{ "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": [ [ "45924886...", "Q9Z2I9-1..." ], [ "45924886...", "Q9P2R7-1..." ] ], "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" } ], [ "45924886", "Q9Z2I9-1", "10090", "protein_xref_mgi_homologset", "45924886" ], [ "45924886", "Q9P2R7-1", "9606", "protein_xref_mgi_homologset", "45924886" ], [ "45924886", "F1LM47-1", "10116", "protein_xref_mgi_homologset", "45924886" ], [ "45922946", "Q3U507-1", "10090", "protein_xref_mgi_homologset", "45922946" ], [ "45922946", "Q9BXC1-1", "9606", "protein_xref_mgi_homologset", "45922946" ], [ "45922946", "D3ZWS1-1", "10116", "protein_xref_mgi_homologset", "45922946" ], [ "45926488", "P16646-1", "10090", "protein_xref_mgi_homologset", "45926488" ], [ "45926488", "Q01453-1", "9606", "protein_xref_mgi_homologset", "45926488" ], [ "45926488", "P25094-1", "10116", "protein_xref_mgi_homologset", "45926488" ], [ "45926489", "Q9QXV3-1", "10090", "protein_xref_mgi_homologset", "45926489" ], [ "45926489", "Q9UK53-1", "9606", "protein_xref_mgi_homologset", "45926489" ], [ "45928288", "P52483-1", "10090", "protein_xref_mgi_homologset", "45928288" ], [ "45928288", "Q969T4-1", "9606", "protein_xref_mgi_homologset", "45928288" ], [ "45934450", "D3Z7A9-1", "10090", "protein_xref_mgi_homologset", "45934450" ], [ "45934450", "A6NI73-1", "9606", "protein_xref_mgi_homologset", "45934450" ], [ "45934450", "A0A8I6AFZ4-1", "10116", "protein_xref_mgi_homologset", "45934450" ], [ "45931885", "Q8C031-1", "10090", "protein_xref_mgi_homologset", "45931885" ], [ "45931885", "Q9HCJ2-1", "9606", "protein_xref_mgi_homologset", "45931885" ], [ "45931885", "D3ZXT1-1", "10116", "protein_xref_mgi_homologset", "45931885" ], [ "45926482", "Q8BX22-1", "10090", "protein_xref_mgi_homologset", "45926482" ], [ "45926482", "Q9UJQ4-1", "9606", "protein_xref_mgi_homologset", "45926482" ], [ "45926482", "M0RDM1-1", "10116", "protein_xref_mgi_homologset", "45926482" ], [ "45926483", "Q9CQZ0-1", "10090", "protein_xref_mgi_homologset", "45926483" ], [ "45926483", "Q53FV1-1", "9606", "protein_xref_mgi_homologset", "45926483" ], [ "45926483", "D4A2I4-1", "10116", "protein_xref_mgi_homologset", "45926483" ], [ "45926480", "Q8BFU1-1", "10090", "protein_xref_mgi_homologset", "45926480" ], [ "45926480", "Q9NUM3-1", "9606", "protein_xref_mgi_homologset", "45926480" ], [ "45926480", "Q3KR82-1", "10116", "protein_xref_mgi_homologset", "45926480" ], [ "45926481", "Q78IQ7-1", "10090", "protein_xref_mgi_homologset", "45926481" ], [ "45926481", "Q6P5W5-1", "9606", "protein_xref_mgi_homologset", "45926481" ], [ "45926481", "A0JPN2-1", "10116", "protein_xref_mgi_homologset", "45926481" ], [ "45926486", "Q9D132-1", "10090", "protein_xref_mgi_homologset", "45926486" ], [ "45926486", "O00322-1", "9606", "protein_xref_mgi_homologset", "45926486" ], [ "45926487", "Q9D6I7-1", "10090", "protein_xref_mgi_homologset", "45926487" ], [ "45926487", "Q5T7M9-1", "9606", "protein_xref_mgi_homologset", "45926487" ], [ "45926487", "B2RYE8-1", "10116", "protein_xref_mgi_homologset", "45926487" ], [ "45926484", "P51667-1", "10090", "protein_xref_mgi_homologset", "45926484" ], [ "45926484", "P10916-1", "9606", "protein_xref_mgi_homologset", "45926484" ], [ "45926484", "P08733-1", "10116", "protein_xref_mgi_homologset", "45926484" ], [ "45926485", "Q8K2U2-1", "10090", "protein_xref_mgi_homologset", "45926485" ], [ "45926485", "Q3KRA9-1", "9606", "protein_xref_mgi_homologset", "45926485" ], [ "45926485", "G3V9E2-1", "10116", "protein_xref_mgi_homologset", "45926485" ], [ "45932674", "Q8BHG2-1", "10090", "protein_xref_mgi_homologset", "45932674" ], [ "45932674", "Q9NWV4-1", "9606", "protein_xref_mgi_homologset", "45932674" ], [ "45932674", "Q498R7-1", "10116", "protein_xref_mgi_homologset", "45932674" ], [ "45928286", "Q3TCX3-1", "10090", "protein_xref_mgi_homologset", "45928286" ], [ "45928286", "Q7Z7F0-1", "9606", "protein_xref_mgi_homologset", "45928286" ], [ "45932676", "Q3V188-1", "10090", "protein_xref_mgi_homologset", "45932676" ], [ "45932676", "P21128-1", "9606", "protein_xref_mgi_homologset", "45932676" ], [ "45932676", "D3ZSZ1-1", "10116", "protein_xref_mgi_homologset", "45932676" ], [ "45932677", "Q9JKL4-1", "10090", "protein_xref_mgi_homologset", "45932677" ], [ "45932677", "Q9BU61-1", "9606", "protein_xref_mgi_homologset", "45932677" ], [ "45932677", "O08776-1", "10116", "protein_xref_mgi_homologset", "45932677" ], [ "45932670", "Q14BE7-1", "10090", "protein_xref_mgi_homologset", "45932670" ], [ "45932670", "Q5JRC9-1", "9606", "protein_xref_mgi_homologset", "45932670" ], [ "45932670", "Q8NA70-1", "9606", "protein_xref_mgi_homologset", "45932670" ], [ "45932670", "Q5HY64-1", "9606", "protein_xref_mgi_homologset", "45932670" ], [ "45932672", "B1AW18-1", "10090", "protein_xref_mgi_homologset", "45932672" ], [ "45932672", "D4ADV7-1", "10116", "protein_xref_mgi_homologset", "45932672" ], [ "45928287", "Q6P5D3-1", "10090", "protein_xref_mgi_homologset", "45928287" ], [ "45928287", "Q6P158-1", "9606", "protein_xref_mgi_homologset", "45928287" ], [ "45934302", "Q08EG8-1", "10090", "protein_xref_mgi_homologset", "45934302" ], [ "45934302", "P60014-1", "9606", "protein_xref_mgi_homologset", "45934302" ], [ "45934302", "P60369-1", "9606", "protein_xref_mgi_homologset", "45934302" ], [ "45934302", "P60409-1", "9606", "protein_xref_mgi_homologset", "45934302" ], [ "45934302", "D4A3Q1-1", "10116", "protein_xref_mgi_homologset", "45934302" ], [ "45932678", "Q8CEE0-1", "10090", "protein_xref_mgi_homologset", "45932678" ], [ "45932678", "Q86XR8-1", "9606", "protein_xref_mgi_homologset", "45932678" ], [ "45932678", "B4F7A7-1", "10116", "protein_xref_mgi_homologset", "45932678" ], [ "45932679", "Q7TSI1-1", "10090", "protein_xref_mgi_homologset", "45932679" ], [ "45932679", "Q9Y4G2-1", "9606", "protein_xref_mgi_homologset", "45932679" ], [ "45932679", "Q5PQS0-1", "10116", "protein_xref_mgi_homologset", "45932679" ], [ "45934453", "Q61450-1", "10090", "protein_xref_mgi_homologset", "45934453" ], [ "45934453", "Q8NHJ6-1", "9606", "protein_xref_mgi_homologset", "45934453" ], [ "45934453", "A0A0G2JVH3-1", "10116", "protein_xref_mgi_homologset", "45934453" ], [ "45931594", "G3X942-1", "10090", "protein_xref_mgi_homologset", "45931594" ], [ "45931594", "Q9HCQ5-1", "9606", "protein_xref_mgi_homologset", "45931594" ], [ "45931594", "D3ZQA1-1", "10116", "protein_xref_mgi_homologset", "45931594" ], [ "45922863", "Q9CR42-1", "10090", "protein_xref_mgi_homologset", "45922863" ], [ "45922863", "Q15327-1", "9606", "protein_xref_mgi_homologset", "45922863" ], [ "45922863", "Q8R560-1", "10116", "protein_xref_mgi_homologset", "45922863" ], [ "45923821", "Q8CHB8-1", "10090", "protein_xref_mgi_homologset", "45923821" ], [ "45923821", "Q6EMB2-1", "9606", "protein_xref_mgi_homologset", "45923821" ], [ "45931595", "Q0GGX2-1", "10090", "protein_xref_mgi_homologset", "45931595" ] ] }, "readme": "Name\n - Homolog Clusters\n\nVersion\n - v-2.4.1\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], Luke Johnson [luke.johnson@email.gwu.edu], Urnisha Bhuiyan [sbhuiyan28@email.gwu.edu], Cyrus Au-Yeung [cyruschauyeung@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-2.4.1/compiled/protein_homolog_clusters.csv\n Name: dicty_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_protein_transcriptlocus.csv\n Name: dicty_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_protein_xref_geneid.csv\n Name: dicty_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/dicty_protein_xref_oma.csv\n Name: fruitfly_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_transcriptlocus.csv\n Name: fruitfly_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_xref_geneid.csv\n Name: fruitfly_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/fruitfly_protein_xref_oma.csv\n Name: human_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_protein_transcriptlocus.csv\n Name: human_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_protein_xref_geneid.csv\n Name: human_protein_xref_hgnc.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_protein_xref_hgnc.csv\n Name: human_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/human_protein_xref_oma.csv\n Name: mouse_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/mouse_protein_transcriptlocus.csv\n Name: mouse_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/mouse_protein_xref_geneid.csv\n Name: mouse_protein_xref_mgi.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/mouse_protein_xref_mgi.csv\n Name: mouse_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/mouse_protein_xref_oma.csv\n Name: pig_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_transcriptlocus.csv\n Name: pig_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_xref_geneid.csv\n Name: pig_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/pig_protein_xref_oma.csv\n Name: rat_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_transcriptlocus.csv\n Name: rat_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_xref_geneid.csv\n Name: rat_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/rat_protein_xref_oma.csv\n Name: sarscov1_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/sarscov1_protein_xref_geneid.csv\n Name: sarscov2_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/sarscov2_protein_xref_geneid.csv\n Name: yeast_protein_transcriptlocus.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/yeast_protein_transcriptlocus.csv\n Name: yeast_protein_xref_geneid.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/yeast_protein_xref_geneid.csv\n Name: yeast_protein_xref_oma.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/yeast_protein_xref_oma.csv\n Name: mgi_homologs.tsv\n URI: https:/data.glygen.org/ln2downloads/mgi/2024_01_31/mgi_homologs.tsv\n Name: dicty_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_fruitfly_oma_orthologs.txt\n Name: dicty_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_human_oma_orthologs.txt\n Name: dicty_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_mouse_oma_orthologs.txt\n Name: dicty_pig_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_pig_oma_orthologs.txt\n Name: dicty_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_rat_oma_orthologs.txt\n Name: dicty_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/dicty_yeast_oma_orthologs.txt\n Name: fruitfly_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_dicty_oma_orthologs.txt\n Name: fruitfly_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_human_oma_orthologs.txt\n Name: fruitfly_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_mouse_oma_orthologs.txt\n Name: fruitfly_pig_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_pig_oma_orthologs.txt\n Name: fruitfly_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_rat_oma_orthologs.txt\n Name: fruitfly_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/fruitfly_yeast_oma_orthologs.txt\n Name: human_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_dicty_oma_orthologs.txt\n Name: human_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_fruitfly_oma_orthologs.txt\n Name: human_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_mouse_oma_orthologs.txt\n Name: human_pig_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_pig_oma_orthologs.txt\n Name: human_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_rat_oma_orthologs.txt\n Name: human_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/human_yeast_oma_orthologs.txt\n Name: mouse_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/mouse_dicty_oma_orthologs.txt\n Name: mouse_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/mouse_fruitfly_oma_orthologs.txt\n Name: mouse_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/mouse_human_oma_orthologs.txt\n Name: mouse_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/mouse_rat_oma_orthologs.txt\n Name: mouse_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/mouse_yeast_oma_orthologs.txt\n Name: pig_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_dicty_oma_orthologs.txt\n Name: pig_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_fruitfly_oma_orthologs.txt\n Name: pig_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_human_oma_orthologs.txt\n Name: pig_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_mouse_oma_orthologs.txt\n Name: pig_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_rat_oma_orthologs.txt\n Name: pig_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/pig_yeast_oma_orthologs.txt\n Name: rat_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_dicty_oma_orthologs.txt\n Name: rat_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_fruitfly_oma_orthologs.txt\n Name: rat_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_human_oma_orthologs.txt\n Name: rat_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_mouse_oma_orthologs.txt\n Name: rat_pig_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_pig_oma_orthologs.txt\n Name: rat_yeast_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/rat_yeast_oma_orthologs.txt\n Name: yeast_dicty_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_dicty_oma_orthologs.txt\n Name: yeast_fruitfly_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_fruitfly_oma_orthologs.txt\n Name: yeast_human_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_human_oma_orthologs.txt\n Name: yeast_mouse_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_mouse_oma_orthologs.txt\n Name: yeast_pig_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_pig_oma_orthologs.txt\n Name: yeast_rat_oma_orthologs.txt\n URI: https:/data.glygen.org/ln2downloads/oma/2024_02_13/yeast_rat_oma_orthologs.txt\n Output Subdomain\n Name: protein_homolog_clusters.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/protein_homolog_clusters.csv\n Name: protein_homolog_clusters.stat.csv\n URI: https:/data.glygen.org/ln2releases/data/v-2.4.1/reviewed/protein_homolog_clusters.stat.csv\n\nFields\n Name: \"homolog_cluster_id\"\n Description: \"NA\"\n Unique Values: \"37636\"\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"63186\"\n Name: \"tax_id\"\n Description: \"NCBI Taxonomy database Identifier\"\n Unique Values: \"10\"\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: \"37635\"", "downloadurl": "/ln2data/releases/data/v-2.4.1/reviewed/protein_homolog_clusters.csv" }