{ "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" ], "species": [ "Mus musculus", "Homo sapiens", "Rattus norvegicus", "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": [ [ "43789272...", "P48381-1..." ], [ "43789272...", "P48380-1..." ] ], "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" } ], [ "43789272", "P48381-1", "10090", "protein_xref_mgi_homologset", "43789272" ], [ "43789272", "P48380-1", "9606", "protein_xref_mgi_homologset", "43789272" ], [ "43789272", "A0A8I6GK32-1", "10116", "protein_xref_mgi_homologset", "43789272" ], [ "43789273", "Q6W3F0-1", "10090", "protein_xref_mgi_homologset", "43789273" ], [ "43789273", "Q7Z4N8-1", "9606", "protein_xref_mgi_homologset", "43789273" ], [ "43789273", "Q6W3E9-1", "10116", "protein_xref_mgi_homologset", "43789273" ], [ "43789270", "Q99PG0-1", "10090", "protein_xref_mgi_homologset", "43789270" ], [ "43789270", "P22760-1", "9606", "protein_xref_mgi_homologset", "43789270" ], [ "43789270", "Q9QZH8-1", "10116", "protein_xref_mgi_homologset", "43789270" ], [ "43789271", "Q8BUY2-1", "10090", "protein_xref_mgi_homologset", "43789271" ], [ "43789271", "D4A8F5-1", "10116", "protein_xref_mgi_homologset", "43789271" ], [ "43789276", "O54949-1", "10090", "protein_xref_mgi_homologset", "43789276" ], [ "43789276", "Q9UBE8-1", "9606", "protein_xref_mgi_homologset", "43789276" ], [ "43789276", "D3ZSZ3-1", "10116", "protein_xref_mgi_homologset", "43789276" ], [ "43789277", "P97346-1", "10090", "protein_xref_mgi_homologset", "43789277" ], [ "43789277", "Q6DKJ4-1", "9606", "protein_xref_mgi_homologset", "43789277" ], [ "43789277", "A0A8I6A4C2-1", "10116", "protein_xref_mgi_homologset", "43789277" ], [ "43789274", "Q8VCD6-1", "10090", "protein_xref_mgi_homologset", "43789274" ], [ "43789274", "Q9BRK0-1", "9606", "protein_xref_mgi_homologset", "43789274" ], [ "43789274", "A0A0G2K1L5-1", "10116", "protein_xref_mgi_homologset", "43789274" ], [ "43789275", "G3UW60-1", "10090", "protein_xref_mgi_homologset", "43789275" ], [ "43789275", "O60279-1", "9606", "protein_xref_mgi_homologset", "43789275" ], [ "43789275", "D3ZSC1-1", "10116", "protein_xref_mgi_homologset", "43789275" ], [ "43789908", "P04184-1", "10090", "protein_xref_mgi_homologset", "43789908" ], [ "43789908", "P04183-1", "9606", "protein_xref_mgi_homologset", "43789908" ], [ "43789908", "P27158-1", "10116", "protein_xref_mgi_homologset", "43789908" ], [ "43789909", "Q9DCU6-1", "10090", "protein_xref_mgi_homologset", "43789909" ], [ "43789909", "Q9BYD3-1", "9606", "protein_xref_mgi_homologset", "43789909" ], [ "43789909", "D4A131-1", "10116", "protein_xref_mgi_homologset", "43789909" ], [ "43789278", "P08680-1", "10090", "protein_xref_mgi_homologset", "43789278" ], [ "43789278", "P22557-1", "9606", "protein_xref_mgi_homologset", "43789278" ], [ "43789278", "Q63147-1", "10116", "protein_xref_mgi_homologset", "43789278" ], [ "43789279", "P04925-1", "10090", "protein_xref_mgi_homologset", "43789279" ], [ "43789279", "P04156-1", "9606", "protein_xref_mgi_homologset", "43789279" ], [ "43789279", "P13852-1", "10116", "protein_xref_mgi_homologset", "43789279" ], [ "43789902", "P81066-1", "10090", "protein_xref_mgi_homologset", "43789902" ], [ "43789902", "Q9BZI1-1", "9606", "protein_xref_mgi_homologset", "43789902" ], [ "43789902", "D3ZGA0-1", "10116", "protein_xref_mgi_homologset", "43789902" ], [ "43790498", "Q9JJT2-1", "10090", "protein_xref_mgi_homologset", "43790498" ], [ "43790498", "Q9GZZ7-1", "9606", "protein_xref_mgi_homologset", "43790498" ], [ "43790498", "Q9EPI2-1", "10116", "protein_xref_mgi_homologset", "43790498" ], [ "43789903", "O35658-1", "10090", "protein_xref_mgi_homologset", "43789903" ], [ "43789903", "Q07021-1", "9606", "protein_xref_mgi_homologset", "43789903" ], [ "43789903", "O35796-1", "10116", "protein_xref_mgi_homologset", "43789903" ], [ "43798957", "Q5IBH6-1", "10090", "protein_xref_mgi_homologset", "43798957" ], [ "43798957", "Q8NFV5-1", "9606", "protein_xref_mgi_homologset", "43798957" ], [ "43798957", "P0DTA3-1", "9606", "protein_xref_mgi_homologset", "43798957" ], [ "43798957", "A6NLX3-1", "9606", "protein_xref_mgi_homologset", "43798957" ], [ "43798957", "A6NIY4-1", "9606", "protein_xref_mgi_homologset", "43798957" ], [ "43798957", "A0A8I6A4C0-1", "10116", "protein_xref_mgi_homologset", "43798957" ], [ "43800125", "Q08423-1", "10090", "protein_xref_mgi_homologset", "43800125" ], [ "43800125", "P04155-1", "9606", "protein_xref_mgi_homologset", "43800125" ], [ "43800125", "Q63467-1", "10116", "protein_xref_mgi_homologset", "43800125" ], [ "43790499", "Q9D6D0-1", "10090", "protein_xref_mgi_homologset", "43790499" ], [ "43790499", "O95847-1", "9606", "protein_xref_mgi_homologset", "43790499" ], [ "43790499", "A0A8I6ALR4-1", "10116", "protein_xref_mgi_homologset", "43790499" ], [ "43789904", "Q920R0-1", "10090", "protein_xref_mgi_homologset", "43789904" ], [ "43789904", "Q96Q42-1", "9606", "protein_xref_mgi_homologset", "43789904" ], [ "43789904", "P0C5Y8-1", "10116", "protein_xref_mgi_homologset", "43789904" ], [ "43791670", "Q04690-1", "10090", "protein_xref_mgi_homologset", "43791670" ], [ "43791670", "P21359-1", "9606", "protein_xref_mgi_homologset", "43791670" ], [ "43791670", "P97526-1", "10116", "protein_xref_mgi_homologset", "43791670" ], [ "43795833", "Q7TQE7-1", "10090", "protein_xref_mgi_homologset", "43795833" ], [ "43795833", "Q8NCT3-1", "9606", "protein_xref_mgi_homologset", "43795833" ], [ "43795833", "D4ABI4-1", "10116", "protein_xref_mgi_homologset", "43795833" ], [ "43789905", "Q8BFP9-1", "10090", "protein_xref_mgi_homologset", "43789905" ], [ "43789905", "Q15118-1", "9606", "protein_xref_mgi_homologset", "43789905" ], [ "43789905", "Q63065-1", "10116", "protein_xref_mgi_homologset", "43789905" ], [ "43787623", "Q5RJI4-1", "10090", "protein_xref_mgi_homologset", "43787623" ], [ "43787623", "Q504Y2-1", "9606", "protein_xref_mgi_homologset", "43787623" ], [ "43787622", "Q91ZT7-1", "10090", "protein_xref_mgi_homologset", "43787622" ], [ "43787622", "Q8WXI3-1", "9606", "protein_xref_mgi_homologset", "43787622" ], [ "43787622", "A0A8J8YAH4-1", "10116", "protein_xref_mgi_homologset", "43787622" ], [ "43787621", "O70503-1", "10090", "protein_xref_mgi_homologset", "43787621" ], [ "43787621", "Q53GQ0-1", "9606", "protein_xref_mgi_homologset", "43787621" ], [ "43787621", "Q6P7R8-1", "10116", "protein_xref_mgi_homologset", "43787621" ], [ "43787620", "P51865-1", "10090", "protein_xref_mgi_homologset", "43787620" ], [ "43787620", "P13385-1", "9606", "protein_xref_mgi_homologset", "43787620" ], [ "43787627", "O89100-1", "10090", "protein_xref_mgi_homologset", "43787627" ], [ "43787627", "O75791-1", "9606", "protein_xref_mgi_homologset", "43787627" ], [ "43787627", "Q3KR57-1", "10116", "protein_xref_mgi_homologset", "43787627" ], [ "43787626", "Q9DCI9-1", "10090", "protein_xref_mgi_homologset", "43787626" ], [ "43787626", "Q9BYC8-1", "9606", "protein_xref_mgi_homologset", "43787626" ], [ "43787625", "O35691-1", "10090", "protein_xref_mgi_homologset", "43787625" ] ] }, "readme": "Name\n - Homolog Clusters\n\nVersion\n - v-2.1.1\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-2.1.1/compiled/protein_homolog_clusters.csv\n Name: fruitfly_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_transcriptlocus.csv\n Name: fruitfly_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_geneid.csv\n Name: fruitfly_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/fruitfly_protein_xref_oma.csv\n Name: human_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_transcriptlocus.csv\n Name: human_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_geneid.csv\n Name: human_protein_xref_hgnc.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_hgnc.csv\n Name: human_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/human_protein_xref_oma.csv\n Name: mouse_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_transcriptlocus.csv\n Name: mouse_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_geneid.csv\n Name: mouse_protein_xref_mgi.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_mgi.csv\n Name: mouse_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/mouse_protein_xref_oma.csv\n Name: rat_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_transcriptlocus.csv\n Name: rat_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_geneid.csv\n Name: rat_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/rat_protein_xref_oma.csv\n Name: sarscov1_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov1_protein_xref_geneid.csv\n Name: sarscov2_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/sarscov2_protein_xref_geneid.csv\n Name: mgi_homologs.tsv\n URI: /data/shared/glyds/downloads/mgi/2023_04/mgi_homologs.tsv\n Name: fruitfly_human_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/fruitfly_human_oma_orthologs.txt\n Name: fruitfly_mouse_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/fruitfly_mouse_oma_orthologs.txt\n Name: fruitfly_rat_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/fruitfly_rat_oma_orthologs.txt\n Name: human_fruitfly_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/human_fruitfly_oma_orthologs.txt\n Name: human_mouse_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/human_mouse_oma_orthologs.txt\n Name: human_rat_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/human_rat_oma_orthologs.txt\n Name: mouse_fruitfly_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/mouse_fruitfly_oma_orthologs.txt\n Name: mouse_human_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/mouse_human_oma_orthologs.txt\n Name: mouse_rat_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/mouse_rat_oma_orthologs.txt\n Name: rat_fruitfly_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/rat_fruitfly_oma_orthologs.txt\n Name: rat_human_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/rat_human_oma_orthologs.txt\n Name: rat_mouse_oma_orthologs.txt\n URI: /data/shared/glyds/downloads/oma/2023_05_23/rat_mouse_oma_orthologs.txt\n Output Subdomain\n Name: protein_homolog_clusters.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_homolog_clusters.csv\n Name: protein_homolog_clusters.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.1.1/reviewed/protein_homolog_clusters.stat.csv\n\nFields\n Name: \"homolog_cluster_id\"\n Description: \"NA\"\n Unique Values: \"32643\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"54087\"\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: \"32642\"", "downloadurl": "/ln2data/releases/data/v-2.1.1/reviewed/protein_homolog_clusters.csv" }