{"id":"https://openalex.org/W2146270437","doi":"https://doi.org/10.1093/bioinformatics/bti123","title":"Operon prediction without a training set","display_name":"Operon prediction without a training set","publication_year":2004,"publication_date":"2004-11-11","ids":{"openalex":"https://openalex.org/W2146270437","doi":"https://doi.org/10.1093/bioinformatics/bti123","mag":"2146270437","pmid":"https://pubmed.ncbi.nlm.nih.gov/15539453"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti123","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti123","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046077040","display_name":"B. P. Westover","orcid":null},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B. P. Westover","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University St. Louis, MO 63130, USA","Department of Computer Science and Engineering, Washington University, St Louis, MO, 63130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University St. Louis, MO 63130, USA","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University, St Louis, MO, 63130, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080937008","display_name":"Jeremy Buhler","orcid":"https://orcid.org/0000-0002-4159-4226"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. D. Buhler","raw_affiliation_strings":["Department of Computer Science and Engineering, Washington University, St Louis, MO, 63130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Washington University, St Louis, MO, 63130, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040631615","display_name":"Justin L. Sonnenburg","orcid":"https://orcid.org/0000-0003-2299-6817"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. L. Sonnenburg","raw_affiliation_strings":["Department of Molecular Biology and Pharmacology and Center for Genome Sciences, Washington University School of Medicine St. Louis, MO 63108, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Biology and Pharmacology and Center for Genome Sciences, Washington University School of Medicine St. Louis, MO 63108, USA#TAB#","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063884903","display_name":"Jeffrey I. Gordon","orcid":"https://orcid.org/0000-0001-8304-3548"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. I. Gordon","raw_affiliation_strings":["Department of Molecular Biology and Pharmacology and Center for Genome Sciences, Washington University School of Medicine St. Louis, MO 63108, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Molecular Biology and Pharmacology and Center for Genome Sciences, Washington University School of Medicine St. Louis, MO 63108, USA#TAB#","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046077040"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":4.281,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.94628305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"7","first_page":"880","last_page":"888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.5012999773025513,"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"}},"topics":[{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.5012999773025513,"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"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.44589999318122864,"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":0.012299999594688416,"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/operon","display_name":"Operon","score":0.9403795003890991},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7561540007591248},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6069396734237671},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5996167659759521},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5983360409736633},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5053775906562805},{"id":"https://openalex.org/keywords/regulon","display_name":"Regulon","score":0.499755859375},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.48609209060668945},{"id":"https://openalex.org/keywords/bacterial-genome-size","display_name":"Bacterial genome size","score":0.44363927841186523},{"id":"https://openalex.org/keywords/genome-project","display_name":"Genome project","score":0.43284329771995544},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42075973749160767},{"id":"https://openalex.org/keywords/synteny","display_name":"Synteny","score":0.4119439125061035},{"id":"https://openalex.org/keywords/escherichia-coli","display_name":"Escherichia coli","score":0.2763471305370331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2546995282173157}],"concepts":[{"id":"https://openalex.org/C203075996","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operon","level":4,"score":0.9403795003890991},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7561540007591248},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6069396734237671},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5996167659759521},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5983360409736633},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5053775906562805},{"id":"https://openalex.org/C62361671","wikidata":"https://www.wikidata.org/wiki/Q1754612","display_name":"Regulon","level":4,"score":0.499755859375},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.48609209060668945},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.44363927841186523},{"id":"https://openalex.org/C89566754","wikidata":"https://www.wikidata.org/wiki/Q2273828","display_name":"Genome project","level":4,"score":0.43284329771995544},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42075973749160767},{"id":"https://openalex.org/C53702515","wikidata":"https://www.wikidata.org/wiki/Q971246","display_name":"Synteny","level":4,"score":0.4119439125061035},{"id":"https://openalex.org/C547475151","wikidata":"https://www.wikidata.org/wiki/Q25419","display_name":"Escherichia coli","level":3,"score":0.2763471305370331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2546995282173157},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001439","descriptor_name":"Bacteroides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001439","descriptor_name":"Bacteroides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001439","descriptor_name":"Bacteroides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009876","descriptor_name":"Operon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009876","descriptor_name":"Operon","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009876","descriptor_name":"Operon","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti123","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti123","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15539453","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15539453","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":"Comparative Study"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3889000384","display_name":null,"funder_award_id":"CDK30292","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1977854982","https://openalex.org/W2022846158","https://openalex.org/W2025853251","https://openalex.org/W2036847531","https://openalex.org/W2038437697","https://openalex.org/W2039700732","https://openalex.org/W2042045767","https://openalex.org/W2093342565","https://openalex.org/W2100332892","https://openalex.org/W2102498314","https://openalex.org/W2107337820","https://openalex.org/W2109621905","https://openalex.org/W2122614000","https://openalex.org/W2129149283","https://openalex.org/W2134599124","https://openalex.org/W2137141752","https://openalex.org/W2142418779","https://openalex.org/W2152824658","https://openalex.org/W2157865313","https://openalex.org/W2158714788"],"related_works":["https://openalex.org/W2132790938","https://openalex.org/W2171972144","https://openalex.org/W1796329565","https://openalex.org/W1976388816","https://openalex.org/W2004986663","https://openalex.org/W1544013284","https://openalex.org/W2038893582","https://openalex.org/W2141829569","https://openalex.org/W2032847418","https://openalex.org/W1526689651"],"abstract_inverted_index":{"MOTIVATION:":[0],"Annotation":[1],"of":[2,22,58,65,84,95,107,113,125,152,159,167,183,195,208,214],"operons":[3,66,85,109,207],"in":[4,12,29,44,67,104,110,175,223],"a":[5,30,55,82,117,122,149,153,176,192],"bacterial":[6],"genome":[7,112,161,213],"is":[8,121],"an":[9,14,136],"important":[10],"step":[11],"determining":[13],"organism's":[15],"transcriptional":[16],"regulatory":[17],"program.":[18],"While":[19],"extensive":[20,143],"studies":[21],"operon":[23,42,52,137],"structure":[24],"have":[25],"been":[26],"carried":[27],"out":[28],"few":[31],"species":[32,89],"such":[33,75],"as":[34],"Escherichia":[35],"coli,":[36],"fewer":[37],"resources":[38],"exist":[39],"to":[40,61,140,219],"inform":[41],"prediction":[43],"newly":[45,72],"sequenced":[46,73],"genomes.":[47],"In":[48],"particular,":[49],"many":[50],"extant":[51],"finders":[53],"require":[54],"large":[56],"body":[57],"training":[59,144],"examples":[60,76],"learn":[62],"the":[63,68,93,105,111,126,157,160,168,205,212,224],"properties":[64,94,158],"target":[69],"organism.":[70],"For":[71],"genomes,":[74],"are":[77],"generally":[78],"not":[79,91],"available;":[80],"moreover,":[81],"model":[83],"trained":[86],"on":[87,148,204,211],"one":[88],"may":[90],"reflect":[92],"other,":[96],"distantly":[97],"related":[98],"organisms.":[99],"We":[100,134,146,199],"encountered":[101],"these":[102],"issues":[103],"course":[106],"predicting":[108],"Bacteroides":[114],"thetaiotaomicron":[115],"(B.theta),":[116],"common":[118,177,188],"anaerobe":[119],"that":[120,164,170],"prominent":[123],"component":[124],"normal":[127],"adult":[128],"human":[129],"intestinal":[130],"microbial":[131],"community.":[132],"RESULTS:":[133],"describe":[135],"predictor":[138,202],"designed":[139],"work":[141],"without":[142],"data.":[145],"rely":[147],"small":[150],"set":[151],"priori":[154],"assumptions":[155],"about":[156],"being":[162],"annotated":[163],"permit":[165],"estimation":[166],"probability":[169],"two":[171],"adjacent":[172],"genes":[173],"lie":[174],"operon.":[178],"Predictions":[179],"integrate":[180],"several":[181],"sources":[182],"information,":[184],"including":[185],"intergenic":[186],"distance,":[187],"functional":[189],"annotation":[190],"and":[191,210],"novel":[193],"formulation":[194],"conserved":[196],"gene":[197],"order.":[198],"validate":[200],"our":[201,221],"both":[203],"known":[206],"E.coli":[209],"B.theta,":[215],"using":[216],"expression":[217],"data":[218],"evaluate":[220],"predictions":[222],"latter.":[225]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
