{ "object_id": "https://biocomputeobject.org/GLY_000499/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": "", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "GlyGen-PubChem Protein Crossreferences", "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": "GlyGen-PubChem Protein Crossreferences Mapping", "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": "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" }, { "affiliation": "", "contribution": [ "contributedBy" ], "name": "Not Applicable", "email": "" } ], "created": "2020-06-04T09:25:12.224023", "modified": "2022-01-13T17:10:17.085590", "version": "v-2.0.2" }, "description_domain": { "keywords": [ "PubChem Protein", "GlyGen", "crossreferences", "human", "mouse", "rat", "hcv1a", "hcv1b", "sarscov1", "sarscov2", "NCBI RefSeq" ], "pipeline_steps": [ { "name": "make-species-agnostic-dataset.py", "step_number": 1, "version": "", "input_list": [ { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv", "filename": "human_proteoform_glycosylation_sites_glyconnect.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv", "filename": "http://data.glygen.org/ln2data/releases/data/v-1.12.3/reviewed/" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv", "filename": "human_proteoform_glycosylation_sites_harvard.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv", "filename": "human_proteoform_glycosylation_sites_literature.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv", "filename": "human_proteoform_glycosylation_sites_pdb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv", "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv", "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv", "filename": "mouse_proteoform_glycosylation_sites_pdb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv", "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv", "filename": "rat_proteoform_glycosylation_sites_pdb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_citations_unicarbkb_literature.csv", "filename": "sarscov2_proteoform_citations_unicarbkb_literature.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv", "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv", "filename": "human_protein_xref_refseq.csv" }, { "uri": "mouse_protein_xref_refseq.csv", "filename": "mouse_protein_xref_refseq.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv", "filename": "rat_protein_xref_refseq.csv" }, { "uri": "http://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv", "filename": "sarscov1_protein_xref_refseq.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv", "filename": "protein_glygen_uniprotkb_xref_mapping.tsv" } ], "prerequisite": [], "description": "The script loads the GlyGen's UniProtKB protein accessions for human, mouse, rat, hcv1a, hcv1b, sarscov1 and sarscov2 species and maps it to the refseq accessions and adds the corresponding glycosylation annotation to extract it into a csv dataset file. " } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [] }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "usability_domain": [ "The GlyGen-PubChem Protein Cross-references dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], mouse [taxid:10090], rat [taxid:10116], hcv1a [taxid:11108], hcv1b [taxid:11116], sarscov1 [taxid:694009] and sarscov2 [taxid:2697049] glycoproteins for the purpose of PubChem Protein to GlyGen cross-references. In the dataset, the UniProtKB glycoprotein accessions are mapped to the RefSeq accessions and glycosylation annotation corresponding to glycoprotein have been added. The glycosylation annotation provides information about total (N,O,S,C) glycosylation sites followed by (if available) reported N-glycans and/or reported O-glycans with the number of sites. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, NCBI RefSeq and GlyGen. " ], "etag": "011bb2f8551e5f52a7246831eb298d56", "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "fruitfly_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv" } }, { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv" } }, { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } }, { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "glycan_xref_pubchem.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv" } }, { "uri": { "filename": "hcv1a_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv" } }, { "uri": { "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "hcv1b_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv" } }, { "uri": { "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "human_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv" } }, { "uri": { "filename": "human_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_gptwiki.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_harvard.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_literature_mining.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_pdb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_tyr_o_linked.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_unicarbkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv" } }, { "uri": { "filename": "human_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "mouse_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv" } }, { "uri": { "filename": "mouse_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_literature_mining.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_pdb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "uri": { "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "rat_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv" } }, { "uri": { "filename": "rat_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_literature_mining.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_pdb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "uri": { "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "sarscov1_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv" } }, { "uri": { "filename": "sarscov1_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv" } }, { "uri": { "filename": "sarscov1_proteoform_glycosylation_sites_literature.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv" } }, { "uri": { "filename": "sarscov1_proteoform_glycosylation_sites_unicarbkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "uri": { "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "uri": { "filename": "sarscov2_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv" } }, { "uri": { "filename": "sarscov2_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv" } }, { "uri": { "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv" } }, { "uri": { "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv" } }, { "uri": { "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pubchem_xref_mapping.csv", "filename": "protein_glygen_pubchem_xref_mapping.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_pubchem_xref_mapping.stat.csv", "filename": "protein_glygen_pubchem_xref_mapping.stat.csv" } } ] } }