{ "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" ], "tag": [ "Homologs" ], "file_type": [ "csv" ], "status": [ "Reviewed" ], "scope": [ "internal" ], "species": [ "Mus musculus", "Homo sapiens", "Rattus norvegicus", "Saccharomyces cerevisiae S288C", "Drosophila melanogaster", "Severe acute respiratory syndrome coronavirus 2", "Severe acute respiratory syndrome-related coronavirus", "Hepatitis C virus (isolate H)", "Hepatitis C virus (isolate Japanese)" ] }, "minitable": { "content": [ [ "45238093...", "Q9CQX4-1..." ], [ "45238093...", "Q15004-1..." ] ], "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" } ], [ "45238093", "Q9CQX4-1", "10090", "protein_xref_mgi_homologset", "45238093" ], [ "45238093", "Q15004-1", "9606", "protein_xref_mgi_homologset", "45238093" ], [ "45238091", "Q8CHS4-1", "10090", "protein_xref_mgi_homologset", "45238091" ], [ "45238091", "Q9NUJ7-1", "9606", "protein_xref_mgi_homologset", "45238091" ], [ "45238090", "Q3UR85-1", "10090", "protein_xref_mgi_homologset", "45238090" ], [ "45238090", "Q9Y2G1-1", "9606", "protein_xref_mgi_homologset", "45238090" ], [ "45238090", "D4A352-1", "10116", "protein_xref_mgi_homologset", "45238090" ], [ "45238096", "Q8BGB2-1", "10090", "protein_xref_mgi_homologset", "45238096" ], [ "45238096", "Q9ULT0-1", "9606", "protein_xref_mgi_homologset", "45238096" ], [ "45238094", "Q9JIQ3-1", "10090", "protein_xref_mgi_homologset", "45238094" ], [ "45238094", "Q9NR28-1", "9606", "protein_xref_mgi_homologset", "45238094" ], [ "45238094", "D4A7Z5-1", "10116", "protein_xref_mgi_homologset", "45238094" ], [ "45239991", "Q6NVG5-1", "10090", "protein_xref_mgi_homologset", "45239991" ], [ "45239991", "Q8N565-1", "9606", "protein_xref_mgi_homologset", "45239991" ], [ "45239991", "D4A9U9-1", "10116", "protein_xref_mgi_homologset", "45239991" ], [ "45238099", "Q6PFX2-1", "10090", "protein_xref_mgi_homologset", "45238099" ], [ "45238099", "Q5SZJ8-1", "9606", "protein_xref_mgi_homologset", "45238099" ], [ "45238098", "Q69ZK0-1", "10090", "protein_xref_mgi_homologset", "45238098" ], [ "45238098", "Q8TCU6-1", "9606", "protein_xref_mgi_homologset", "45238098" ], [ "45238098", "A0A8I6GLR6-1", "10116", "protein_xref_mgi_homologset", "45238098" ], [ "45244594", "P16373-1", "10090", "protein_xref_mgi_homologset", "45244594" ], [ "45244594", "O75290-1", "9606", "protein_xref_mgi_homologset", "45244594" ], [ "45244594", "Q9Y6R6-1", "9606", "protein_xref_mgi_homologset", "45244594" ], [ "45244594", "D3ZXG1-1", "10116", "protein_xref_mgi_homologset", "45244594" ], [ "45232639", "A2BDX3-1", "10090", "protein_xref_mgi_homologset", "45232639" ], [ "45232639", "O95396-1", "9606", "protein_xref_mgi_homologset", "45232639" ], [ "45232638", "Q8CGC4-1", "10090", "protein_xref_mgi_homologset", "45232638" ], [ "45232638", "Q9BX40-1", "9606", "protein_xref_mgi_homologset", "45232638" ], [ "45234016", "Q811S7-1", "10090", "protein_xref_mgi_homologset", "45234016" ], [ "45234016", "Q9NZI7-1", "9606", "protein_xref_mgi_homologset", "45234016" ], [ "45234016", "A0A8I6GFC7-1", "10116", "protein_xref_mgi_homologset", "45234016" ], [ "45232631", "O35942-1", "10090", "protein_xref_mgi_homologset", "45232631" ], [ "45232631", "P51955-1", "9606", "protein_xref_mgi_homologset", "45232631" ], [ "45232631", "A0A8I6AHQ6-1", "10116", "protein_xref_mgi_homologset", "45232631" ], [ "45229134", "Q91V27-1", "10090", "protein_xref_mgi_homologset", "45229134" ], [ "45229134", "Q9BV36-1", "9606", "protein_xref_mgi_homologset", "45229134" ], [ "45229134", "A0A8I5ZSZ6-1", "10116", "protein_xref_mgi_homologset", "45229134" ], [ "45232633", "Q9QZB7-1", "10090", "protein_xref_mgi_homologset", "45232633" ], [ "45232633", "Q9NZ32-1", "9606", "protein_xref_mgi_homologset", "45232633" ], [ "45232632", "Q8BMG8-1", "10090", "protein_xref_mgi_homologset", "45232632" ], [ "45232632", "Q9H2D1-1", "9606", "protein_xref_mgi_homologset", "45232632" ], [ "45232632", "B2GV53-1", "10116", "protein_xref_mgi_homologset", "45232632" ], [ "45232635", "Q8C2S0-1", "10090", "protein_xref_mgi_homologset", "45232635" ], [ "45232635", "Q9H0E7-1", "9606", "protein_xref_mgi_homologset", "45232635" ], [ "45232634", "O08795-1", "10090", "protein_xref_mgi_homologset", "45232634" ], [ "45232634", "P14314-1", "9606", "protein_xref_mgi_homologset", "45232634" ], [ "45232634", "B1WC34-1", "10116", "protein_xref_mgi_homologset", "45232634" ], [ "45232637", "Q9D9G3-1", "10090", "protein_xref_mgi_homologset", "45232637" ], [ "45232637", "Q9UKJ5-1", "9606", "protein_xref_mgi_homologset", "45232637" ], [ "45232637", "G3V6A1-1", "10116", "protein_xref_mgi_homologset", "45232637" ], [ "45232636", "Q99K43-1", "10090", "protein_xref_mgi_homologset", "45232636" ], [ "45232636", "O43663-1", "9606", "protein_xref_mgi_homologset", "45232636" ], [ "45232636", "A0A8I6APJ5-1", "10116", "protein_xref_mgi_homologset", "45232636" ], [ "45241565", "A0A1B0GR74-1", "10090", "protein_xref_mgi_homologset", "45241565" ], [ "45241565", "A6NJ69-1", "9606", "protein_xref_mgi_homologset", "45241565" ], [ "45243100", "Q8VGC7-1", "10090", "protein_xref_mgi_homologset", "45243100" ], [ "45243100", "Q8NH50-1", "9606", "protein_xref_mgi_homologset", "45243100" ], [ "45243100", "D4ACY8-1", "10116", "protein_xref_mgi_homologset", "45243100" ], [ "45239990", "Q307W7-1", "10090", "protein_xref_mgi_homologset", "45239990" ], [ "45239990", "A6PVL3-1", "9606", "protein_xref_mgi_homologset", "45239990" ], [ "45239453", "Q6PDZ2-1", "10090", "protein_xref_mgi_homologset", "45239453" ], [ "45239453", "Q15572-1", "9606", "protein_xref_mgi_homologset", "45239453" ], [ "45239453", "Q6P773-1", "10116", "protein_xref_mgi_homologset", "45239453" ], [ "45229135", "Q9QYC3-1", "10090", "protein_xref_mgi_homologset", "45229135" ], [ "45229135", "Q7RTS1-1", "9606", "protein_xref_mgi_homologset", "45229135" ], [ "45229135", "P70562-1", "10116", "protein_xref_mgi_homologset", "45229135" ], [ "45234010", "Q91YE2-1", "10090", "protein_xref_mgi_homologset", "45234010" ], [ "45234010", "Q96KS0-1", "9606", "protein_xref_mgi_homologset", "45234010" ], [ "45234010", "Q6AYU4-1", "10116", "protein_xref_mgi_homologset", "45234010" ], [ "45244586", "Q8BHM7-1", "10090", "protein_xref_mgi_homologset", "45244586" ], [ "45244586", "Q96H86-1", "9606", "protein_xref_mgi_homologset", "45244586" ], [ "45244586", "M0R5W9-1", "10116", "protein_xref_mgi_homologset", "45244586" ], [ "45239994", "Q61470-1", "10090", "protein_xref_mgi_homologset", "45239994" ], [ "45239994", "P11049-1", "9606", "protein_xref_mgi_homologset", "45239994" ], [ "45239994", "P31053-1", "10116", "protein_xref_mgi_homologset", "45239994" ], [ "45229398", "O54897-1", "10090", "protein_xref_mgi_homologset", "45229398" ], [ "45229398", "Q9NS67-1", "9606", "protein_xref_mgi_homologset", "45229398" ], [ "45229398", "Q9JJH3-1", "10116", "protein_xref_mgi_homologset", "45229398" ], [ "45229399", "Q9CW79-1", "10090", "protein_xref_mgi_homologset", "45229399" ], [ "45229399", "Q92805-1", "9606", "protein_xref_mgi_homologset", "45229399" ], [ "45229399", "D4A6K4-1", "10116", "protein_xref_mgi_homologset", "45229399" ], [ "45239993", "Q8BWU3-1", "10090", "protein_xref_mgi_homologset", "45239993" ], [ "45239993", "Q6UXB0-3", "9606", "protein_xref_mgi_homologset", "45239993" ], [ "45239993", "M0RBP4-1", "10116", "protein_xref_mgi_homologset", "45239993" ] ] }, "readme": "Name\n - Homolog Clusters\n\nVersion\n - v-2.3.1\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], Robel Kahsay [rykahsay@gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Jingyue Wu [jingyue.wu@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-2.3.1/compiled/protein_homolog_clusters.csv\n Name: dicty_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_xref_geneid.csv\n Name: dicty_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/dicty_protein_xref_oma.csv\n Name: fruitfly_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_protein_transcriptlocus.csv\n Name: fruitfly_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_protein_xref_geneid.csv\n Name: fruitfly_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/fruitfly_protein_xref_oma.csv\n Name: human_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_transcriptlocus.csv\n Name: human_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_xref_geneid.csv\n Name: human_protein_xref_hgnc.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_xref_hgnc.csv\n Name: human_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/human_protein_xref_oma.csv\n Name: mouse_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_transcriptlocus.csv\n Name: mouse_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_xref_geneid.csv\n Name: mouse_protein_xref_mgi.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_xref_mgi.csv\n Name: mouse_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/mouse_protein_xref_oma.csv\n Name: rat_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_protein_transcriptlocus.csv\n Name: rat_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_protein_xref_geneid.csv\n Name: rat_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/rat_protein_xref_oma.csv\n Name: sarscov1_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov1_protein_xref_geneid.csv\n Name: sarscov2_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/sarscov2_protein_xref_geneid.csv\n Name: yeast_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_transcriptlocus.csv\n Name: yeast_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_geneid.csv\n Name: yeast_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/yeast_protein_xref_oma.csv\n Name: mgi_homologs.tsv\n URI: https:/data.glygen.org/ln2downloads/mgi/2023_10_23/mgi_homologs.tsv\n Name: dicty_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/dicty_fruitfly_oma_orthologs.txt\n Name: dicty_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/dicty_human_oma_orthologs.txt\n Name: dicty_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/dicty_mouse_oma_orthologs.txt\n Name: dicty_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/dicty_rat_oma_orthologs.txt\n Name: dicty_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/dicty_yeast_oma_orthologs.txt\n Name: fruitfly_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/fruitfly_dicty_oma_orthologs.txt\n Name: fruitfly_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/fruitfly_human_oma_orthologs.txt\n Name: fruitfly_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/fruitfly_mouse_oma_orthologs.txt\n Name: fruitfly_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/fruitfly_rat_oma_orthologs.txt\n Name: fruitfly_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/fruitfly_yeast_oma_orthologs.txt\n Name: human_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/human_dicty_oma_orthologs.txt\n Name: human_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/human_fruitfly_oma_orthologs.txt\n Name: human_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/human_mouse_oma_orthologs.txt\n Name: human_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/human_rat_oma_orthologs.txt\n Name: human_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/human_yeast_oma_orthologs.txt\n Name: mouse_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/mouse_dicty_oma_orthologs.txt\n Name: mouse_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/mouse_fruitfly_oma_orthologs.txt\n Name: mouse_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/mouse_human_oma_orthologs.txt\n Name: mouse_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/mouse_rat_oma_orthologs.txt\n Name: mouse_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/mouse_yeast_oma_orthologs.txt\n Name: rat_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/rat_dicty_oma_orthologs.txt\n Name: rat_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/rat_fruitfly_oma_orthologs.txt\n Name: rat_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/rat_human_oma_orthologs.txt\n Name: rat_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/rat_mouse_oma_orthologs.txt\n Name: rat_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/rat_yeast_oma_orthologs.txt\n Name: yeast_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/yeast_dicty_oma_orthologs.txt\n Name: yeast_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/yeast_fruitfly_oma_orthologs.txt\n Name: yeast_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/yeast_human_oma_orthologs.txt\n Name: yeast_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/yeast_mouse_oma_orthologs.txt\n Name: yeast_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2023_10_11/yeast_rat_oma_orthologs.txt\n Output Subdomain\n Name: protein_homolog_clusters.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/protein_homolog_clusters.csv\n Name: protein_homolog_clusters.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.3.1/reviewed/protein_homolog_clusters.stat.csv\n\nFields\n Name: \"homolog_cluster_id\"\n Description: \"NA\"\n Unique Values: \"32562\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"54870\"\n Name: \"tax_id\"\n Description: \"NCBI Taxonomy database Identifier\"\n Unique Values: \"9\"\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: \"32561\"", "downloadurl": "/ln2data/releases/data/v-2.3.1/reviewed/protein_homolog_clusters.csv" }