{ "object_id": "https://biocomputeobject.org/GLY_000980/v-2.5.1", "etag": "abac5db0f749a916a1aa89b9b9038699", "spec_version": "1.3.0", "provenance_domain": { "name": "Chicken Glycosylation Sites (GlyConnect) ", "version": "v-2.5.1", "license": "https://creativecommons.org/licenses/by/4.0/", "created": "2020-02-10T10:16:50.152756", "modified": "2024-05-21T15:16:24.995Z", "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jeetvora@gwu.edu" }, { "name": "Robel Kahsay", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "rykahsay@gwu.edu" }, { "name": "Frederique Lisacek", "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "email": "frederique.lisacek@sib.swiss" }, { "name": "Julien Mariethoz", "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "email": "julien.mariethoz@sib.swiss" }, { "name": "Karina Martinez", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "karinamartinez@gwu.edu" }, { "name": "Luke Johnson", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "luke.johnson@email.gwu.edu" }, { "name": "Urnisha Bhuiyan", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "sbhuiyan28@email.gwu.edu" }, { "name": "Cyrus Au-Yeung", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "cyruschauyeung@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" }, { "name": "Kate Warner", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "k.warner1@gwu.edu" } ] }, "usability_domain": [ "The Chicken Glycosylation Sites (GlyConnect) dataset contains Gallus gallus [taxid:9606] 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:Homo sapiens). If you use this dataset please provide proper attribution to GlyConnect and GlyGen." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/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": "Gallus gallus", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "glycosylation", "reported glycosylation" ], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "input_list": [], "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 (chicken_proteoform_glycosylation_sites_glyconnect.1.log)", "prerequisite": [], "output_list": [] } ] }, "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-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ] }, "parametric_domain": [ { "value": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/n_sequon_info.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.5.1/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2024_04_02/cellosaurus.txt" } }, { "uri": { "filename": "glyconnect_chicken.json", "uri": "https:/data.glygen.org/ln2downloads/glyconnect/2024_04_02/glyconnect_chicken.json" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_glyconnect.csv", "filename": "chicken_proteoform_glycosylation_sites_glyconnect.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.5.1/reviewed/chicken_proteoform_glycosylation_sites_glyconnect.stat.csv", "filename": "chicken_proteoform_glycosylation_sites_glyconnect.stat.csv" } } ] }, "error_domain": {} }