{
    "bcoid": "GLY_000410",
    "title": "GlyGen-UniProtKB Crossreferences Mapping",
    "description": "The GlyGen-UniProtKB Crossreferences dataset contains UniProtKB glycoprotein accessions for human [taxid:9606], ...",
    "filename": "protein_glygen_uniprotkb_xref_mapping.tsv",
    "filetype": "tsv",
    "categories": {
        "molecule": "Protein",
        "tags": "GlyGen-UniProtKB Crossreferences",
        "file_type": "tsv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q9P1W8...",
                "4 sites..."
            ],
            [
                "Q2NKX8...",
                "1 site, 1 O-..."
            ]
        ],
        "headers": [
            "uniprotkb_pr...",
            "additional_i..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_primary_accession"
                },
                {
                    "type": "string",
                    "label": "additional_info"
                }
            ],
            [
                "Q9P1W8",
                "4 sites"
            ],
            [
                "Q2NKX8",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P24387",
                "1 site, 6 N-linked glycans (1 site)"
            ],
            [
                "Q8N3G9",
                "3 sites"
            ],
            [
                "P14625",
                "11 sites, 12 N-linked glycans (5 sites), 1 O-linked glycan (3 sites)"
            ],
            [
                "Q07444",
                "3 sites"
            ],
            [
                "P01587",
                "4 sites"
            ],
            [
                "Q8TE77",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9BYT8",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q15067",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P15260",
                "5 sites, 6 N-linked glycans (4 sites)"
            ],
            [
                "P22272",
                "4 sites"
            ],
            [
                "Q80TS8",
                "3 sites"
            ],
            [
                "Q5QD23",
                "1 site"
            ],
            [
                "Q08406",
                "5 sites"
            ],
            [
                "A5D8T8",
                "2 sites, 1 O-linked glycan (1 site)"
            ],
            [
                "O14657",
                "2 sites, 4 N-linked glycans (1 site)"
            ],
            [
                "Q91XZ0",
                "4 sites, 1 N-linked glycan (1 site)"
            ],
            [
                "Q9Z137",
                "2 sites"
            ],
            [
                "Q13228",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q96L08",
                "1 site"
            ],
            [
                "Q96LB9",
                "1 site"
            ],
            [
                "Q8N394",
                "1 site"
            ],
            [
                "Q9BZW8",
                "8 sites"
            ],
            [
                "P24046",
                "3 sites"
            ],
            [
                "Q6AYF4",
                "10 sites"
            ],
            [
                "Q99MF4",
                "2 sites"
            ],
            [
                "Q70EX6",
                "2 sites"
            ],
            [
                "Q16538",
                "1 site"
            ],
            [
                "P25100",
                "2 sites"
            ],
            [
                "Q76JU9",
                "1 site"
            ],
            [
                "P13284",
                "5 sites, 18 N-linked glycans (2 sites)"
            ],
            [
                "Q3UZZ4",
                "2 sites"
            ],
            [
                "O00418",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P47801",
                "3 sites"
            ],
            [
                "Q63484",
                "2 sites"
            ],
            [
                "Q08211",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "P41274",
                "3 sites"
            ],
            [
                "Q9Z139",
                "4 sites"
            ],
            [
                "P01881",
                "5 sites"
            ],
            [
                "O75019",
                "6 sites"
            ],
            [
                "Q96AT9",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q6P996",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "Q69YH5",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9UPC5",
                "5 sites"
            ],
            [
                "A6NHS7",
                "3 sites"
            ],
            [
                "Q8NFQ6",
                "10 sites"
            ],
            [
                "Q16630",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q08357",
                "1 site"
            ],
            [
                "Q8WXG6",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "Q96T37",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9P0J7",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q09666",
                "23 sites, 2 O-linked glycans (23 sites)"
            ],
            [
                "Q8TE12",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "O88909",
                "1 site"
            ],
            [
                "Q8K596",
                "2 sites"
            ],
            [
                "O60765",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q8NG95",
                "2 sites"
            ],
            [
                "Q7M758",
                "10 sites"
            ],
            [
                "P51868",
                "1 site"
            ],
            [
                "Q8VCH9",
                "2 sites"
            ],
            [
                "P69478",
                "4 sites"
            ],
            [
                "Q96IX5",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9EPK6",
                "2 sites, 3 N-linked glycans (1 site)"
            ],
            [
                "Q9UBS5",
                "7 sites"
            ],
            [
                "P07759",
                "4 sites, 5 N-linked glycans (2 sites)"
            ],
            [
                "Q16762",
                "1 site"
            ],
            [
                "P11831",
                "15 sites, 1 O-linked glycan (12 sites)"
            ],
            [
                "P49771",
                "2 sites"
            ],
            [
                "P0DMU3",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "O60359",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9H7Y0",
                "1 site"
            ],
            [
                "Q9BZX2",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P22771",
                "2 sites"
            ],
            [
                "Q96S94",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P97707",
                "2 sites"
            ],
            [
                "Q3TAS6",
                "1 site, 6 N-linked glycans (1 site)"
            ],
            [
                "P51674",
                "2 sites"
            ],
            [
                "Q96EM0",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P47914",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q96NH3",
                "1 site"
            ],
            [
                "A2RUS2",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "Q6UVK1",
                "18 sites, 2 N-linked glycans (1 site), 3 O-linked glycans (2 sites)"
            ],
            [
                "Q3U497",
                "1 site"
            ]
        ]
    },
    "readme": "Name\n   - GlyGen-UniProtKB Crossreferences Mapping\n\nVersion\n   - 1.8.25\n\nCreated on\n  - 2020-04-01T12:08:42.022917\n\nModified on\n   - 2020-06-04T13:32:16.780973\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu]\n\nAuthors\n   - \n\nChecksum\n   - \n\nUsability Domain\n   - 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\n\nDescription Domain\n   Keywords\n   - UniProtKB\n   - GlyGen\n   - crossreferences\n   - human\n   - mouse\n   - rat\n\n   Pipeline Steps\n   - Step-1: The script loads the GlyGen's UniProtKB protein accessions for human, mouse and rat species and extracts it into a csv dataset file\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-species-agnostic-dataset.py\n\n\n   Software Prerequisites\n      Name: Python\n      Version: 2.7.5\n      URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n   Input Subdomain\n      Name: human_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/human_protein_masterlist.csv\n      Name: rat_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/mouse_protein_masterlist.csv\n      Name: rat_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/rat_protein_masterlist.csv\n   Output Subdomain\n      Name: protein_glygen_uniprotkb_xref_mapping.tsv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv\n      Name: protein_glygen_uniprotkb_xref_mapping.stat.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.25/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv\n\nFields\n      Name: \"src_xref_key\"\n     Description: \"Source Xref  key\"\n      Unique Values: \"1\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"119\"\n      Name: \"title\"\n     Description: \"Title of the published article in the journal\"\n      Unique Values: \"119\"\n      Name: \"src_xref_id\"\n     Description: \"Source X-ref ID\"\n      Unique Values: \"120\"\n      Name: \"journal_name\"\n     Description: \"The name of the journal in which the article is published\"\n      Unique Values: \"49\"\n      Name: \"authors\"\n     Description: \"NA\"\n      Unique Values: \"118\"\n      Name: \"publication_date\"\n     Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n      Unique Values: \"117\"\n      Name: \"glytoucan_ac\"\n     Description: \"Unique accession assigned to the registered glycan structure in GlyTouCan database\"\n      Unique Values: \"115\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"",
    "downloadurl": "/ln2data/releases/data/v-1.8.25/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv"
}
