{"id":"https://openalex.org/W2161965550","doi":"https://doi.org/10.1093/bioinformatics/bti628","title":"Combining phylogenetic motif discovery and motif clustering to predict co-regulated genes","display_name":"Combining phylogenetic motif discovery and motif clustering to predict co-regulated genes","publication_year":2005,"publication_date":"2005-08-16","ids":{"openalex":"https://openalex.org/W2161965550","doi":"https://doi.org/10.1093/bioinformatics/bti628","mag":"2161965550","pmid":"https://pubmed.ncbi.nlm.nih.gov/16105899"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3832/16840829/bti628.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3832/16840829/bti628.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038551920","display_name":"Shane T. Jensen","orcid":"https://orcid.org/0000-0003-0945-5725"},"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":"S. T. Jensen","raw_affiliation_strings":["Department of Statistics, The Wharton School, University of Pennsylvania, USA. stjensen@wharton.upenn.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, The Wharton School, University of Pennsylvania, USA. stjensen@wharton.upenn.edu","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090522460","display_name":"Lei Shen","orcid":"https://orcid.org/0000-0003-4040-8716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012820890","display_name":"Jun S. Liu","orcid":"https://orcid.org/0000-0002-4450-7239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. S. Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5038551920"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":2.7629,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.90572251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"20","first_page":"3832","last_page":"3839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.29319998621940613,"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":0.29319998621940613,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.17329999804496765,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.16110000014305115,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/motif","display_name":"Motif (music)","score":0.7857730388641357},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6821607351303101},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6368858814239502},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5666120648384094},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.555679440498352},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5392476320266724},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.5327610373497009},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5234032273292542},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5052128434181213},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4096240997314453},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4036550223827362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2988137900829315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19541257619857788}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.7857730388641357},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6821607351303101},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6368858814239502},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5666120648384094},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.555679440498352},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5392476320266724},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5327610373497009},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5234032273292542},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5052128434181213},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4096240997314453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4036550223827362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2988137900829315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19541257619857788},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D005786","descriptor_name":"Gene Expression Regulation","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3832/16840829/bti628.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16105899","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16105899","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":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti628","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti628","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/20/3832/16840829/bti628.pdf","source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1994755936","https://openalex.org/W2018527742","https://openalex.org/W2019896510","https://openalex.org/W2021606207","https://openalex.org/W2033776526","https://openalex.org/W2038774163","https://openalex.org/W2051867008","https://openalex.org/W2073850887","https://openalex.org/W2084908610","https://openalex.org/W2100889355","https://openalex.org/W2101291953","https://openalex.org/W2107268689","https://openalex.org/W2135221645","https://openalex.org/W2143670813","https://openalex.org/W2154165587","https://openalex.org/W2166064969","https://openalex.org/W2167188257","https://openalex.org/W2168786813","https://openalex.org/W2913066018","https://openalex.org/W4255582690"],"related_works":["https://openalex.org/W3170299350","https://openalex.org/W2073661767","https://openalex.org/W2143211236","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2159636084","https://openalex.org/W2610941444","https://openalex.org/W2117168988","https://openalex.org/W2154430121","https://openalex.org/W2103777723"],"abstract_inverted_index":{"MOTIVATION:":[0],"We":[1,69],"present":[2],"a":[3,30],"sequence-based":[4],"framework":[5,72],"and":[6,28,58,92,101,113,132],"algorithm":[7],"PHYLOCLUS":[8],"for":[9,121],"predicting":[10],"co-regulated":[11,75],"genes.":[12],"In":[13],"our":[14,71],"approach,":[15],"de":[16],"novo":[17],"discovery":[18,112],"methods":[19],"are":[20,46,95,104],"used":[21,36,120],"to":[22,37,65,73,110],"find":[23],"motifs":[24,91,117],"conserved":[25],"by":[26],"evolution":[27],"then":[29],"Bayesian":[31],"hierarchical":[32],"clustering":[33,50,114],"model":[34],"is":[35],"cluster":[38,64],"these":[39],"motifs,":[40],"thereby":[41],"grouping":[42],"together":[43],"genes":[44,76],"that":[45],"putatively":[47],"co-regulated.":[48],"Our":[49,89],"procedure":[51],"allows":[52],"both":[53],"the":[54,59,78,111],"number":[55],"of":[56,115],"clusters":[57,94,103],"motif":[60],"width":[61],"within":[62],"each":[63],"be":[66,119,136],"unknown.":[67],"RESULTS:":[68],"use":[70],"predict":[74],"in":[77,106],"bacterium":[79],"Bacillus":[80],"subtilis":[81],"using":[82,97],"six":[83],"other":[84],"closely":[85],"related":[86],"bacterial":[87],"species.":[88],"predicted":[90],"gene":[93],"validated":[96],"several":[98],"external":[99],"sources":[100],"significant":[102],"examined":[105],"detail.":[107],"An":[108],"extension":[109],"two-block":[116],"can":[118,135],"inference":[122],"about":[123],"synergistic":[124],"binding":[125],"relationships":[126],"between":[127],"transcription":[128],"factors.":[129],"AVAILABILITY:":[130],"Software":[131],"Supplementary":[133],"Materials":[134],"downloaded":[137],"at":[138],"http://stat.wharton.upenn.edu/~stjensen/research/phyloclus.html":[139],"or":[140],"http://www.fas.harvard.edu/~junliu/phyloclus.html":[141],"CONTACT:":[142],"stjensen@wharton.upenn.edu.":[143]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}
