{"id":"https://openalex.org/W1977027195","doi":"https://doi.org/10.1093/nar/gkj123","title":"OrthoMCL-DB: querying a comprehensive multi-species collection of ortholog groups","display_name":"OrthoMCL-DB: querying a comprehensive multi-species collection of ortholog groups","publication_year":2005,"publication_date":"2005-12-28","ids":{"openalex":"https://openalex.org/W1977027195","doi":"https://doi.org/10.1093/nar/gkj123","mag":"1977027195","pmid":"https://pubmed.ncbi.nlm.nih.gov/16381887"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkj123","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkj123","pdf_url":"https://academic.oup.com/nar/article-pdf/34/suppl_1/D363/3925910/gkj123.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":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":"gold","oa_url":"https://academic.oup.com/nar/article-pdf/34/suppl_1/D363/3925910/gkj123.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100352749","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-3508-8834"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"F. Chen","raw_affiliation_strings":["Department of Chemistry, Center for Bioinformatics, Penn Genomics Institute, University of Pennsylvania, Philadelphia, PA 19104-6018, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Center for Bioinformatics, Penn Genomics Institute, University of Pennsylvania, Philadelphia, PA 19104-6018, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100352749"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":{"value":3630,"currency":"USD","value_usd":3630},"fwci":9.2499,"has_fulltext":true,"cited_by_count":933,"citation_normalized_percentile":{"value":0.98782475,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"90001","first_page":"D363","last_page":"D368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9998999834060669,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.9121705889701843},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5562435388565063},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.47892317175865173},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.4652109444141388},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4630439877510071},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.40711748600006104},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1996523141860962},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15725168585777283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.07987388968467712}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.9121705889701843},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5562435388565063},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.47892317175865173},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4652109444141388},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4630439877510071},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.40711748600006104},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1996523141860962},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15725168585777283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.07987388968467712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"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":"D000818","descriptor_name":"Animals","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":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/nar/gkj123","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkj123","pdf_url":"https://academic.oup.com/nar/article-pdf/34/suppl_1/D363/3925910/gkj123.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":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:16381887","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16381887","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:CiteSeerX.psu:10.1.1.276.5024","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.276.5024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ncbi.nlm.nih.gov/pub/pmc/48/2a/Nucleic_Acids_Res_2006_Jan_1_34(Database_issue)_D363-D368.tar.gz","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:1347485","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1347485","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"Text"}],"best_oa_location":{"id":"doi:10.1093/nar/gkj123","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkj123","pdf_url":"https://academic.oup.com/nar/article-pdf/34/suppl_1/D363/3925910/gkj123.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":true,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3406993978","display_name":null,"funder_award_id":"HHSN266200400037C","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G4528626165","display_name":null,"funder_award_id":"R01 AI058515","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G5808456229","display_name":null,"funder_award_id":"R01-AI058515","funder_id":"https://openalex.org/F4320337355","funder_display_name":"National Institute of Allergy and Infectious Diseases"},{"id":"https://openalex.org/G6054765826","display_name":null,"funder_award_id":"HHSN266200400037C","funder_id":"https://openalex.org/F4320332177","funder_display_name":"Agency for Healthcare Research and Quality"}],"funders":[{"id":"https://openalex.org/F4320306135","display_name":"Ellison Medical Foundation","ror":"https://ror.org/01pqy3846"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332177","display_name":"Agency for Healthcare Research and Quality","ror":"https://ror.org/03jmfdf59"},{"id":"https://openalex.org/F4320337355","display_name":"National Institute of Allergy and Infectious Diseases","ror":"https://ror.org/043z4tv69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1977027195.pdf","grobid_xml":"https://content.openalex.org/works/W1977027195.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1519987066","https://openalex.org/W1659313070","https://openalex.org/W1973316812","https://openalex.org/W1990453950","https://openalex.org/W2008856488","https://openalex.org/W2010562878","https://openalex.org/W2021064499","https://openalex.org/W2044145517","https://openalex.org/W2068687524","https://openalex.org/W2121564430","https://openalex.org/W2124166542","https://openalex.org/W2132926880","https://openalex.org/W2141885858","https://openalex.org/W2155606054","https://openalex.org/W2167188257","https://openalex.org/W3095583226","https://openalex.org/W3199943451","https://openalex.org/W4210400672","https://openalex.org/W4229899734","https://openalex.org/W4251079740"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2086525401","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254"],"abstract_inverted_index":{"The":[0,89],"OrthoMCL":[1,44,162],"database":[2,91],"(http://orthomcl.cbil.upenn.edu)":[3],"houses":[4],"ortholog":[5,87,90,131],"group":[6,99],"predictions":[7],"for":[8,130,174,181],"55":[9],"species,":[10,186],"including":[11],"16":[12],"bacterial":[13],"and":[14,22,40,70,142,150,155,169,187,191],"4":[15,38],"archaeal":[16],"genomes":[17],"representing":[18],"phylogenetically":[19],"diverse":[20],"lineages,":[21],"most":[23],"currently":[24],"available":[25,173],"complete":[26],"eukaryotic":[27],"genomes:":[28],"24":[29],"unikonts":[30],"(12":[31],"animals,":[32],"9":[33],"fungi,":[34],"microsporidium,":[35],"Dictyostelium,":[36],"Entamoeba),":[37],"plants/algae":[39],"7":[41],"apicomplexan":[42],"parasites.":[43],"software":[45],"was":[46],"used":[47],"to":[48],"cluster":[49],"proteins":[50,77,141],"based":[51,95],"on":[52,96],"sequence":[53,145,196],"similarity,":[54],"using":[55,117],"an":[56],"all-against-all":[57],"BLAST":[58,105],"search":[59],"of":[60,67,75,79,139,153,159],"each":[61],"species'":[62],"proteome,":[63],"followed":[64],"by":[65],"normalization":[66],"inter-species":[68],"differences,":[69],"Markov":[71],"clustering.":[72],"A":[73],"total":[74,81],"511,797":[76],"(81.6%":[78],"the":[80,134,137,164],"dataset)":[82],"were":[83],"clustered":[84],"into":[85],"70,388":[86],"groups.":[88],"may":[92,113],"be":[93,115,189],"queried":[94],"protein":[97],"or":[98,104,122],"accession":[100],"numbers,":[101],"keyword":[102],"descriptions":[103],"similarity.":[106],"Ortholog":[107],"groups":[108,132],"exhibiting":[109],"specific":[110],"phyletic":[111,135],"patterns":[112],"also":[114],"identified,":[116],"either":[118],"a":[119,123,143,147,156,178],"graphical":[120,151,157],"interface":[121],"text-based":[124],"Phyletic":[125],"Pattern":[126],"Expression":[127],"grammar.":[128],"Information":[129],"includes":[133],"profile,":[136],"list":[138],"member":[140],"multiple":[144,185],"alignment,":[146],"statistical":[148],"summary":[149],"view":[152],"similarities,":[154],"representation":[158],"domain":[160],"architecture.":[161],"software,":[163],"entire":[165],"FASTA":[166],"dataset":[167],"employed":[168],"clustering":[170],"results":[171],"are":[172],"download.":[175],"OrthoMCL-DB":[176],"provides":[177],"centralized":[179],"warehouse":[180],"orthology":[182],"prediction":[183],"among":[184],"will":[188],"updated":[190],"expanded":[192],"as":[193],"additional":[194],"genome":[195],"data":[197],"become":[198],"available.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":62},{"year":2019,"cited_by_count":44},{"year":2018,"cited_by_count":62},{"year":2017,"cited_by_count":71},{"year":2016,"cited_by_count":58},{"year":2015,"cited_by_count":62},{"year":2014,"cited_by_count":60},{"year":2013,"cited_by_count":64},{"year":2012,"cited_by_count":57}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}