{ "object_id": "https://biocomputeobject.org/GLY_000335/v-2.7.1", "spec_version": "1.3.0", "etag": "bc988257fd970cb5b323755779e412cd", "provenance_domain": { "name": "HCV1a Glycosylation Sites (Literature + UniCarbKB)", "version": "v-2.7.1", "created": "2020-02-10T14:13:38.047090", "modified": "2024-05-17T11:23:56.687Z", "contributors": [ { "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": "UniCarbKB", "contribution": [ "contributedBy" ], "name": "Matthew Campbell", "email": "m.campbell2@griffith.edu.au" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "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": "Kate Warner", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "k.warner1@gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The HCV1a Glycosylation Sites (Literature + UniCarbKB) dataset contains glycosylation sites experimentally reported on Hepatitis C virus (isolate H77) [taxid:63746] protein. The data was extracted from publication PMID:18187336. (Iacob RE, Perdivara I, Przybylski M, Tomer KB. Mass spectrometric characterization of glycosylation of hepatitis C virus E2 envelope glycoprotein reveals extended microheterogeneity of N-glycans. J Am Soc Mass Spectrom. 2008;19(3):428\u2013444. doi:10.1016/j.jasms.2007.11.022). The glycan compositions from the publication were assigned GlyTouCan accessions by UniCarbKB. [https://academic.oup.com/nar/article/42/D1/D215/1052197 ,https://doi.org/10.1093/nar/gkt1128]" ], "description_domain": { "keywords": [ "reported glycosylation", "HCV" ], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "step_number": 1, "input_list": [], "description": "1) The data was extracted from the publications using supplemental material (Table 1,2,3). 2) The GenBank accession number (AF009606) retrieved from the paper was matched to the best hit UniProtKB Ac. (P27958) using the NCBI BLAST. 3) The glycan compositions provided by the paper were mapped to GlyTouCan Accession manually. 4) The source cell-line and mass-spectrometry data such as analyzer, chromatography, etc. were also extracted from the paper. 5) QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions and checked the validity of amino acid and glycosite position on the .fasta sequence in UniProtKB for that protein.", "prerequisite": [], "output_list": [] } ] }, "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": {} }, "io_domain": { "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv", "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.stat.csv", "filename": "hcv1a_proteoform_glycosylation_sites_literature.stat.csv" } } ], "input_subdomain": [ { "uri": { "filename": "glycosylation_sites_lit_23090970_s2.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/glycosylation_sites_lit_23090970_s2.csv" } }, { "uri": { "filename": "glycosylation_sites_lit_23090970_s5.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/glycosylation_sites_lit_23090970_s5.csv" } }, { "uri": { "filename": "glycosylation_sites_lit_24190977_s5.cs", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/glycosylation_sites_lit_24190977_s5.cs" } }, { "uri": { "filename": "glycosylation_sites_lit_x_sx.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/glycosylation_sites_lit_x_sx.csv" } }, { "uri": { "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/hcv1a_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "sarscov1_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/compiled/sarscov1_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/misc/n_sequon_info.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.7.1/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "https:/data.glygen.org/ln2downloads/cellosaurus/2024_09_05/cellosaurus.txt" } } ] }, "parametric_domain": [ { "value": "" } ], "error_domain": {}, "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": "Hepatitis C virus (isolate H77)", "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" } ] } } ] }