{ "object_id": "https://biocomputeobject.org/GLY_000530/1.11.2", "spec_version": "1.3", "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": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites", "category_name": "tags" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "provenance_domain": { "license": "", "name": "SARS-CoV2 Glycosylation sites", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Rahi Navelkar", "email": "rsn13@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Frederique Lisacek", "email": "frederique.lisacek@sib.swiss" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Julien Mariethoz", "email": "julien.mariethoz@sib.swiss" }, { "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": "2020-09-24T13:36:00.724463", "modified": "2020-12-11T14:21:03.916525", "version": "1.11.2" }, "description_domain": { "keywords": [ "glycosylation", "reported glycosylation" ], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/source/glyconnect_sarscov2.json", "filename": "glyconnect_sarscov2.json" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv", "filename": "sarscov2_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_canonicalsequences.fasta", "filename": "sarscov2_protein_canonicalsequences.fasta" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv", "filename": "https://data.glygen.org/ln2wwwdata/reviewed/glycan_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2wwwdata/logs/sarscov2_proteoform_glycosylation_sites_glyconnect.1.log", "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.1.log" }, { "uri": "https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv", "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv" } ], "prerequisite": [], "description": "The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the 2019-09 UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (sarscov2_proteoform_glycosylation_sites_glyconnect.1.log)" } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "uri": "https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {}, "emperical_error": {} }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "usability_domain": [ "The SARS-CoV2 Glycosylation Sites (GlyConnect) dataset contains SARS-CoV2 [taxid:2697049] UniProtKB canonical accessions with information on reported glycosylation sites in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Severe acute respiratory syndrome coronavirus 2 (2019-nCoV)). If you use this dataset please provide proper attribution to GlyConnect and GlyGen." ], "etag": "241721379e513408fe8eec3cd6a9d984", "io_domain": { "input_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/glycan_masterlist.csv", "filename": "glycan_masterlist.csv" } }, { "uri": { "uri": "https:/data.glygen.org/ln2downloads/glyconnect/v-x.x.x/glyconnect_sarscov2.json", "filename": "sglyconnect_sarscov2.json" } }, { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_canonicalsequences.fasta", "filename": "sarscov2_protein_canonicalsequences.fasta" } }, { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_protein_masterlist.csv", "filename": "sarscov2_protein_masterlist.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv", "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv" } }, { "mediatype": "", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv", "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.1.log" } } ] } }