{
    "bcoid": "GLY_000316",
    "title": "Human Protein PTM Annotation (UniProtKB)",
    "description": "The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for ...",
    "filename": "human_protein_ptm_annotation_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": "Homo sapiens",
        "molecule": "Protein",
        "tags": "PTM annotation",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q8TBF5-1...",
                "20534510..."
            ],
            [
                "Q8TBF5-1...",
                "19349973..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "pmid..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "pmid"
                },
                {
                    "type": "string",
                    "label": "eco_id"
                },
                {
                    "type": "string",
                    "label": "ptm_annotation"
                }
            ],
            [
                "Q8TBF5-1",
                "20534510",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19349973",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16765900",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16335952",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16740002",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19159218",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "12754519",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "23803857",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "11336649",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "27152332",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "22106953",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "21478864",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "SIP8A89C514D119C6F4",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "1533657",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "23934049",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "2401370",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "26280335",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20145116",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "21827946",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20727575",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19563754",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "25500532",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "SIPF058BA6C1F60DFA4",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "8216207",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16859706",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19285951",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "12794138",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20879038",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "10970843",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "10671517",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "1458595",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19900540",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20470363",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "28739914",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20457942",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20006580",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "28489325",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "8576151",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "24548619",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "12077416",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "Q9DA48",
                "ECO_0000250",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "24753537",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "26542571",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "25282151",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "15557162",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "Q6SJQ0",
                "ECO_0000250",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20223752",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "3010309",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "3903517",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "3839290",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "12796776",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "26169044",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16678114",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "21886772",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "30140003",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16007225",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "12660814",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "1699669",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "21884936",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20008117",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "28067262",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "21964574",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16740594",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "30598546",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "30630874",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "10993067",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "24297919",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20015956",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "26095358",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "P19518",
                "ECO_0000250",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "15485681",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "11046064",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "11513746",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "2050678",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "P10499",
                "ECO_0000250",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "20210363",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "10698685",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "9174053",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "9480870",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "8985184",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "16752921",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "8546710",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "19136951",
                "ECO_0000269",
                "N-glycosylated."
            ],
            [
                "Q8TBF5-1",
                "Q8BMF8",
                "ECO_0000250",
                "N-glycosylated."
            ]
        ]
    },
    "readme": "Name\n   - Human Protein PTM Annotation (UniProtKB)\n\nVersion\n   - 1.5.27\n\nCreated on\n  - 2019-11-30T13:58:37.032006\n\nModified on\n   - 2020-04-11T11:28:33.003978\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu]\n\nAuthors\n   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The Human Protein PTM Annotation (UniProtKB) dataset contains human [taxid:9606] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen\n\nDescription Domain\n   Keywords\n   - ptm annotation\n   - glycosylation\n   - phosphorylation\n\n   Pipeline Steps\n   - Step-1: The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format\n\nExecution Domain\n   Scripts   - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-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: uniprot-proteome-homo-sapiens.nt\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/uniprot-proteome-homo-sapiens.nt\n      Name: human_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n   Output Subdomain\n      Name: human_protein_ptm_annotation_uniprotkb.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.csv\n      Name: human_protein_ptm_annotation_uniprotkb.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_ptm_annotation_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"Accession assigned to the protein isoform chosen to be the canonical sequence to which all positional annotation refers in UniProtKB database\"\n      Unique Values: \"4752\"\n      Name: \"eco_id\"\n     Description: \"Evidence & Conclusion Ontology (ECO) identifier\"\n      Unique Values: \"8\"\n      Name: \"pmid\"\n     Description: \"NCBI PubMed database Identifier\"\n      Unique Values: \"6704\"\n      Name: \"ptm_annotation\"\n     Description: \"The Post Translational Modifiaction (PTM) annotation in UniProtKB that provides more context and description about the PTMs occuring on a proein\"\n      Unique Values: \"5297\"",
    "downloadurl": "/ln2data/releases/data/v-1.5.27/reviewed/human_protein_ptm_annotation_uniprotkb.csv"
}
