{
    "bcoid": "GLY_000229",
    "title": "Rat UniProtKB Xref OMA",
    "description": "The Rat UniProtKB Xref OMA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...",
    "filename": "rat_protein_xref_oma.csv",
    "filetype": "csv",
    "categories": {
        "species": "Rattus norvegicus",
        "molecule": "Protein",
        "tags": "Oma cross-references",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "Q5RJK9-1...",
                "protein_xref..."
            ],
            [
                "Q5RJK8-1...",
                "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"
                }
            ],
            [
                "Q5RJK9-1",
                "protein_xref_oma",
                "RGKDHAK",
                ""
            ],
            [
                "Q5RJK8-1",
                "protein_xref_oma",
                "KFDCSAM",
                ""
            ],
            [
                "D3ZZY8-1",
                "protein_xref_oma",
                "PAIIRIS",
                ""
            ],
            [
                "D3ZG10-1",
                "protein_xref_oma",
                "AKFDFMA",
                ""
            ],
            [
                "D3ZB44-1",
                "protein_xref_oma",
                "PRVIIQL",
                ""
            ],
            [
                "D3ZZY2-1",
                "protein_xref_oma",
                "HRNTSKW",
                ""
            ],
            [
                "Q5RJK0-1",
                "protein_xref_oma",
                "VYAFCTM",
                ""
            ],
            [
                "Q5RJK3-1",
                "protein_xref_oma",
                "ALQAWFP",
                ""
            ],
            [
                "P30349-1",
                "protein_xref_oma",
                "NSNFRMK",
                ""
            ],
            [
                "Q5RJK5-1",
                "protein_xref_oma",
                "KWQGTDE",
                ""
            ],
            [
                "D3ZB48-1",
                "protein_xref_oma",
                "LEFNNHA",
                ""
            ],
            [
                "Q5RJK6-1",
                "protein_xref_oma",
                "TIKHEVG",
                ""
            ],
            [
                "A0A0G2K0H3-1",
                "protein_xref_oma",
                "TNCANGH",
                ""
            ],
            [
                "Q5XIH0-1",
                "protein_xref_oma",
                "MAGNDKQ",
                ""
            ],
            [
                "Q6MG51-1",
                "protein_xref_oma",
                "WLPRPWG",
                ""
            ],
            [
                "F1M2W7-1",
                "protein_xref_oma",
                "RHVACQS",
                ""
            ],
            [
                "Q6MG53-1",
                "protein_xref_oma",
                "CMVISIY",
                ""
            ],
            [
                "D4AAV0-1",
                "protein_xref_oma",
                "IQETFPF",
                ""
            ],
            [
                "Q4KLP0-1",
                "protein_xref_oma",
                "GMAIDNP",
                ""
            ],
            [
                "M0RAP0-1",
                "protein_xref_oma",
                "ATNMRIY",
                ""
            ],
            [
                "M0RAP1-1",
                "protein_xref_oma",
                "GPFDEQI",
                ""
            ],
            [
                "M0RAP6-1",
                "protein_xref_oma",
                "KSHIDDC",
                ""
            ],
            [
                "A0A0G2JVG5-1",
                "protein_xref_oma",
                "QWKEQQW",
                ""
            ],
            [
                "A0A0G2JVG6-1",
                "protein_xref_oma",
                "HIYTINL",
                ""
            ],
            [
                "M0RAP5-1",
                "protein_xref_oma",
                "RNGNVMA",
                ""
            ],
            [
                "A0A0G2JVG8-1",
                "protein_xref_oma",
                "PEDQAVY",
                ""
            ],
            [
                "F1M1W4-1",
                "protein_xref_oma",
                "NMTENMA",
                ""
            ],
            [
                "M0R5G7-1",
                "protein_xref_oma",
                "RYAYSTY",
                ""
            ],
            [
                "Q9WUD9-1",
                "protein_xref_oma",
                "XIASGMA",
                ""
            ],
            [
                "M0R5G5-1",
                "protein_xref_oma",
                "HLEHSFT",
                ""
            ],
            [
                "Q925Q4-1",
                "protein_xref_oma",
                "SRCCTIS",
                ""
            ],
            [
                "Q9QX69-1",
                "protein_xref_oma",
                "ACMFADW",
                ""
            ],
            [
                "A0A0G2K1J7-1",
                "protein_xref_oma",
                "TQHNRTQ",
                ""
            ],
            [
                "P30348-1",
                "protein_xref_oma",
                "INTHSKF",
                ""
            ],
            [
                "A0A0G2JUK9-1",
                "protein_xref_oma",
                "IILCSYV",
                ""
            ],
            [
                "D3ZLV0-1",
                "protein_xref_oma",
                "LAISCND",
                ""
            ],
            [
                "D3ZLV5-1",
                "protein_xref_oma",
                "TPGKFDP",
                ""
            ],
            [
                "A0A096MJY8-1",
                "protein_xref_oma",
                "AYDGLYD",
                ""
            ],
            [
                "Q8VHI8-1",
                "protein_xref_oma",
                "CVFYIVQ",
                ""
            ],
            [
                "D3ZLV9-1",
                "protein_xref_oma",
                "TTITDCY",
                ""
            ],
            [
                "A0A096MJY4-1",
                "protein_xref_oma",
                "LVMPNSR",
                ""
            ],
            [
                "O88181-1",
                "protein_xref_oma",
                "DFRLGDS",
                ""
            ],
            [
                "A0A096MJY1-1",
                "protein_xref_oma",
                "TERLEGP",
                ""
            ],
            [
                "Q2KMM2-1",
                "protein_xref_oma",
                "HDPREGF",
                ""
            ],
            [
                "Q2KN99-1",
                "protein_xref_oma",
                "NVGNQAG",
                ""
            ],
            [
                "A0A096MJY2-1",
                "protein_xref_oma",
                "NAVLYFR",
                ""
            ],
            [
                "D4A838-1",
                "protein_xref_oma",
                "LMMSWRL",
                ""
            ],
            [
                "Q5M808-1",
                "protein_xref_oma",
                "QRRMEQN",
                ""
            ],
            [
                "D3ZKU2-1",
                "protein_xref_oma",
                "IILGFDI",
                ""
            ],
            [
                "A0A0G2K5R6-1",
                "protein_xref_oma",
                "RIIRRGF",
                ""
            ],
            [
                "D4A830-1",
                "protein_xref_oma",
                "WTQAKCE",
                ""
            ],
            [
                "D4A831-1",
                "protein_xref_oma",
                "LWDDSRT",
                ""
            ],
            [
                "D4A832-1",
                "protein_xref_oma",
                "VCYEQEL",
                ""
            ],
            [
                "D3ZZY5-1",
                "protein_xref_oma",
                "WVWLEEH",
                ""
            ],
            [
                "D4A834-1",
                "protein_xref_oma",
                "FCWTDGS",
                ""
            ],
            [
                "M0R6T1-1",
                "protein_xref_oma",
                "SPYLTPH",
                ""
            ],
            [
                "A0A0G2JZ74-1",
                "protein_xref_oma",
                "LTHIHTY",
                ""
            ],
            [
                "B0JYS4-1",
                "protein_xref_oma",
                "IKTLTHK",
                ""
            ],
            [
                "A0A0G2K5R4-1",
                "protein_xref_oma",
                "CKENFDD",
                ""
            ],
            [
                "O54783-1",
                "protein_xref_oma",
                "NIDFEYQ",
                ""
            ],
            [
                "M0RCZ9-1",
                "protein_xref_oma",
                "SSFHRIM",
                ""
            ],
            [
                "M0RCZ7-1",
                "protein_xref_oma",
                "RCIWHEK",
                ""
            ],
            [
                "M0RCZ2-1",
                "protein_xref_oma",
                "GPTEMPH",
                ""
            ],
            [
                "F1M2W3-1",
                "protein_xref_oma",
                "RMESHTQ",
                ""
            ],
            [
                "P01946-1",
                "protein_xref_oma",
                "LERMFIT",
                ""
            ],
            [
                "M0RCZ1-1",
                "protein_xref_oma",
                "VVAECHM",
                ""
            ],
            [
                "P56571-1",
                "protein_xref_oma",
                "HHIFDGI",
                ""
            ],
            [
                "P56574-1",
                "protein_xref_oma",
                "EATLKYG",
                ""
            ],
            [
                "Q5BK10-1",
                "protein_xref_oma",
                "SCQDFQE",
                ""
            ],
            [
                "M0R7U6-1",
                "protein_xref_oma",
                "DGAKYVH",
                ""
            ],
            [
                "Q6P7Q1-1",
                "protein_xref_oma",
                "LVQWDAG",
                ""
            ],
            [
                "M0R7U1-1",
                "protein_xref_oma",
                "IMECGEP",
                ""
            ],
            [
                "Q6P7Q4-1",
                "protein_xref_oma",
                "NWGTESY",
                ""
            ],
            [
                "F1M4Y5-1",
                "protein_xref_oma",
                "TNPGESQ",
                ""
            ],
            [
                "F7FL53-1",
                "protein_xref_oma",
                "DCVDAPA",
                ""
            ],
            [
                "Q6AY39-1",
                "protein_xref_oma",
                "YRQDFRF",
                ""
            ],
            [
                "Q14U74-1",
                "protein_xref_oma",
                "FWAMGRV",
                ""
            ],
            [
                "Q5M807-1",
                "protein_xref_oma",
                "WPCLHQV",
                ""
            ],
            [
                "P02767-1",
                "protein_xref_oma",
                "EPFATGK",
                ""
            ],
            [
                "D3ZNX2-1",
                "protein_xref_oma",
                "ITRSHTI",
                ""
            ],
            [
                "D4A4W8-1",
                "protein_xref_oma",
                "HTSMLPM",
                ""
            ],
            [
                "D4A4W9-1",
                "protein_xref_oma",
                "KTHAFAK",
                ""
            ],
            [
                "D4A4W0-1",
                "protein_xref_oma",
                "TIACYAG",
                ""
            ],
            [
                "D4A4W1-1",
                "protein_xref_oma",
                "FHATTES",
                ""
            ]
        ]
    },
    "readme": "Name\n   - Rat UniProtKB Xref OMA\n\nVersion\n   - 1.8.24\n\nCreated on\n  - 2019-09-06T14:06:38.957228\n\nModified on\n   - 2020-04-10T11:53:38.323623\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 Rat UniProtKB Xref OMA contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers.  The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n   - The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes.\n\nDescription Domain\n   Keywords\n   - orthologs\n   - OMA\n   - cross-reference\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset\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-rattus-norvegicus.nt\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/source/uniprot-proteome-rattus-norvegicus.nt\n      Name: rat_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_masterlist.csv\n   Output Subdomain\n      Name: rat_protein_xref_oma.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_oma.csv\n      Name: rat_protein_xref_oma.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.8.24/reviewed/rat_protein_xref_oma.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-1.8.24/reviewed/rat_protein_xref_oma.csv"
}
