{
    "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..."
            ],
            [
                "...",
                "1 site, 1 C-..."
            ]
        ],
        "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"
            ],
            [
                "",
                "1 site, 1 C-linked glycan (1 site), 109 Free glycans (1 site), 479 N-linked glycans (1 site), 1 N-linked/o-linked glycan (1 site), 416 O-linked glycans (1 site)"
            ],
            [
                "Q2NKX8",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9WTR0",
                "1 site"
            ],
            [
                "Q8BKG4",
                "3 sites"
            ],
            [
                "P24387",
                "1 site, 6 N-linked glycans (1 site)"
            ],
            [
                "Q15818",
                "2 sites"
            ],
            [
                "P14625",
                "14 sites, 19 N-linked glycans (5 sites), 2 O-linked glycans (6 sites)"
            ],
            [
                "Q07444",
                "3 sites"
            ],
            [
                "P08120",
                "2 sites, 1 O-linked glycan (1 site)"
            ],
            [
                "Q6UWJ8",
                "4 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "Q9BY42",
                "2 sites, 1 O-linked glycan (2 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)"
            ],
            [
                "Q9HBK9",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P15260",
                "6 sites, 10 N-linked glycans (5 sites)"
            ],
            [
                "Q568Z4",
                "1 site"
            ],
            [
                "Q9BY27",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P28656",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q80TS8",
                "3 sites"
            ],
            [
                "P02765",
                "15 sites, 85 N-linked glycans (2 sites), 16 O-linked glycans (11 sites)"
            ],
            [
                "Q5QD23",
                "1 site"
            ],
            [
                "Q08406",
                "5 sites"
            ],
            [
                "A5D8T8",
                "2 sites, 1 O-linked glycan (1 site)"
            ],
            [
                "O14657",
                "5 sites, 4 N-linked glycans (1 site), 1 O-linked glycan (3 sites)"
            ],
            [
                "Q91XZ0",
                "4 sites, 1 N-linked glycan (1 site)"
            ],
            [
                "Q9UC06",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9Z137",
                "2 sites"
            ],
            [
                "Q96N67",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q13228",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q96L08",
                "1 site"
            ],
            [
                "P51859",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q8N394",
                "2 sites, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9BZW8",
                "8 sites"
            ],
            [
                "P24046",
                "3 sites"
            ],
            [
                "Q6AYF4",
                "10 sites"
            ],
            [
                "Q99MF4",
                "2 sites"
            ],
            [
                "Q6PFW1",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q8CGC7",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q16538",
                "1 site"
            ],
            [
                "F7F7A6",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9CR86",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P25100",
                "2 sites"
            ],
            [
                "Q6NX45",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q6UX71",
                "8 sites, 4 N-linked glycans (3 sites), 4 O-linked glycans (4 sites)"
            ],
            [
                "Q3UZZ4",
                "2 sites"
            ],
            [
                "O00418",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9NSC2",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "O95395",
                "1 site"
            ],
            [
                "Q63484",
                "2 sites"
            ],
            [
                "Q08211",
                "3 sites, 1 O-linked glycan (3 sites)"
            ],
            [
                "P41274",
                "3 sites"
            ],
            [
                "Q9Z139",
                "4 sites"
            ],
            [
                "A2RRP1",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P14901",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q6PFX9",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "O75019",
                "6 sites"
            ],
            [
                "P70663",
                "4 sites, 9 N-linked glycans (2 sites), 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)"
            ],
            [
                "Q9WTR5",
                "9 sites, 21 N-linked glycans (4 sites), 1 O-linked glycan (1 site)"
            ],
            [
                "Q8WXG6",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "Q96T37",
                "3 sites, 1 O-linked glycan (3 sites)"
            ],
            [
                "P46109",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9P0J7",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q01102",
                "5 sites"
            ],
            [
                "Q08945",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q09666",
                "85 sites, 3 O-linked glycans (85 sites)"
            ],
            [
                "O95671",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9JLV1",
                "4 sites, 1 O-linked glycan (4 sites)"
            ],
            [
                "A6NKC9",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "P08046",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q8TE12",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q9Z1F6",
                "1 site"
            ],
            [
                "Q8K596",
                "3 sites, 1 O-linked glycan (1 site)"
            ],
            [
                "O60765",
                "1 site, 1 O-linked glycan (1 site)"
            ],
            [
                "Q8NG95",
                "2 sites"
            ],
            [
                "Q9UBU7",
                "2 sites, 1 O-linked glycan (2 sites)"
            ],
            [
                "P97520",
                "1 site"
            ]
        ]
    },
    "readme": "Name\n   - GlyGen-UniProtKB Crossreferences Mapping\n\nVersion\n   - v-x.x.x\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], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.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/glygener/glygen-backend-integration/blob/master/dataset-maker/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: fruitfly_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_masterlist.csv\n      Name: fruitfly_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_protein_xref_refseq.csv\n      Name: fruitfly_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv\n      Name: fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      Name: fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: glycan_xref_pubchem.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/glycan_xref_pubchem.csv\n      Name: hcv1a_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_protein_masterlist.csv\n      Name: hcv1a_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_literature.csv\n      Name: hcv1a_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1a_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: hcv1b_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_protein_masterlist.csv\n      Name: hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/hcv1b_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: human_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_masterlist.csv\n      Name: human_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_protein_xref_refseq.csv\n      Name: human_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_glyconnect.csv\n      Name: human_proteoform_glycosylation_sites_gptwiki.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_gptwiki.csv\n      Name: human_proteoform_glycosylation_sites_harvard.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_harvard.csv\n      Name: human_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining.csv\n      Name: human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: human_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      Name: human_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_pdb.csv\n      Name: human_proteoform_glycosylation_sites_tyr_o_linked.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_tyr_o_linked.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_unicarbkb_glycomics_study.csv\n      Name: human_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/human_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: mouse_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_masterlist.csv\n      Name: mouse_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_protein_xref_refseq.csv\n      Name: mouse_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_glyconnect.csv\n      Name: mouse_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining.csv\n      Name: mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      Name: mouse_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_pdb.csv\n      Name: mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: mouse_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/mouse_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: rat_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_masterlist.csv\n      Name: rat_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_protein_xref_refseq.csv\n      Name: rat_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_glyconnect.csv\n      Name: rat_proteoform_glycosylation_sites_literature_mining.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining.csv\n      Name: rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_literature_mining_manually_verified.csv\n      Name: rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_o_glcnac_mcw.csv\n      Name: rat_proteoform_glycosylation_sites_pdb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_pdb.csv\n      Name: rat_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: rat_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/rat_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: sarscov1_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_masterlist.csv\n      Name: sarscov1_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_protein_xref_refseq.csv\n      Name: sarscov1_proteoform_glycosylation_sites_literature.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_literature.csv\n      Name: sarscov1_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov1_proteoform_glycosylation_sites_uniprotkb.csv\n      Name: sarscov2_protein_masterlist.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_masterlist.csv\n      Name: sarscov2_protein_xref_refseq.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_protein_xref_refseq.csv\n      Name: sarscov2_proteoform_glycosylation_sites_glyconnect.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_glyconnect.csv\n      Name: sarscov2_proteoform_glycosylation_sites_unicarbkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_unicarbkb.csv\n      Name: sarscov2_proteoform_glycosylation_sites_uniprotkb.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/sarscov2_proteoform_glycosylation_sites_uniprotkb.csv\n   Output Subdomain\n      Name: protein_glygen_uniprotkb_xref_mapping.tsv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv\n      Name: protein_glygen_uniprotkb_xref_mapping.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.stat.csv\n\nFields\n      Name: \"uniprotkb_primary_accession\"\n     Description: \"\"\n      Unique Values: \"21686\"\n      Name: \"additional_info\"\n     Description: \"\"\n      Unique Values: \"1551\"",
    "downloadurl": "/ln2data/releases/data/v-2.0.2/reviewed/protein_glygen_uniprotkb_xref_mapping.tsv"
}
