a5aa260723d725079d21","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:55:45.110846","version":"1.0.13"},"description_domain":{"keywords":["protein family","protein domain","protein functional site"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref InterPro contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000106","contributors":[{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"}],"created":"2019-01-23T17:21:05.976176","license":"https://creativecommons.org/licenses/by/4.0/","modified":"","name":"Human Proteome Accessions","version":"1.0.5"}
{"_id":{"$oid":"5c8bc84bf5c47b4a20d22e6b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_interpro.csv","filename":"mouse_protein_xref_interpro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"6d53b987273d19d058c5ccb6a1fd7dc8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T16:59:28.330806","version":"1.0.13"},"description_domain":{"keywords":["protein family","protein domain","protein functional site"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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 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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/"}}],"script":[{"uri":{"access_time":"2019-01-07T16:42:17-0500","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 UniprotKB Xref InterPro contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000107"}
{"_id":{"$oid":"5c8bcd58f5c47b4beb295132"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_kegg.csv","filename":"human_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"532ed0e1a6529b91912b2b87e78eda5f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:05:20.560433","version":"1.0.13"},"description_domain":{"keywords":["pathway","Keggmm"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref KEGG PATHWAY contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000108"}
{"_id":{"$oid":"5c8bcd8cf5c47b4c381e56b5"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_kegg.csv","filename":"mouse_protein_xref_kegg.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://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":"c2d98872878a0c797ba9e22b4da2faeb","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:08:37.810527","version":"1.0.13"},"description_domain":{"keywords":["pathway","Kegg"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniprotKB Xref KEGG PATHWAY contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers","KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000109"}
{"_id":{"$oid":"5c8bce1ef5c47b4cf4e9ac02"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_xref_mim.csv","filename":"human_protein_xref_mim.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://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":"12db37566dfc61727a0cbec83d38d7bc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:11:22.579022","version":"1.0.13"},"description_domain":{"keywords":["phenotype","OMIM"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniprotKB Xref OMIM contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMIM database accessions/identifiers","Online Mendelian Inheritance in Man (OMIM) is a continuously updated catalog of human genes and genetic disorders and traits, with a particular focus on the gene-phenotype relationship.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000110"}
{"_id":{"$oid":"5c8bce48f5c47b4d41044d46"},"io_domain":{"input_subdomain":[],"output_subdomain":[]},"bco_spec_version":"1.3.0","checksum":"17e28232302b0e8471971f5e94eff88d","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"","name":"","contributors":[],"created":"","modified":"2019-03-15T14:41:43.658687","version":"1.0.13"},"description_domain":{"keywords":[],"pipeline_steps":[]},"execution_domain":{"external_data_endpoints":[],"environment_variables":{},"script_driver":"","software_prerequisites":[],"script":[]},"error_domain":{"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":[],"bco_id":"http://data.glygen.org/DSBCO_000111"}
{"_id":{"$oid":"5c8bce85f5c47b4d8e364936"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_nextprot.csv","filename":"human_protein_xref_nextprot.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"ca8f6758b69b49949499e5536befb8f6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:13:55.439644","version":"1.0.13"},"description_domain":{"keywords":["neXtProt"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniprotKB Xref neXtProt contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to neXtProt database accessions/identifiers","neXtProt is a comprehensive human-centric discovery platform, offering its users a seamless integration of and navigation through protein-related data","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000112"}
{"_id":{"$oid":"5c8bcec3f5c47b4ddb803a32"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_oma.csv","filename":"human_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"587a414a7f934037102df12bac6f769d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:19:52.926480","version":"1.0.13"},"description_domain":{"keywords":["ortholog","OMA"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref OMA contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers","The OMA (“Orthologous MAtrix”) project is a method and database for the inference of orthologs among complete genomes.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000113"}
{"_id":{"$oid":"5c8bceeef5c47b4e2b8ee531"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_oma.csv","filename":"mouse_protein_xref_oma.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"https://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":"99bd5844e07592e99518b0905bdc350b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:18:46.804081","version":"1.0.13"},"description_domain":{"keywords":["ortholog","OMA"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref OMA contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers","The OMA (“Orthologous MAtrix”) project is a method and database for the inference of orthologs among complete genomes.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000114"}
{"_id":{"$oid":"5c8bf53ef5c47b579730bf2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_orthodb.csv","filename":"human_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"386ffa81a067cbff36cc5955aed20d7b","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:21:20.050383","version":"1.0.13"},"description_domain":{"keywords":["ortholog","OrthoDB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref OrthoDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000115"}
{"_id":{"$oid":"5c8bf5d8f5c47b57d9c431ba"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_orthodb.csv","filename":"mouse_protein_xref_orthodb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"44a03daa7391abee3f986dd381fa8f95","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:23:27.103831","version":"1.0.13"},"description_domain":{"keywords":["ortholog","OrthoDB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniprotKB Xref OrthoDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers","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","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000116"}
{"_id":{"$oid":"5c8bf741f5c47b5845beebcd"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_panther.csv","filename":"human_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"d530f48532fbea25423a72416c354e94","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:29:25.025671","version":"1.0.13"},"description_domain":{"keywords":["protein family","PANTHER"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref PANTHER contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000117"}
{"_id":{"$oid":"5c8bf7b3f5c47b58714663d6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_panther.csv","filename":"mouse_protein_xref_panther.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"fc26211f3da2441fa9af7f25f53915bf","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:32:39.536807","version":"1.0.13"},"description_domain":{"keywords":["protein family","PANTHER"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniprotKB Xref PANTHER contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers","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.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000118"}
{"_id":{"$oid":"5c8bf849f5c47b58ebb826f6"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pdb.csv","filename":"human_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"e2a013eb40f18b5c98c862fc676bcd4d","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:39:42.433835","version":"1.0.13"},"description_domain":{"keywords":["protein 3D structure","PDB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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 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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref PDB contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000119"}
{"_id":{"$oid":"5c8bf8ebf5c47b59171e9974"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pdb.csv","filename":"mouse_protein_xref_pdb.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"8340813fc61e41be4e0ece284b528f86","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:39:18.818525","version":"1.0.13"},"description_domain":{"keywords":["protein 3D structure","PDB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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 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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref PDB contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers","The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000120"}
{"_id":{"$oid":"5c8c03e6f5c47b59903c90e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pfam.csv","filename":"human_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"932060d3ff605286bebdb26ec4f4f4c6","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:44:46.620489","version":"1.0.13"},"description_domain":{"keywords":["protein family","Pfam"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref Pfam contains human [taxid:9606] 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000121"}
{"_id":{"$oid":"5c8c04aef5c47b59e714ed9a"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pfam.csv","filename":"mouse_protein_xref_pfam.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"231d5be06f19a061fd6471a91ec194d1","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:43:10.682473","version":"1.0.13"},"description_domain":{"keywords":["protein family","Pfam"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref Pfam contains mouse [taxid:10090] 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000122"}
{"_id":{"$oid":"5c8c062ef5c47b5a1fde3210"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pro.csv","filename":"human_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"8e213f4317e50db07625b89e0b2a490f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:48:02.518483","version":"1.0.13"},"description_domain":{"keywords":["protein ontology","PRO"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniprotKB Xref PRO contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000123"}
{"_id":{"$oid":"5c8c069ff5c47b5a4c9b083e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_pro.csv","filename":"mouse_protein_xref_pro.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"521e7bf3b6f60715f52990f3c11fde74","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:49:46.588065","version":"1.0.13"},"description_domain":{"keywords":["protein ontology","PRO"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniprotKB Xref PRO contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers","PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000124"}
{"_id":{"$oid":"5c8c078ef5c47b5a94fa2779"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.csv","filename":"human_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"75ded24f2c16376ef2e53a3df051d14f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:53:55.374730","version":"1.0.13"},"description_domain":{"keywords":["pathway","REACTOME"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000125"}
{"_id":{"$oid":"5c8c0817f5c47b5acea50e64"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_reactome.csv","filename":"mouse_protein_xref_reactome.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"842e82c2add4df2465e7754a5ec44dd8","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T17:53:23.035503","version":"1.0.13"},"description_domain":{"keywords":["pathway","REACTOME"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref Reactome contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers","REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000126"}
{"_id":{"$oid":"5c8c0919f5c47b5b06462bf0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv","filename":"human_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"ec1e3d17c16ecabdb8d605eff22c1696","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-08T12:24:45.660821","version":"1.0.13"},"description_domain":{"keywords":["protein sequence","NCBI RefSeq"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human [taxid:9606] UniprotKB Xref RefSeq contains human UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein.","The dataset is derived from 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000127"}
{"_id":{"$oid":"5c8c09b3f5c47b5b32e9fe6d"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_refseq.csv","filename":"mouse_protein_xref_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"a9ebd41136c9c9f6eef49b7809d0f9da","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T18:00:52.405697","version":"1.0.13"},"description_domain":{"keywords":["protein sequence","NCBI RefSeq"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 UniProtKB Xref RefSeq contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers","NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein.","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000128"}
{"_id":{"$oid":"5c8c101bf5c47b5ba53b598e"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_xref_unicarbkb.csv","filename":"human_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_xref_unicarbkb.stat.csv","filename":"human_protein_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"399a8c46e647985ba7aad362eaa14e17","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T18:02:34.175689","version":"1.0.13"},"description_domain":{"keywords":["glycoprotein","UniCarbKB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Xref UniCarbKB contains human [taxid:9606] 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000129"}
{"_id":{"$oid":"5c8c10e0f5c47b5bfea63abf"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_xref_unicarbkb.csv","filename":"mouse_protein_xref_unicarbkb.csv"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_xref_unicarbkb.stat.csv","filename":"mouse_protein_xref_unicarbkb.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"53a50a742ef315aeed071da7be59b6bc","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"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":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-23T18:04:09.767338","version":"1.0.13"},"description_domain":{"keywords":["glycoprotein","UniCarbKB"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/","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":"2019-01-07T16:40:17-0500","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 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000130"}
{"_id":{"$oid":"5c8c3c82f5c47b68be0cedc0"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"","filename":""}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprot.csv","filename":"human_protein_function_uniprot.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprot.stat.csv","filename":"human_protein_function_uniprot.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"a3252a9c0e2af7bb8801144a8e543856","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniProtKB Protein Function","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T10:33:14.792937","version":"1.0.13"},"description_domain":{"keywords":["protein function"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_uniprot.csv","filename":"human_protein_function_uniprot.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":"2019-01-07T16:40:17-0500","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 Human UniProtKB Protein Function dataset contains biological function annotaion for human [taxid:9606] protein accesions from the UniProtKB database","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000131"}
{"_id":{"$oid":"5c8c3d24f5c47b69152224e1"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_function_uniprot.csv","filename":"mouse_protein_function_uniprot.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_protein_function_uniprot.stat.csv","filename":"mouse_protein_function_uniprot.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"c5a0e8fcb305de6e851d672cbda086ac","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse UniProtKB Protein Function","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T10:39:58.747968","version":"1.0.13"},"description_domain":{"keywords":["protein function"],"pipeline_steps":[{"name":"extract-from-endpoint.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_uniprot.csv","filename":"mouse_protein_function_uniprot.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":"2019-01-07T16:40:17-0500","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 Mouse UniProtKB Protein Function dataset contains biological function annotaion for mouse [taxid:10090] protein accesions from the UniProtKB database","The dataset is derived from 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000132"}
{"_id":{"$oid":"5c8d4ff3f5c47b31a13ff81c"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"}},{"uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_refseq.csv","filename":"human_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://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":"1dbb2d98beaba72bc9a1682a73d0b66f","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Refseq Protein Function","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","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":"2019-03-16T15:35:15.248632","modified":"2019-04-24T10:47:03.644563","version":"1.0.13"},"description_domain":{"keywords":["protein function","NCBI RefSeq"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff","filename":"refseq_protein_all_9606.gpff"},{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv","filename":"human_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_function_refseq.csv","filename":"human_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":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/","filename":""}}],"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-gp.py","filename":"extract-from-gp.py"}}]},"error_domain":{"empirical_error":{},"algorithmic_error":{},"emperical_error":{}},"parametric_domain":[{"step":"","value":"","param":""}],"usability_domain":["The Human RefSeq Protein Function dataset contains biological function annotaion of human [taxid:9606] genes from GeneRIF section in the NCBI RefSeq database","The data is downloaded from NCBI RefSeq and is processed into a dataset by GlyGen. 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":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"}},{"uri":{"access_time":"2019-01-07T16:40:17-0500","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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_function_refseq.csv","filename":"mouse_protein_function_refseq.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://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":"4449eb5059fe623fadbb2bdd5643a085","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Refseq Protein Function","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","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":"2019-03-16T15:38:06.344586","modified":"2019-04-24T10:46:06.266102","version":"1.0.13"},"description_domain":{"keywords":["protein function","NCBI RefSeq"],"pipeline_steps":[{"name":"extract-from-gp.py","step_number":1,"version":"1.0","input_list":[{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_10090.gpff","filename":"refseq_protein_all_10090.gpff"},{"access_time":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_idmapping.csv","filename":"mouse_protein_idmapping.csv"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","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":"2019-01-07T16:40:17-0500","sha1_chksum":"","uri":"https://www.python.org/download/releases/2.7.5/","filename":""}}],"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 RefSeq Protein Function contains biological function annotaion of mouse [taxid:10090] genes from GeneRIF section in the NCBI RefSeq database","The data is downloaded from NCBI RefSeq and is processed into a dataset by GlyGen. 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":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"}},{"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"}}],"output_subdomain":[{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_protein_transcriptlocus.csv","filename":"human_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_protein_transcriptlocus.stat.csv","filename":"human_protein_transcriptlocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"50eb71f64ba39f59df3c149e5a456668","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human Transcript Locus","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":[],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T10:51:28.532984","version":"1.0.13"},"description_domain":{"keywords":["transcript locus","peptide id","Ensembl"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-9606-homo-sapiens-2018-11.nt","filename":"uniprot-proteome-9606-homo-sapiens-2018-11.nt"},{"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"}],"output_list":[{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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 Human Transcript Locus 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 2018-11 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProt and GlyGen"],"bco_id":"http://data.glygen.org/DSBCO_000135"}
{"_id":{"$oid":"5c8d5751f5c47b34a28a481b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"2019-03-05T14:40:17-0500","sha1_chksum":"","uri":"http://data.glygen.org/datasets/source/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"}},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.csv","filename":"mouse_protein_transcriptlocus.csv"}},{"mediatype":"csv","uri":{"access_time":"2019-01-07T16:42:17-0500","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_transcriptlocus.stat.csv","filename":"mouse_protein_transcriptlocus.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"0572c243c767245bb562869da7a7426f","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Mouse Transcript Locus","contributors":[{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Jeet Vora","email":"jeetvora@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Rahi Navelkar","email":"rsn13@gwu.edu"},{"orcid":"","affiliation":"The George Washington University","contribution":["createdBy"],"name":"Robel Kahsay","email":"rykahsay@gwu.edu"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Maria Martin","email":"martin@ebi.ac.uk"},{"orcid":"","affiliation":"EMBL-EBI-UniProt","contribution":["contributedBy"],"name":"Leyla Garcia","email":"ljgarcia@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":"2019-04-24T11:36:52.305115","version":"1.0.13"},"description_domain":{"keywords":["transcript locus","peptide id"],"pipeline_steps":[{"name":"extract-from-endpoint.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/uniprot-proteome-10090-mus-musculus-2018-11.nt","filename":"uniprot-proteome-10090-mus-musculus-2018-11.nt"},{"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":"2019-01-07T16:42:17-0500","sha1_chksum":"","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":"2019-01-07T16:40:17-0500","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":["Th Mouse Transcript Locus 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 2018-11 UniProt release. The dataset is contributed by EMBL-EB-UniProt and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EB-UniProt 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":"d1f16f48209263954b8e708be423e263","extension_domain":{"additional_license":{"data_license":"https://creativecommons.org/licenses/by/4.0/","scripts_license":"https://www.gnu.org/licenses/gpl-3.0.en.html"},"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Protein 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":"2019-04-24T11:49:32.532771","version":"1.0.13"},"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":"2019-01-07T16:40:17-0500","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":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.stat.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"cb38ae8798d1e6b3f55a24b5312048ea","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"Human UniCarbKB 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":"2019-04-16T16:31:37.511217","modified":"2019-04-24T11:50:58.302541","version":"1.0.13"},"description_domain":{"keywords":["citations"],"pipeline_steps":[{"name":"Linux","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}],"prerequisite":[],"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_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/human_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log","filename":"human_proteoform_glycosylation_sites_unicarbkb_glytoucan_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":[],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/make-citations-table.py","filename":"make-citations-table.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_000138"}
{"_id":{"$oid":"5cb63eb3f5c47b10c5f37f2b"},"io_domain":{"input_subdomain":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}},{"uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}}],"output_subdomain":[{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}},{"mediatype":"","uri":{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log","filename":"/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log"}},{"mediatype":"csv","uri":{"access_time":"","sha1_chksum":"","uri":"http://data.glygen.org/datasets/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.stat.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.stat.csv"}}]},"bco_spec_version":"1.3.0","checksum":"77204da43000a48fa5ff72f55ff08554","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"","name":"Mouse UniCarbKB 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":"2019-04-16T16:44:35.331041","modified":"2019-04-18T16:05:11.260013","version":"1.0.13"},"description_domain":{"keywords":["citations"],"pipeline_steps":[{"name":"Linux","step_number":0,"version":"","input_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/source/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}],"prerequisite":[],"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_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations_uniq.csv"}],"output_list":[{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.csv"},{"access_time":"","sha1_chksum":"","uri":"https://data.glygen.org/ln2wwwdata/logs/mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_citations.log","filename":"mouse_proteoform_glycosylation_sites_unicarbkb_glytoucan_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":[],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/make-citations-table.py","filename":"make-citations-table.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_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":"e400173f4d7750b16b487fa5847ed9c0","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"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":"1.0.13"},"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":[],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/make-citations-table.py","filename":"make-citations-table.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":"bdd232932c6fba8850ff2a5757958373","extension_domain":{"fhir_extension":[],"scm_extension":{"scm_repository":"","scm_path":"","scm_type":"git","scm_commit":""}},"provenance_domain":{"license":"https://creativecommons.org/licenses/by/4.0/","name":"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":"1.0.13"},"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":[],"script":[{"uri":{"access_time":"","sha1_chksum":"","uri":"https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/make-citations-table.py","filename":"make-citations-table.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"}