{ "object_id": "https://biocomputeobject.org/GLY_000004/v-2.0.2", "spec_version": "1.3.0", "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": "Homo sapiens", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Glycosyltransferases", "category_name": "tags" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "provenance_domain": { "license": "https://creativecommons.org/licenses/by/4.0/", "name": "Human Glycosyltransferases", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Xavier Holmes", "email": "xavierh@email.gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "authoredBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "authoredBy" ], "name": "Hayley Dingerdissen", "email": "hmhamilt@gwmail.gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Amanda Bell", "email": "amandab2140@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jonathon Keeney", "email": "keeneyjg@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Millicent Quartey", "email": "mquartey@email.gwu.edu" } ], "created": "2019-01-23T17:21:05.870634", "modified": "2020-11-19T09:40:53.639068", "version": "v-2.0.2" }, "description_domain": { "keywords": [ "GT", "glycosyltransferase", "CAZy", "CFG", "EC Number", "GO" ], "pipeline_steps": [ { "name": "make-protein-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv", "filename": "human_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/compiled/human_protein_glycosyltransferase.csv", "filename": "human_protein_glycosyltransferase.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.csv", "filename": "human_protein_glycosyltransferase.csv" } ], "prerequisite": [], "description": "The script maps and replaces the UniProtKb accession to the UniProtKB canonical accession" } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {}, "emperical_error": {} }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "usability_domain": [ "The Human Glycosyltransferases dataset contains list of human [taxid:9606] glycosyltransferases enzymes with evidence of glycosyltransferase activity defined by one or several of the following criteria: gene ontology (GO) or UniProtKB/Swiss-Prot annotation; classification by CAZY database; inclusion in the GT panel developed by the Consortium of Functional Glycomics (CFG); domains reported by InterPro and Pfam. The dataset was created by: Proteomes, gene and protein lists were retrieved from UniProtKB/Swiss-Prot. The full set of proteins comprising the human proteome was retrieved with the following search terms: keyword:\"Complete proteome [KW-0181]\" (now removed from UniProtKB) AND reviewed:yes AND organism:\"Homo sapiens (Human) [9606]\". To retrieve the list of all human glycosyltransferases, the full list of human proteins were filtered using Gene Ontology (GO) terms, with molecular function GO term, GO:0016757 transferase activity, transferring glycosyl groups, each corresponding to a unique gene. To ensure the gene list was comprehensive with respect to available annotations, entries were cross-referenced with two external glycomics databases: the Carbohydrate Active Enzymes database (CAZY, http://www.cazy.org/), the Consortium for Functional Glycomics (CFG) functional glycomics gateway (http://www.functionalglycomics.org/), BRENDA (https://www.brenda-enzymes.org/index.php) and Enzyme Portal (https://www.ebi.ac.uk/enzymeportal/). The list was then filtered to remove any duplicate references resulting from cross-database redundancy or secondary accessions. Entries not already contained in the GO-derived glycosyltransferase gene list were added to the list. InterPro and Pfam accessions were then retrieved for all genes currently in the list. For GlyGen, GTs that were not part of glycan metabolism were removed to produce a manually curated list of glycosyltransferase. If you use this dataset please provide proper attribution to UniProtKB and GlyGen." ], "etag": "056548bc272941fe3b51a1989543f8ad", "io_domain": { "input_subdomain": [ { "uri": { "filename": "human_protein_glycosyltransferase.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/compiled/human_protein_glycosyltransferase.csv" } }, { "uri": { "filename": "human_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.csv", "filename": "human_protein_glycosyltransferase.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_glycosyltransferase.stat.csv", "filename": "human_protein_glycosyltransferase.stat.csv" } } ] } }