{ "object_id": "https://biocomputeobject.org/GLY_000143/v-2.9.1", "spec_version": "1.3.0", "etag": "a638b380d122cc379458fa822cf89688", "provenance_domain": { "name": "Human Protein Glycosylation (Literature)", "version": "v-2.9.1", "license": "https://creativecommons.org/licenses/by/4.0/", "created": "2019-06-14T14:54:26.195339", "modified": "2024-12-10T16:47:37.700Z", "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "email": "jeetvora@gwu.edu", "contribution": [ "createdBy" ] }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "contribution": [ "contributedBy" ], "name": "Not Applicable" }, { "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": "Kate Warner", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "k.warner1@gwu.edu" } ] }, "usability_domain": [ "The dataset provides information on N-glycosylation sites on Human proteins. The data has been processed from the supplementary material from 2 publications (1. \"Deeb, S. J., Cox, J., Schmidt-Supprian, M., & Mann, M. (2013). N-linked Glycosylation Enrichment for In-depth Cell Surface Proteomics of Diffuse Large B-cell Lymphoma Subtypes. Molecular & Cellular Proteomics, 13(1), 240-251. doi:10.1074/mcp.m113.033977\" 2. \"Boersema, P. J., Geiger, T., Winiewski, J. R., & Mann, M. (2012). Quantification of the N-glycosylated Secretome by Super-SILAC During Breast Cancer Progression and in Human Blood Samples. Molecular & Cellular Proteomics, 12(1), 158-171. doi:10.1074/mcp.m112.023614\"). The listed proteins (UniProtKB) accessions are part of the GlyGen UniProtKB canonical list (https://data.glygen.org/GLY_000001). " ], "description_domain": { "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "input_list": [], "description": "The supplementary tables from two publications were downloaded and columns \"protein\" and \"site\" were extracted, and additional column evidence where values=\"the respective PMIDs\" was added to produce the input files. A python script was developed process input files 1. to map the UniProtKB accessions to UniProtKB canonical accessions 2. Check position+amino acid with the canonical fasta sequences (https://data.glygen.org/GLY_000002) to generate the output files.", "prerequisite": [], "output_list": [] } ], "keywords": [ "proteins", "canonical", "glycosylation", "literature", "publications" ] }, "parametric_domain": [ { "value": "" } ], "io_domain": { "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_literature.csv", "filename": "human_proteoform_glycosylation_sites_literature.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/reviewed/human_proteoform_glycosylation_sites_literature.stat.csv", "filename": "human_proteoform_glycosylation_sites_literature.stat.csv" } } ], "input_subdomain": [ { "uri": { "filename": "glycosylation_sites_lit_23090970_s2.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/glycosylation_sites_lit_23090970_s2.csv" } }, { "uri": { "filename": "glycosylation_sites_lit_23090970_s5.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/glycosylation_sites_lit_23090970_s5.csv" } }, { "uri": { "filename": "glycosylation_sites_lit_24190977_s5.cs", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/glycosylation_sites_lit_24190977_s5.cs" } }, { "uri": { "filename": "glycosylation_sites_lit_x_sx.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/glycosylation_sites_lit_x_sx.csv" } }, { "uri": { "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "sarscov1_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/misc/n_sequon_info.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.9.1/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2025_05_19/cellosaurus.txt" } } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "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": "Homo sapiens", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "UniCarbKB publications", "category_name": "tag" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "error_domain": {} }