{"id":"https://openalex.org/W2169929748","doi":"https://doi.org/10.1093/nar/29.1.22","title":"The COG database: new developments in phylogenetic classification of proteins from complete genomes","display_name":"The COG database: new developments in phylogenetic classification of proteins from complete genomes","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2169929748","doi":"https://doi.org/10.1093/nar/29.1.22","mag":"2169929748","pmid":"https://pubmed.ncbi.nlm.nih.gov/11125040"},"language":"en","primary_location":{"id":"doi:10.1093/nar/29.1.22","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/29.1.22","pdf_url":"https://academic.oup.com/nar/article-pdf/29/1/22/9905132/290022.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/nar/article-pdf/29/1/22/9905132/290022.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055758002","display_name":"Roman L. Tatusov","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. L. Tatusov","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055758002"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":null,"fwci":52.7563,"has_fulltext":false,"cited_by_count":1904,"citation_normalized_percentile":{"value":0.99976977,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"1","first_page":"22","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.8544121980667114},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.788112461566925},{"id":"https://openalex.org/keywords/cog","display_name":"Cog","score":0.6135818958282471},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.5763593912124634},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5740487575531006},{"id":"https://openalex.org/keywords/archaea","display_name":"Archaea","score":0.5201140642166138},{"id":"https://openalex.org/keywords/caenorhabditis-elegans","display_name":"Caenorhabditis elegans","score":0.514947235584259},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.47264522314071655},{"id":"https://openalex.org/keywords/phylogenetics","display_name":"Phylogenetics","score":0.4328545331954956},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3208500146865845},{"id":"https://openalex.org/keywords/bacteria","display_name":"Bacteria","score":0.21654611825942993},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1533891260623932}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.8544121980667114},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.788112461566925},{"id":"https://openalex.org/C4661277","wikidata":"https://www.wikidata.org/wiki/Q1054157","display_name":"Cog","level":2,"score":0.6135818958282471},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5763593912124634},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5740487575531006},{"id":"https://openalex.org/C550995028","wikidata":"https://www.wikidata.org/wiki/Q10872","display_name":"Archaea","level":3,"score":0.5201140642166138},{"id":"https://openalex.org/C2778944004","wikidata":"https://www.wikidata.org/wiki/Q91703","display_name":"Caenorhabditis elegans","level":3,"score":0.514947235584259},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.47264522314071655},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.4328545331954956},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3208500146865845},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.21654611825942993},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1533891260623932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001105","descriptor_name":"Archaea","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004331","descriptor_name":"Drosophila melanogaster","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/nar/29.1.22","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/29.1.22","pdf_url":"https://academic.oup.com/nar/article-pdf/29/1/22/9905132/290022.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:11125040","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11125040","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic acids research","raw_type":null},{"id":"pmh:oai:europepmc.org:280217","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC29819","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:29819","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:29819","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/29819","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Res","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/nar/29.1.22","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/29.1.22","pdf_url":"https://academic.oup.com/nar/article-pdf/29/1/22/9905132/290022.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2169929748.pdf","grobid_xml":"https://content.openalex.org/works/W2169929748.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W207833169","https://openalex.org/W1542719686","https://openalex.org/W1988710574","https://openalex.org/W1990453950","https://openalex.org/W2133790733","https://openalex.org/W2141515295","https://openalex.org/W2141652419","https://openalex.org/W2148640876","https://openalex.org/W2158714788","https://openalex.org/W2159266221","https://openalex.org/W4230501579"],"related_works":["https://openalex.org/W2174809885","https://openalex.org/W2883025420","https://openalex.org/W2057191541","https://openalex.org/W2949296710","https://openalex.org/W1992658754","https://openalex.org/W2111939425","https://openalex.org/W2065083790","https://openalex.org/W2604174992","https://openalex.org/W2375383082","https://openalex.org/W1974895455"],"abstract_inverted_index":{"The":[0,85],"database":[1,92],"of":[2,4,7,18,27,37,63,108,124],"Clusters":[3],"Orthologous":[5],"Groups":[6],"proteins":[8,20,33,58,118],"(COGs),":[9],"which":[10,57],"represents":[11],"an":[12],"attempt":[13],"on":[14,101],"a":[15,49],"phylogenetic":[16],"classification":[17,123],"the":[19,41,52,61,67,72,90,109,120],"encoded":[21,59],"in":[22,56,60],"complete":[23],"genomes,":[24],"currently":[25],"consists":[26],"2791":[28],"COGs":[29,53,127],"including":[30],"45":[31],"350":[32],"from":[34],"30":[35],"genomes":[36,62,125],"bacteria,":[38],"archaea":[39,82],"and":[40,71,77,98,104,122,126],"yeast":[42],"Saccharomyces":[43],"cerevisiae":[44],"(http://www.ncbi.nlm.nih.":[45],"gov/COG).":[46],"In":[47],"addition,":[48],"supplement":[50],"to":[51,89,115],"is":[54,113],"available,":[55],"two":[64],"multicellular":[65],"eukaryotes,":[66],"nematode":[68],"Caenorhabditis":[69],"elegans":[70],"fruit":[73],"fly":[74],"Drosophila":[75],"melanogaster,":[76],"shared":[78],"with":[79,96],"bacteria":[80],"and/or":[81],"were":[83],"included.":[84],"new":[86,117],"features":[87],"added":[88],"COG":[91,103],"include":[93],"information":[94],"pages":[95],"structural":[97],"functional":[99],"details":[100],"each":[102],"literature":[105],"references,":[106],"improvements":[107],"COGNITOR":[110],"program":[111],"that":[112],"used":[114],"fit":[116],"into":[119],"COGs,":[121],"constructed":[128],"by":[129],"using":[130],"principal":[131],"component":[132],"analysis.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":51},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":68},{"year":2021,"cited_by_count":80},{"year":2020,"cited_by_count":64},{"year":2019,"cited_by_count":64},{"year":2018,"cited_by_count":42},{"year":2017,"cited_by_count":62},{"year":2016,"cited_by_count":65},{"year":2015,"cited_by_count":78},{"year":2014,"cited_by_count":92},{"year":2013,"cited_by_count":69},{"year":2012,"cited_by_count":85}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
