{
    "bcoid": "GLY_000404",
    "title": "Human UniProtKB Xref Pharos",
    "description": "The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...",
    "filename": "human_protein_xref_pharos.csv",
    "filetype": "csv",
    "categories": {
        "species": [
            "Homo sapiens"
        ],
        "molecule": [
            "Protein"
        ],
        "tags": [
            "Pharos cross-references"
        ],
        "file_type": [
            "csv"
        ],
        "status": [
            "Reviewed"
        ],
        "scope": [
            "internal"
        ]
    },
    "minitable": {
        "content": [
            [
                "P30613-1...",
                "protein_xref..."
            ],
            [
                "Q96J66-1...",
                "protein_xref..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "xref_key..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                },
                {
                    "type": "string",
                    "label": "xref_label"
                }
            ],
            [
                "P30613-1",
                "protein_xref_pharos",
                "P30613",
                "Pyruvate kinase PKLR"
            ],
            [
                "Q96J66-1",
                "protein_xref_pharos",
                "Q96J66",
                "ATP-binding cassette sub-family C member 11"
            ],
            [
                "Q96J65-1",
                "protein_xref_pharos",
                "Q96J65",
                "Multidrug resistance-associated protein 9"
            ],
            [
                "P40424-1",
                "protein_xref_pharos",
                "P40424",
                "Pre-B-cell leukemia transcription factor 1"
            ],
            [
                "P40425-1",
                "protein_xref_pharos",
                "P40425",
                "Pre-B-cell leukemia transcription factor 2"
            ],
            [
                "P40426-1",
                "protein_xref_pharos",
                "P40426",
                "Pre-B-cell leukemia transcription factor 3"
            ],
            [
                "P40429-1",
                "protein_xref_pharos",
                "P40429",
                "60S ribosomal protein L13a"
            ],
            [
                "Q9H2I8-1",
                "protein_xref_pharos",
                "Q9H2I8",
                "Leucine-rich melanocyte differentiation-associated protein"
            ],
            [
                "H0YL14-1",
                "protein_xref_pharos",
                "H0YL14",
                "Transmembrane protein 250"
            ],
            [
                "Q9BXR3-1",
                "protein_xref_pharos",
                "Q69384",
                "Endogenous retrovirus group K member 6 Env polyprotein"
            ],
            [
                "Q9BXR3-1",
                "protein_xref_pharos",
                "Q69383",
                "Endogenous retrovirus group K member 6 Rec protein"
            ],
            [
                "Q5VVP1-1",
                "protein_xref_pharos",
                "Q5VVP1",
                "Spermatogenesis-associated protein 31A6"
            ],
            [
                "Q8N865-1",
                "protein_xref_pharos",
                "Q8N865",
                "Uncharacterized protein C7orf31"
            ],
            [
                "A6NIR3-1",
                "protein_xref_pharos",
                "A6NIR3",
                "Arf-GAP with GTPase, ANK repeat and PH domain-containing protein 5"
            ],
            [
                "Q86VY4-1",
                "protein_xref_pharos",
                "Q86VY4",
                "Testis-specific Y-encoded-like protein 5"
            ],
            [
                "Q86VY9-1",
                "protein_xref_pharos",
                "Q86VY9",
                "Transmembrane protein 200A"
            ],
            [
                "Q9Y5S9-1",
                "protein_xref_pharos",
                "Q9Y5S9",
                "RNA-binding protein 8A"
            ],
            [
                "P19075-1",
                "protein_xref_pharos",
                "P19075",
                "Tetraspanin-8"
            ],
            [
                "Q99519-1",
                "protein_xref_pharos",
                "Q99519",
                "Sialidase-1"
            ],
            [
                "O15417-1",
                "protein_xref_pharos",
                "O15417",
                "Trinucleotide repeat-containing gene 18 protein"
            ],
            [
                "Q96RU7-1",
                "protein_xref_pharos",
                "Q96RU7",
                "Tribbles homolog 3"
            ],
            [
                "Q96RU3-1",
                "protein_xref_pharos",
                "Q96RU3",
                "Formin-binding protein 1"
            ],
            [
                "Q96RU2-1",
                "protein_xref_pharos",
                "Q96RU2",
                "Ubiquitin carboxyl-terminal hydrolase 28"
            ],
            [
                "Q96RU8-1",
                "protein_xref_pharos",
                "Q96RU8",
                "Tribbles homolog 1"
            ],
            [
                "Q6ZRV3-1",
                "protein_xref_pharos",
                "Q6ZRV3",
                "Putative uncharacterized protein encoded by LINC00696"
            ],
            [
                "Q6ZRV2-1",
                "protein_xref_pharos",
                "Q6ZRV2",
                "Protein FAM83H"
            ],
            [
                "P16520-1",
                "protein_xref_pharos",
                "P16520",
                "Guanine nucleotide-binding protein G(I)/G(S)/G(T) subunit beta-3"
            ],
            [
                "Q8NCJ5-1",
                "protein_xref_pharos",
                "Q8NCJ5",
                "SPRY domain-containing protein 3"
            ],
            [
                "Q9Y296-1",
                "protein_xref_pharos",
                "Q9Y296",
                "Trafficking protein particle complex subunit 4"
            ],
            [
                "Q9Y297-1",
                "protein_xref_pharos",
                "Q9Y297",
                "F-box/WD repeat-containing protein 1A"
            ],
            [
                "Q9Y294-1",
                "protein_xref_pharos",
                "Q9Y294",
                "Histone chaperone ASF1A"
            ],
            [
                "Q9Y295-1",
                "protein_xref_pharos",
                "Q9Y295",
                "Developmentally-regulated GTP-binding protein 1"
            ],
            [
                "Q6ICB4-1",
                "protein_xref_pharos",
                "Q6ICB4",
                "Sesquipedalian-2"
            ],
            [
                "Q6ICB0-1",
                "protein_xref_pharos",
                "Q6ICB0",
                "Desumoylating isopeptidase 1"
            ],
            [
                "P17693-1",
                "protein_xref_pharos",
                "P17693",
                "HLA class I histocompatibility antigen, alpha chain G"
            ],
            [
                "O00507-1",
                "protein_xref_pharos",
                "O00507",
                "Probable ubiquitin carboxyl-terminal hydrolase FAF-Y"
            ],
            [
                "O00505-1",
                "protein_xref_pharos",
                "O00505",
                "Importin subunit alpha-4"
            ],
            [
                "O00501-1",
                "protein_xref_pharos",
                "O00501",
                "Claudin-5"
            ],
            [
                "Q8IYD2-1",
                "protein_xref_pharos",
                "Q8IYD2",
                "Kelch domain-containing protein 8A"
            ],
            [
                "Q8IYD1-1",
                "protein_xref_pharos",
                "Q8IYD1",
                "Eukaryotic peptide chain release factor GTP-binding subunit ERF3B"
            ],
            [
                "Q8IYD9-1",
                "protein_xref_pharos",
                "Q8IYD9",
                "Lung adenoma susceptibility protein 2"
            ],
            [
                "Q8IYD8-1",
                "protein_xref_pharos",
                "Q8IYD8",
                "Fanconi anemia group M protein"
            ],
            [
                "Q9H0H3-1",
                "protein_xref_pharos",
                "Q9H0H3",
                "Kelch-like protein 25"
            ],
            [
                "Q8IVD9-1",
                "protein_xref_pharos",
                "Q8IVD9",
                "NudC domain-containing protein 3"
            ],
            [
                "P24903-1",
                "protein_xref_pharos",
                "P24903",
                "Cytochrome P450 2F1"
            ],
            [
                "Q5M9N0-1",
                "protein_xref_pharos",
                "Q5M9N0",
                "Coiled-coil domain-containing protein 158"
            ],
            [
                "Q8N7C0-1",
                "protein_xref_pharos",
                "Q8N7C0",
                "Leucine-rich repeat-containing protein 52"
            ],
            [
                "Q9NV23-1",
                "protein_xref_pharos",
                "Q9NV23",
                "S-acyl fatty acid synthase thioesterase, medium chain"
            ],
            [
                "Q9NV29-1",
                "protein_xref_pharos",
                "Q9NV29",
                "Transmembrane protein 100"
            ],
            [
                "Q2M238-1",
                "protein_xref_pharos",
                "Q2M238",
                "Putative RRN3-like protein RRN3P1"
            ],
            [
                "Q9UQ26-6",
                "protein_xref_pharos",
                "Q9UQ26",
                "Regulating synaptic membrane exocytosis protein 2"
            ],
            [
                "P0C7I6-2",
                "protein_xref_pharos",
                "P0C7I6",
                "Coiled-coil domain-containing protein 159"
            ],
            [
                "P0C7I0-1",
                "protein_xref_pharos",
                "P0C7I0",
                "Inactive ubiquitin carboxyl-terminal hydrolase 17-like protein 8"
            ],
            [
                "Q5HYW2-1",
                "protein_xref_pharos",
                "Q5HYW2",
                "NHS-like protein 2"
            ],
            [
                "Q5HYW3-1",
                "protein_xref_pharos",
                "Q5HYW3",
                "Retrotransposon Gag-like protein 5"
            ],
            [
                "Q9Y5J9-1",
                "protein_xref_pharos",
                "Q9Y5J9",
                "Mitochondrial import inner membrane translocase subunit Tim8 B"
            ],
            [
                "P45984-1",
                "protein_xref_pharos",
                "P45984",
                "Mitogen-activated protein kinase 9"
            ],
            [
                "Q7Z5G4-1",
                "protein_xref_pharos",
                "Q7Z5G4",
                "Golgin subfamily A member 7"
            ],
            [
                "Q9Y5J6-1",
                "protein_xref_pharos",
                "Q9Y5J6",
                "Mitochondrial import inner membrane translocase subunit Tim10 B"
            ],
            [
                "Q9Y5J7-1",
                "protein_xref_pharos",
                "Q9Y5J7",
                "Mitochondrial import inner membrane translocase subunit Tim9"
            ],
            [
                "P27469-1",
                "protein_xref_pharos",
                "P27469",
                "G0/G1 switch protein 2"
            ],
            [
                "Q9H239-1",
                "protein_xref_pharos",
                "Q9H239",
                "Matrix metalloproteinase-28"
            ],
            [
                "Q9H237-1",
                "protein_xref_pharos",
                "Q9H237",
                "Protein-serine O-palmitoleoyltransferase porcupine"
            ],
            [
                "Q8NEQ5-1",
                "protein_xref_pharos",
                "Q8NEQ5",
                "Transmembrane protein C1orf162"
            ],
            [
                "Q8NEQ6-1",
                "protein_xref_pharos",
                "Q8NEQ6",
                "Steroid receptor-associated and regulated protein"
            ],
            [
                "Q8N9X3-1",
                "protein_xref_pharos",
                "Q8N9X3",
                "Putative uncharacterized protein encoded by LINC01356"
            ],
            [
                "Q8N9X5-1",
                "protein_xref_pharos",
                "Q8N9X5",
                "Transmembrane protein 75"
            ],
            [
                "A8MVJ9-1",
                "protein_xref_pharos",
                "A8MVJ9",
                "Putative histone PARylation factor 1-like"
            ],
            [
                "Q9H7J1-1",
                "protein_xref_pharos",
                "Q9H7J1",
                "Protein phosphatase 1 regulatory subunit 3E"
            ],
            [
                "O60830-1",
                "protein_xref_pharos",
                "O60830",
                "Mitochondrial import inner membrane translocase subunit Tim17-B"
            ],
            [
                "O60831-1",
                "protein_xref_pharos",
                "O60831",
                "PRA1 family protein 2"
            ],
            [
                "O60832-1",
                "protein_xref_pharos",
                "O60832",
                "H/ACA ribonucleoprotein complex subunit 4"
            ],
            [
                "O14579-1",
                "protein_xref_pharos",
                "O14579",
                "Coatomer subunit epsilon"
            ],
            [
                "Q7LDG7-1",
                "protein_xref_pharos",
                "Q7LDG7",
                "RAS guanyl-releasing protein 2"
            ],
            [
                "P17900-1",
                "protein_xref_pharos",
                "P17900",
                "Ganglioside GM2 activator"
            ],
            [
                "Q9NPI9-1",
                "protein_xref_pharos",
                "Q9NPI9",
                "Inward rectifier potassium channel 16"
            ],
            [
                "Q9NPI8-1",
                "protein_xref_pharos",
                "Q9NPI8",
                "Fanconi anemia group F protein"
            ],
            [
                "Q9NPI5-1",
                "protein_xref_pharos",
                "Q9NPI5",
                "Nicotinamide riboside kinase 2"
            ],
            [
                "Q9NPI7-1",
                "protein_xref_pharos",
                "Q9NPI7",
                "Lysine-rich coiled-coil protein 1"
            ],
            [
                "Q9NPI6-1",
                "protein_xref_pharos",
                "Q9NPI6",
                "mRNA-decapping enzyme 1A"
            ],
            [
                "Q9NPI1-1",
                "protein_xref_pharos",
                "Q9NPI1",
                "Bromodomain-containing protein 7"
            ],
            [
                "Q9NPI0-1",
                "protein_xref_pharos",
                "Q9NPI0",
                "Transmembrane protein 138"
            ],
            [
                "Q05397-1",
                "protein_xref_pharos",
                "Q05397",
                "Focal adhesion kinase 1"
            ],
            [
                "Q96LT9-1",
                "protein_xref_pharos",
                "Q96LT9",
                "RNA-binding protein 40"
            ]
        ]
    },
    "readme": "Name\n   - Human UniProtKB Xref Pharos\n\nVersion\n   - v-2.1.1\n\nCreated on\n  - 2020-03-20T14:14:17.733990\n\nModified on\n   - 2022-09-26T09:05:56.452067\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@email.gwu.edu]\n\nAuthors\n   - Tudor I Oprea [TOprea@salud.unm.edu], Paul Barrett [paul.barrett@nih.gov], Ajay Pillai [ajay.pillai3@nih.gov]\n\nChecksum\n   - \n\nUsability Domain\n   - The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen\n   - Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health.\n   - The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases\n   - Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072\n   - https://pharos.nih.gov/about\n\nDescription Domain\n   Keywords\n   - Pharos\n   - Illuminating the Druggable Genome\n   - drug-targeted protein families\n   - G-protein-coupled receptors (GPCRs)\n   - ion channels (ICs)\n   - kinases\n\n   Pipeline Steps\n   - Step-1: The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. The accessions that are not mapped are logged in the log file. \n\nExecution Domain\n   Scripts   - https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/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: batch.10.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.10.json\n      Name: batch.11.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.11.json\n      Name: batch.12.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.12.json\n      Name: batch.13.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.13.json\n      Name: batch.14.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.14.json\n      Name: batch.15.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.15.json\n      Name: batch.16.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.16.json\n      Name: batch.17.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.17.json\n      Name: batch.18.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.18.json\n      Name: batch.19.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.19.json\n      Name: batch.1.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.1.json\n      Name: batch.20.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.20.json\n      Name: batch.21.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.21.json\n      Name: batch.2.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.2.json\n      Name: batch.3.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.3.json\n      Name: batch.4.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.4.json\n      Name: batch.5.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.5.json\n      Name: batch.6.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.6.json\n      Name: batch.7.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.7.json\n      Name: batch.8.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.8.json\n      Name: batch.9.json\n      URI: /data/shared/glyds/downloads/pharos/03_2020/batch.9.json\n   Output Subdomain\n      Name: human_protein_xref_pharos.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pharos.csv\n      Name: human_protein_xref_pharos.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_pharos.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"19949\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"20021\"\n      Name: \"xref_label\"\n     Description: \"Label/Name associated with x-ref\"\n      Unique Values: \"20018\"",
    "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/human_protein_xref_pharos.csv"
}
