{
    "bcoid": "GLY_000258",
    "title": "Homolog Clusters",
    "description": "The Homolog Clusters dataset contains homologs of human [taxid: 9606], mouse [taxid:10090] and rat [taxid:10116] ...",
    "filename": "protein_homolog_clusters.csv",
    "filetype": "csv",
    "categories": {
        "molecule": "Protein",
        "tags": "Homologs",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "35234...",
                "Q8BFQ8-1..."
            ],
            [
                "35234...",
                "Q8NB37-1..."
            ]
        ],
        "headers": [
            "homolog_clus...",
            "uniprotkb_ca..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "homolog_cluster_id"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "tax_id"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                }
            ],
            [
                "35234",
                "Q8BFQ8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "35234"
            ],
            [
                "35234",
                "Q8NB37-1",
                "9606",
                "protein_xref_mgi_homologset",
                "35234"
            ],
            [
                "35234",
                "D3ZVI9-1",
                "10116",
                "protein_xref_mgi_homologset",
                "35234"
            ],
            [
                "110555",
                "Q7TR16-1",
                "10090",
                "protein_xref_mgi_homologset",
                "110555"
            ],
            [
                "110555",
                "A0A0G2K1C2-1",
                "10116",
                "protein_xref_mgi_homologset",
                "110555"
            ],
            [
                "110555",
                "D3ZW68-1",
                "10116",
                "protein_xref_mgi_homologset",
                "110555"
            ],
            [
                "110555",
                "A0A0G2K6E1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "110555"
            ],
            [
                "110550",
                "Q7TQZ0-1",
                "10090",
                "protein_xref_mgi_homologset",
                "110550"
            ],
            [
                "110550",
                "Q8NGF8-1",
                "9606",
                "protein_xref_mgi_homologset",
                "110550"
            ],
            [
                "110550",
                "A0A0G2JZJ2-1",
                "10116",
                "protein_xref_mgi_homologset",
                "110550"
            ],
            [
                "73393",
                "B9EJV3-1",
                "10090",
                "protein_xref_mgi_homologset",
                "73393"
            ],
            [
                "73393",
                "Q9C091-1",
                "9606",
                "protein_xref_mgi_homologset",
                "73393"
            ],
            [
                "73463",
                "A7L9Z8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "73463"
            ],
            [
                "73463",
                "O75185-1",
                "9606",
                "protein_xref_mgi_homologset",
                "73463"
            ],
            [
                "73463",
                "Q8R4C1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "73463"
            ],
            [
                "35542",
                "E9QAE1-1",
                "10090",
                "protein_xref_mgi_homologset",
                "35542"
            ],
            [
                "35542",
                "O14513-1",
                "9606",
                "protein_xref_mgi_homologset",
                "35542"
            ],
            [
                "35238",
                "Q8C4S8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "35238"
            ],
            [
                "35238",
                "Q9ULE3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "35238"
            ],
            [
                "35238",
                "D3ZLQ1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "35238"
            ],
            [
                "35239",
                "Q8CCH2-1",
                "10090",
                "protein_xref_mgi_homologset",
                "35239"
            ],
            [
                "35239",
                "Q5JS37-1",
                "9606",
                "protein_xref_mgi_homologset",
                "35239"
            ],
            [
                "11542",
                "Q99P68-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11542"
            ],
            [
                "11542",
                "Q9BQB4-1",
                "9606",
                "protein_xref_mgi_homologset",
                "11542"
            ],
            [
                "11542",
                "Q99P67-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11542"
            ],
            [
                "32238",
                "Q8K2H6-1",
                "10090",
                "protein_xref_mgi_homologset",
                "32238"
            ],
            [
                "32238",
                "Q9UM13-1",
                "9606",
                "protein_xref_mgi_homologset",
                "32238"
            ],
            [
                "32238",
                "B5DEP3-1",
                "10116",
                "protein_xref_mgi_homologset",
                "32238"
            ],
            [
                "11546",
                "Q99LQ4-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11546"
            ],
            [
                "11546",
                "Q8N300-1",
                "9606",
                "protein_xref_mgi_homologset",
                "11546"
            ],
            [
                "11546",
                "Q4KLG3-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11546"
            ],
            [
                "11875",
                "Q925I7-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11875"
            ],
            [
                "11875",
                "Q9GZP0-1",
                "9606",
                "protein_xref_mgi_homologset",
                "11875"
            ],
            [
                "11875",
                "Q9EQT1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11875"
            ],
            [
                "11544",
                "Q9D666-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11544"
            ],
            [
                "11544",
                "O94901-8",
                "9606",
                "protein_xref_mgi_homologset",
                "11544"
            ],
            [
                "11544",
                "A0A0G2K016-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11544"
            ],
            [
                "11545",
                "Q8R4U7-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11545"
            ],
            [
                "11545",
                "Q86V48-1",
                "9606",
                "protein_xref_mgi_homologset",
                "11545"
            ],
            [
                "11545",
                "Q9ESV1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11545"
            ],
            [
                "131539",
                "A0A140LHH9-1",
                "10090",
                "protein_xref_mgi_homologset",
                "131539"
            ],
            [
                "131539",
                "F1LYQ6-1",
                "10116",
                "protein_xref_mgi_homologset",
                "131539"
            ],
            [
                "11548",
                "Q9ERR8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "11548"
            ],
            [
                "11548",
                "Q9P2F9-1",
                "9606",
                "protein_xref_mgi_homologset",
                "11548"
            ],
            [
                "11548",
                "D4AEC6-1",
                "10116",
                "protein_xref_mgi_homologset",
                "11548"
            ],
            [
                "103894",
                "P62257-1",
                "10090",
                "protein_xref_mgi_homologset",
                "103894"
            ],
            [
                "103894",
                "P62256-1",
                "9606",
                "protein_xref_mgi_homologset",
                "103894"
            ],
            [
                "73902",
                "Q99N19-1",
                "10090",
                "protein_xref_mgi_homologset",
                "73902"
            ],
            [
                "73902",
                "Q08477-1",
                "9606",
                "protein_xref_mgi_homologset",
                "73902"
            ],
            [
                "73902",
                "P51871-1",
                "10116",
                "protein_xref_mgi_homologset",
                "73902"
            ],
            [
                "5982",
                "Q9DAM5-1",
                "10090",
                "protein_xref_mgi_homologset",
                "5982"
            ],
            [
                "5982",
                "Q9HC21-1",
                "9606",
                "protein_xref_mgi_homologset",
                "5982"
            ],
            [
                "5982",
                "Q6AYL0-1",
                "10116",
                "protein_xref_mgi_homologset",
                "5982"
            ],
            [
                "19396",
                "Q80T54-1",
                "10090",
                "protein_xref_mgi_homologset",
                "19396"
            ],
            [
                "19396",
                "D3ZQ49-1",
                "10116",
                "protein_xref_mgi_homologset",
                "19396"
            ],
            [
                "5980",
                "Q8CCF0-1",
                "10090",
                "protein_xref_mgi_homologset",
                "5980"
            ],
            [
                "5980",
                "Q8WWY3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "5980"
            ],
            [
                "5980",
                "D3ZI68-1",
                "10116",
                "protein_xref_mgi_homologset",
                "5980"
            ],
            [
                "5981",
                "Q9CRA8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "5981"
            ],
            [
                "5981",
                "Q9NQT4-1",
                "9606",
                "protein_xref_mgi_homologset",
                "5981"
            ],
            [
                "5981",
                "F1LSX7-1",
                "10116",
                "protein_xref_mgi_homologset",
                "5981"
            ],
            [
                "5984",
                "Q9EQ61-1",
                "10090",
                "protein_xref_mgi_homologset",
                "5984"
            ],
            [
                "5984",
                "O00541-1",
                "9606",
                "protein_xref_mgi_homologset",
                "5984"
            ],
            [
                "5984",
                "Q3B8N8-1",
                "10116",
                "protein_xref_mgi_homologset",
                "5984"
            ],
            [
                "19390",
                "Q5GH64-1",
                "10090",
                "protein_xref_mgi_homologset",
                "19390"
            ],
            [
                "19390",
                "Q5GH72-1",
                "9606",
                "protein_xref_mgi_homologset",
                "19390"
            ],
            [
                "19390",
                "Q5GH56-1",
                "10116",
                "protein_xref_mgi_homologset",
                "19390"
            ],
            [
                "134867",
                "P58252-1",
                "10090",
                "protein_xref_mgi_homologset",
                "134867"
            ],
            [
                "134867",
                "P13639-1",
                "9606",
                "protein_xref_mgi_homologset",
                "134867"
            ],
            [
                "134867",
                "P05197-1",
                "10116",
                "protein_xref_mgi_homologset",
                "134867"
            ],
            [
                "55616",
                "P18242-1",
                "10090",
                "protein_xref_mgi_homologset",
                "55616"
            ],
            [
                "55616",
                "P07339-1",
                "9606",
                "protein_xref_mgi_homologset",
                "55616"
            ],
            [
                "55616",
                "P24268-1",
                "10116",
                "protein_xref_mgi_homologset",
                "55616"
            ],
            [
                "123852",
                "Q9CZA5-1",
                "10090",
                "protein_xref_mgi_homologset",
                "123852"
            ],
            [
                "123852",
                "Q6PEW1-1",
                "9606",
                "protein_xref_mgi_homologset",
                "123852"
            ],
            [
                "123852",
                "Q5HZA3-1",
                "10116",
                "protein_xref_mgi_homologset",
                "123852"
            ],
            [
                "32484",
                "Q8VHR5-1",
                "10090",
                "protein_xref_mgi_homologset",
                "32484"
            ],
            [
                "32484",
                "Q8WXI9-1",
                "9606",
                "protein_xref_mgi_homologset",
                "32484"
            ],
            [
                "32484",
                "Q4V8E1-1",
                "10116",
                "protein_xref_mgi_homologset",
                "32484"
            ],
            [
                "32507",
                "Q99MZ3-1",
                "10090",
                "protein_xref_mgi_homologset",
                "32507"
            ],
            [
                "32507",
                "Q9NP71-1",
                "9606",
                "protein_xref_mgi_homologset",
                "32507"
            ],
            [
                "32507",
                "Q8VIP2-1",
                "10116",
                "protein_xref_mgi_homologset",
                "32507"
            ],
            [
                "82192",
                "Q8BVK9-1",
                "10090",
                "protein_xref_mgi_homologset",
                "82192"
            ],
            [
                "82192",
                "Q9HB58-1",
                "9606",
                "protein_xref_mgi_homologset",
                "82192"
            ]
        ]
    },
    "readme": "Name\n   - Homolog Clusters\n\nVersion\n   - 1.11.2\n\nCreated on\n  - 2019-09-06T14:06:38.985197\n\nModified on\n   - 2022-01-19T13:37:05.369499\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   - Not Applicable []\n\nChecksum\n   - \n\nUsability Domain\n   - The Homolog Clusters dataset contains homologs of human [taxid: 9606], mouse [taxid:10090] and rat [taxid:10116] species mapped to UniProtKB canonical accessions. The homologs data is downloaded from OMA browser and MGI. If you use this dataset please provide proper attribution to MGI, OMA Browser and GlyGen. \n\nDescription Domain\n   Keywords\n   - homologs\n   - orthologs\n   - MGI\n   - OMA\n\n   Pipeline Steps\n   - Step-1: The script extracts the human, mouse and rat homologs from the input files and using xref files, maps the identifiers to UniProtKB canonical accessions. \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: mouse_human_orthologs_oma_release-24_061319_03-45pm.csv\n      URI: https://data.glygen.org//ln2downloads/oma/2019_06/mouse_human_orthologs_oma_release-24_061319_03-45pm.csv\n      Name: human_protein_xref_hgnc.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_xref_hgnc.csv\n      Name: mgi_homologs.csv\n      URI: https://data.glygen.org//ln2downloads/mgi/2020_12/mgi_homologs.csv\n      Name: mouse_protein_xref_geneid.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_protein_xref_geneid.csv\n      Name: human_protein_xref_geneid.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_xref_geneid.csv\n      Name: rat_protein_xref_geneid.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/rat_protein_xref_geneid.csv\n      Name: human_protein_xref_oma.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/human_protein_xref_oma.csv\n      Name: mouse_protein_xref_oma.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_protein_xref_oma.csv\n      Name: mgi_orthologs_hom_allorganism_release6.14_060419_12-33pm.csv\n      URI: https://data.glygen.org//ln2downloads/mgi/2019_06/mgi_orthologs_hom_allorganism_release6.14_060419_12-33pm.csv\n      Name: rat_human_orthologs_oma_release-24_061319_12-24pm.csv\n      URI: https://data.glygen.org//ln2downloads/oma/2019_06/rat_human_orthologs_oma_release-24_061319_12-24pm.csv\n      Name: rat_protein_xref_oma.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/rat_protein_xref_oma.csv\n      Name: mouse_protein_xref_mgi.csv\n      URI: https://data.glygen.org//ln2releases/data/v-1.11.2/reviewed/mouse_protein_xref_mgi.csv\n   Output Subdomain\n      Name: protein_homolog_clusters.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/protein_homolog_clusters.csv\n      Name: protein_homolog_clusters.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/protein_homolog_clusters.stat.csv",
    "downloadurl": "/ln2data/releases/data/v-1.12.1/reviewed/protein_homolog_clusters.csv"
}
