{ "object_id": "https://biocomputeobject.org/GLY_000004/1.0.13", "license": "https://creativecommons.org/licenses/by/4.0/", "contributors": [ { "orcid": "", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@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", "spec_version": "1.3.0", "modified": "2019-02-21T11:39:49.590409", "extension_domain": [ { "extension_schema": "http://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Reviewed", "category_name": "status" } ] } } ], "io_domain": { "input_subdomain": [ { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/source/human_protein_glycosyltransferase_2018_11.csv", "filename": "human_protein_glycosyltransferase_2018_11.csv" } }, { "uri": { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv", "filename": "human_protein_idmapping.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_glycosyltransferase.csv", "filename": "human_protein_glycosyltransferase.csv" } }, { "mediatype": "csv", "uri": { "uri": "http://data.glygen.org/datasets/reviewed/human_protein_glycosyltransferase.stat.csv", "filename": "human_protein_glycosyltransferase.stat.csv" } } ] }, "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Human Glycosyltransferases", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Hayley Dingerdissen", "email": "hmhamilt@gwmail.gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "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": [ { "uri": "https://data.glygen.org/ln2wwwdata/source/human_protein_glycosyltransferase_2018_11.csv", "filename": "human_protein_glycosyltransferase_2018_11.csv" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/human_protein_idmapping.csv", "filename": "human_protein_idmapping.csv" } ], "output_list": [ { "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] \u201cGlycosyltransferase\u201d [KW-0328] were retrieved from UniProtKB/Swiss-Prot using the following query: \u201ckeyword:\"Glycosyltransferase [KW-0328]\" keyword:\"Complete proteome [KW-0181]\" AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\"\u201d (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 \u201ctransferase activity, transferring glycosyl groups\u201d [GO:0016757] and descendants with relationship \u201cenables\u201d 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 \u201c9606\u201d into the search bar corresponding to \u201cTax_id.\u201d 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": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-csv.py", "filename": "extract-from-csv.py" } } ] }, "version": "1.0.5", "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" ], "etag": "628f14d3529b50c7d47d3006a6b6bee2", "_id": { "$oid": "5c48e8d1f5c47b65ae4b5cef" }, "name": "Human Glycosyltransferases" }