{
    "object_id": "https://biocomputeobject.org/GLY_000410/v-2.3.1",
    "spec_version": "1.3.0",
    "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": "Protein",
                        "category_name": "molecule"
                    },
                    {
                        "category_value": "GlyGen-UniProtKB Crossreferences",
                        "category_name": "tag"
                    },
                    {
                        "category_value": "tsv",
                        "category_name": "file_type"
                    },
                    {
                        "category_value": "Reviewed",
                        "category_name": "status"
                    },
                    {
                        "category_value": "internal",
                        "category_name": "scope"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Homo sapiens"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Rattus norvegicus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Mus musculus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Drosophila melanogaster"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Saccharomyces cerevisiae S288C"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Hepatitis C virus (isolate Japanese)"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome coronavirus 2"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Severe acute respiratory syndrome-related coronavirus"
                    },
                    {
                        "category_name": "species",
                        "category_value": "Hepatitis C virus (isolate H)"
                    }
                ]
            }
        }
    ],
    "provenance_domain": {
        "license": "\"https://creativecommons.org/licenses/by/4.0/\"",
        "name": "GlyGen-UniProtKB 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": "Robel Kahsay",
                "email": "rykahsay@gwu.edu"
            },
            {
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "name": "Karina Martinez",
                "email": "karinamartinez@gwu.edu"
            },
            {
                "name": "Jingyue Wu",
                "affiliation": "The George Washington University",
                "contribution": [
                    "createdBy"
                ],
                "email": "jingyue.wu@email.gwu.edu"
            }
        ],
        "created": "2020-04-01T12:08:42.022917",
        "modified": "2022-09-26T09:05:56.496595",
        "version": "v-2.3.1"
    },
    "description_domain": {
        "keywords": [
            "UniProtKB",
            "GlyGen",
            "crossreferences",
            "human",
            "mouse",
            "rat"
        ],
        "pipeline_steps": [
            {
                "name": "make-species-agnostic-dataset.py",
                "step_number": 1,
                "version": "",
                "input_list": [],
                "output_list": [],
                "prerequisite": [],
                "description": "The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file"
            }
        ]
    },
    "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-species-agnostic-dataset.py",
                    "filename": "make-species-agnostic-dataset.py"
                }
            }
        ]
    },
    "parametric_domain": [
        {
            "step": "",
            "param": "",
            "value": ""
        }
    ],
    "usability_domain": [
        "The GlyGen-UniProtKB Crossreferences 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 UniProtKB to GlyGen crossreferences. In the dataset, the UniProtKB glycoprotein accessions have corresponding glycosylation annotation present in the datasets. 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": "b8ebf6902d4b11be01a9dbc4bf763bff",
    "io_domain": {
        "input_subdomain": [
            {
                "uri": {
                    "filename": "dicty_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "dicty_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "fruitfly_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "glycan_xref_pubchem.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/glycan_xref_pubchem.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1a_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_proteoform_glycosylation_sites_literature.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1a_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1b_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "hcv1b_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_gptwiki.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_harvard.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_harvard.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_literature.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/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-2.3.1/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_oglcnac_atlas.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_atlas.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_oglcnac_mcw.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_oglcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_o_gluc.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_proteoform_glycosylation_sites_o_gluc.csv"
                }
            },
            {
                "uri": {
                    "filename": "human_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/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-2.3.1/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-2.3.1/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-2.3.1/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-2.3.1/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_protein_xref_mgi.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_xref_mgi.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/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-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_atlas.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_oglcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "mouse_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_literature_mining.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/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-2.3.1/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_oglcnac_atlas.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_atlas.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_oglcnac_mcw.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_oglcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_pdb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_pdb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv"
                }
            },
            {
                "uri": {
                    "filename": "rat_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_literature.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov1_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_unicarbkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "sarscov2_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_protein_masterlist.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_masterlist.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_protein_xref_refseq.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_refseq.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_glyconnect.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_glyconnect.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_atlas.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_oglcnac_mcw.csv"
                }
            },
            {
                "uri": {
                    "filename": "yeast_proteoform_glycosylation_sites_uniprotkb.csv",
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_proteoform_glycosylation_sites_uniprotkb.csv"
                }
            }
        ],
        "output_subdomain": [
            {
                "mediatype": "tsv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv",
                    "filename": "protein_glygen_uniprotkb_xref_mapping.tsv"
                }
            },
            {
                "mediatype": "csv",
                "uri": {
                    "uri": "https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv",
                    "filename": "protein_glygen_uniprotkb_xref_mapping.stat.csv"
                }
            }
        ]
    },
    "error_domain": {
        "empirical_error": {},
        "algorithmic_error": {}
    }
}
