{
    "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": [
            [
                "41493209...",
                "Q8BHJ7-1..."
            ],
            [
                "41493209...",
                "P31644-1..."
            ]
        ],
        "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"
                }
            ],
            [
                "41493209",
                "Q8BHJ7-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493209"
            ],
            [
                "41493209",
                "P31644-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493209"
            ],
            [
                "41493209",
                "P19969-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493209"
            ],
            [
                "41493208",
                "Q9D658-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493208"
            ],
            [
                "41493208",
                "O75365-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493208"
            ],
            [
                "41493208",
                "B0K032-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493208"
            ],
            [
                "41502219",
                "P61514-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502219"
            ],
            [
                "41502219",
                "P61513-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502219"
            ],
            [
                "41502218",
                "Q4G0F8-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502218"
            ],
            [
                "41502218",
                "Q9NPG3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502218"
            ],
            [
                "41502218",
                "D4A8C6-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41502218"
            ],
            [
                "41497278",
                "Q8CH77-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41497278"
            ],
            [
                "41497278",
                "Q8NEY1-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41497278"
            ],
            [
                "41497278",
                "F1LYK3-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41497278"
            ],
            [
                "41497279",
                "Q3TBT3-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41497279"
            ],
            [
                "41497279",
                "Q86WV6-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41497279"
            ],
            [
                "41497279",
                "F1M391-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41497279"
            ],
            [
                "41493203",
                "E9PX57-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493203"
            ],
            [
                "41493203",
                "Q6ZMV9-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493203"
            ],
            [
                "41493203",
                "E9PSL8-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493203"
            ],
            [
                "41493202",
                "P26361-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493202"
            ],
            [
                "41493202",
                "P13569-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493202"
            ],
            [
                "41493202",
                "P34158-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493202"
            ],
            [
                "41493201",
                "Q8K411-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493201"
            ],
            [
                "41493201",
                "Q5JRX3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493201"
            ],
            [
                "41493201",
                "A0A0G2K6D5-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493201"
            ],
            [
                "41493200",
                "Q811B1-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493200"
            ],
            [
                "41493200",
                "Q86Y38-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493200"
            ],
            [
                "41493207",
                "Q61409-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493207"
            ],
            [
                "41493207",
                "Q13370-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493207"
            ],
            [
                "41493207",
                "Q63085-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493207"
            ],
            [
                "41493206",
                "P46938-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493206"
            ],
            [
                "41493206",
                "P46937-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493206"
            ],
            [
                "41493206",
                "Q2EJA0-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493206"
            ],
            [
                "41493205",
                "Q8VCX5-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493205"
            ],
            [
                "41493205",
                "Q9BPX6-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493205"
            ],
            [
                "41493205",
                "Q6P6Q9-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493205"
            ],
            [
                "41493204",
                "O70324-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41493204"
            ],
            [
                "41493204",
                "P36021-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41493204"
            ],
            [
                "41493204",
                "Q8K1P8-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41493204"
            ],
            [
                "41504438",
                "A2RTS7-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41504438"
            ],
            [
                "41504438",
                "Q5T089-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41504438"
            ],
            [
                "41504438",
                "Q641X6-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41504438"
            ],
            [
                "41502748",
                "E9Q9Y3-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502748"
            ],
            [
                "41502748",
                "Q96M83-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502748"
            ],
            [
                "41502748",
                "Q6AYJ6-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41502748"
            ],
            [
                "41504721",
                "A0A1L1SVH0-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41504721"
            ],
            [
                "41504721",
                "Q8NGF6-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41504721"
            ],
            [
                "41504721",
                "D3ZE76-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41504721"
            ],
            [
                "41502223",
                "Q8BGH7-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502223"
            ],
            [
                "41502223",
                "Q9NRR3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502223"
            ],
            [
                "41502223",
                "A1L1K4-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41502223"
            ],
            [
                "41500523",
                "Q6P3B9-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41500523"
            ],
            [
                "41500523",
                "Q8N0V3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41500523"
            ],
            [
                "41500523",
                "A0A0G2K1B0-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41500523"
            ],
            [
                "41505102",
                "Q7TRE6-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41505102"
            ],
            [
                "41505102",
                "Q8NGG6-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505102"
            ],
            [
                "41505102",
                "D4AE39-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41505102"
            ],
            [
                "41505102",
                "A0A8I6AQV2-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41505102"
            ],
            [
                "41502146",
                "Q9EPJ9-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502146"
            ],
            [
                "41502146",
                "Q8N6T3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502146"
            ],
            [
                "41502146",
                "Q62848-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41502146"
            ],
            [
                "41504720",
                "Q8VF55-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41504720"
            ],
            [
                "41504720",
                "Q8NGI7-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41504720"
            ],
            [
                "41504720",
                "D3ZT33-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41504720"
            ],
            [
                "41502441",
                "Q5XF90-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41502441"
            ],
            [
                "41502441",
                "Q4VNC1-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41502441"
            ],
            [
                "41502441",
                "F1M9L4-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41502441"
            ],
            [
                "41504064",
                "Q8BJ34-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41504064"
            ],
            [
                "41504064",
                "Q9Y4F3-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41504064"
            ],
            [
                "41504064",
                "Q8VIG2-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41504064"
            ],
            [
                "41503628",
                "Q6PDM4-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41503628"
            ],
            [
                "41503628",
                "Q8IYA8-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41503628"
            ],
            [
                "41503628",
                "M0R8J7-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41503628"
            ],
            [
                "41496036",
                "Q99LJ6-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41496036"
            ],
            [
                "41496036",
                "Q96SL4-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41496036"
            ],
            [
                "41496036",
                "A0A8I6ARN0-1",
                "10116",
                "protein_xref_mgi_homologset",
                "41496036"
            ],
            [
                "41505334",
                "D3YUJ6-1",
                "10090",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "O95521-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "O60809-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "O60813-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "O95522-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "Q5VWM6-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ],
            [
                "41505334",
                "P0DUQ2-1",
                "9606",
                "protein_xref_mgi_homologset",
                "41505334"
            ]
        ]
    },
    "readme": "Name\n   - Homolog Clusters\n\nVersion\n   - v-2.0.3\n\nCreated on\n  - 2019-09-06T14:06:38.985197\n\nModified on\n   - 2022-09-26T09:04:47.943513\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/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: protein_homolog_clusters.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/compiled/protein_homolog_clusters.csv\n      Name: fruitfly_protein_transcriptlocus.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/fruitfly_protein_transcriptlocus.csv\n      Name: fruitfly_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/fruitfly_protein_xref_geneid.csv\n      Name: fruitfly_protein_xref_oma.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/fruitfly_protein_xref_oma.csv\n      Name: human_protein_transcriptlocus.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_transcriptlocus.csv\n      Name: human_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_xref_geneid.csv\n      Name: human_protein_xref_hgnc.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_xref_hgnc.csv\n      Name: human_protein_xref_oma.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/human_protein_xref_oma.csv\n      Name: mouse_protein_transcriptlocus.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/mouse_protein_transcriptlocus.csv\n      Name: mouse_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/mouse_protein_xref_geneid.csv\n      Name: mouse_protein_xref_mgi.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/mouse_protein_xref_mgi.csv\n      Name: mouse_protein_xref_oma.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/mouse_protein_xref_oma.csv\n      Name: rat_protein_transcriptlocus.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_transcriptlocus.csv\n      Name: rat_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_xref_geneid.csv\n      Name: rat_protein_xref_oma.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/rat_protein_xref_oma.csv\n      Name: sarscov1_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/sarscov1_protein_xref_geneid.csv\n      Name: sarscov2_protein_xref_geneid.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/sarscov2_protein_xref_geneid.csv\n      Name: mgi_homologs.csv\n      URI: /data/shared/glyds/downloads/mgi/2022_07_07/mgi_homologs.csv\n      Name: fruitfly_human_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/fruitfly_human_oma_orthologs_july2022.csv\n      Name: fruitfly_mouse_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/fruitfly_mouse_oma_orthologs_july2022.csv\n      Name: fruitfly_rat_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/fruitfly_rat_oma_orthologs_july2022.csv\n      Name: human_fruitfly_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/human_fruitfly_oma_orthologs_july2022.csv\n      Name: human_mouse_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/human_mouse_oma_orthologs_july2022.csv\n      Name: human_rat_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/human_rat_oma_orthologs_july2022.csv\n      Name: mouse_fruitfly_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/mouse_fruitfly_oma_orthologs_july2022.csv\n      Name: mouse_human_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/mouse_human_oma_orthologs_july2022.csv\n      Name: mouse_rat_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/mouse_rat_oma_orthologs_july2022.csv\n      Name: rat_fruitfly_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/rat_fruitfly_oma_orthologs_july2022.csv\n      Name: rat_human_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/rat_human_oma_orthologs_july2022.csv\n      Name: rat_mouse_oma_orthologs_july2022.csv\n      URI: /data/shared/glyds/downloads/oma/2022_07_07/rat_mouse_oma_orthologs_july2022.csv\n   Output Subdomain\n      Name: protein_homolog_clusters.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/protein_homolog_clusters.csv\n      Name: protein_homolog_clusters.stat.csv\n      URI: https:/data.glygen.org/ln2releases/data/v-2.0.3/reviewed/protein_homolog_clusters.stat.csv\n\nFields\n      Name: \"homolog_cluster_id\"\n     Description: \"NA\"\n      Unique Values: \"32719\"\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"55207\"\n      Name: \"tax_id\"\n     Description: \"NCBI Taxonomy database Identifier\"\n      Unique Values: \"8\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"4\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"32718\"",
    "downloadurl": "/ln2data/releases/data/v-2.0.3/reviewed/protein_homolog_clusters.csv"
}
