{"id":"https://openalex.org/W2021282293","doi":"https://doi.org/10.1073/pnas.112341999","title":"Identification of the binding sites of regulatory proteins in bacterial genomes","display_name":"Identification of the binding sites of regulatory proteins in bacterial genomes","publication_year":2002,"publication_date":"2002-08-14","ids":{"openalex":"https://openalex.org/W2021282293","doi":"https://doi.org/10.1073/pnas.112341999","mag":"2021282293","pmid":"https://pubmed.ncbi.nlm.nih.gov/12181488","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/129344"},"language":"en","primary_location":{"id":"doi:10.1073/pnas.112341999","doi":"https://doi.org/10.1073/pnas.112341999","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.112341999","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/129344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348508","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-8495-8467","observed_orcids":["https://orcid.org/0000-0001-8495-8467"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I83399316","display_name":"Rockefeller University","ror":"https://ror.org/0420db125","country_code":"US","type":"education","lineage":["https://openalex.org/I83399316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I83399316"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075657014","display_name":"Virgil A. Rhodius","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I83399316","display_name":"Rockefeller University","ror":"https://ror.org/0420db125","country_code":"US","type":"education","lineage":["https://openalex.org/I83399316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Virgil Rhodius","raw_affiliation_strings":["Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I83399316"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061964396","display_name":"Carol A. Gross","orcid":"https://orcid.org/0000-0002-5595-9732","observed_orcids":["https://orcid.org/0000-0002-5595-9732"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I83399316","display_name":"Rockefeller University","ror":"https://ror.org/0420db125","country_code":"US","type":"education","lineage":["https://openalex.org/I83399316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Gross","raw_affiliation_strings":["Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I83399316"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036408112","display_name":"Eric D. Siggia","orcid":"https://orcid.org/0000-0001-7482-1854","observed_orcids":["https://orcid.org/0000-0001-7482-1854"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I83399316","display_name":"Rockefeller University","ror":"https://ror.org/0420db125","country_code":"US","type":"education","lineage":["https://openalex.org/I83399316"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric D. Siggia","raw_affiliation_strings":["Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Biochemistry and Biophysics, and Department of Stomatology and Department of Microbiology and Immunology, University of California, 513 Parnassus Avenue, San Francisco, CA 94143; and Center for Studies in Physics and Biology, The Rockefeller University, Box 25, 1230 York Avenue, New York, NY 10021","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I83399316"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8276,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.93663511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"99","issue":"18","first_page":"11772","last_page":"11777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.5044000148773193,"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":0.5044000148773193,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.23899999260902405,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.21789999306201935,"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/transcription-factor-binding-sites","display_name":"transcription factor binding sites","score":0.9509999752044678},{"id":"https://openalex.org/keywords/bacterial-transcriptional-regulation","display_name":"bacterial transcriptional regulation","score":0.703000009059906},{"id":"https://openalex.org/keywords/escherichia-coli-genome","display_name":"Escherichia coli genome","score":0.8299999833106995},{"id":"https://openalex.org/keywords/regulon","display_name":"regulon","score":0.6399999856948853},{"id":"https://openalex.org/keywords/dna-binding-proteins","display_name":"DNA-binding proteins","score":0.699999988079071},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"multiple sequence alignment","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C62361671","wikidata":"https://www.wikidata.org/wiki/Q1754612","display_name":"Regulon","level":4,"score":0.9077523946762085},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6988183856010437},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6549136638641357},{"id":"https://openalex.org/C3742359","wikidata":"https://www.wikidata.org/wiki/Q4839988","display_name":"Bacterial genome size","level":4,"score":0.5875595211982727},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5843181610107422},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.5502656698226929},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.5215827822685242},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5083908438682556},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.46798941493034363},{"id":"https://openalex.org/C94966510","wikidata":"https://www.wikidata.org/wiki/Q2252764","display_name":"DNA-binding protein","level":4,"score":0.42618680000305176},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4201815724372864},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.35573774576187134},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.2722249925136566},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.09848353266716003}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004269","descriptor_name":"DNA, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1073/pnas.112341999","doi":"https://doi.org/10.1073/pnas.112341999","is_oa":false,"landing_page_url":"https://doi.org/10.1073/pnas.112341999","pdf_url":null,"source":{"id":"https://openalex.org/S125754415","display_name":"Proceedings of the National Academy of Sciences","issn_l":"0027-8424","issn":["0027-8424","1091-6490"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-a","doyens","erih-plus","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320052","host_organization_name":"National Academy of Sciences","host_organization_lineage":["https://openalex.org/P4310320052"],"host_organization_lineage_names":["National Academy of Sciences"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the National Academy of Sciences","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:129344","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/129344","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,"listed_in":[],"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":"Proc Natl Acad Sci U S A","raw_type":"Text"},{"id":"pmid:12181488","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12181488","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,"listed_in":[],"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":"Proceedings of the National Academy of Sciences of the United States of America","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:129344","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/129344","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,"listed_in":[],"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":"Proc Natl Acad Sci U S A","raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1691451501","display_name":"Theoretical Condensed Matter Physics","funder_award_id":"0129848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6314967280","display_name":"Mutational Analysis of E. Coli Core RNA Polymerase","funder_award_id":"R01GM057755","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G778556979","display_name":null,"funder_award_id":"GM 57755","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337367","display_name":"Division of Materials Research","ror":"https://ror.org/01pc7k308"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1214546200","https://openalex.org/W1498410508","https://openalex.org/W1509938542","https://openalex.org/W1512810258","https://openalex.org/W1956090332","https://openalex.org/W1975924111","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2005244073","https://openalex.org/W2022236187","https://openalex.org/W2032231928","https://openalex.org/W2062402656","https://openalex.org/W2070587756","https://openalex.org/W2071090620","https://openalex.org/W2072152345","https://openalex.org/W2079131652","https://openalex.org/W2084908610","https://openalex.org/W2088639752","https://openalex.org/W2126873530","https://openalex.org/W2134153749","https://openalex.org/W2136913687","https://openalex.org/W2142182986","https://openalex.org/W2147055980","https://openalex.org/W2150776759","https://openalex.org/W2150926065","https://openalex.org/W2154199509","https://openalex.org/W2159883877","https://openalex.org/W2168370822","https://openalex.org/W2168786813","https://openalex.org/W2611831635"],"related_works":["https://openalex.org/W2397114812","https://openalex.org/W2086496019","https://openalex.org/W7096114598","https://openalex.org/W2392984208","https://openalex.org/W1985924888","https://openalex.org/W2029368474","https://openalex.org/W1560191797","https://openalex.org/W2039286232","https://openalex.org/W1591821893","https://openalex.org/W2106542976"],"abstract_inverted_index":{"We":[0,134],"present":[1],"an":[2],"algorithm":[3,36,111,143,231],"that":[4,40],"extracts":[5],"the":[6,20,27,38,58,68,110,113,117,121,137,166,172,184,209,212,216,220],"binding":[7,167,191],"sites":[8,168,192],"(represented":[9],"by":[10,80,206],"position-specific":[11,131,157],"weight":[12,132,158],"matrices)":[13],"for":[14,29,234,240],"many":[15,41],"different":[16],"transcription":[17,176,197],"factors":[18,177],"from":[19],"regulatory":[21,104,228],"regions":[22,119],"of":[23,32,67,89,102,162,169,171,183,195,201,211,219],"a":[24,48,107,125],"genome,":[25],"without":[26],"need":[28],"delineating":[30],"groups":[31,85],"coregulated":[33],"genes.":[34],"The":[35,199,230],"uses":[37],"fact":[39],"DNA-binding":[42],"proteins":[43],"in":[44,120],"bacteria":[45],"bind":[46],"to":[47,97,129,153,189,225],"bipartite":[49],"motif":[50],"with":[51,141,178],"two":[52,76],"short":[53,77],"segments":[54],"more":[55],"conserved":[56],"than":[57],"intervening":[59],"region.":[60],"It":[61],"identifies":[62],"all":[63],"statistically":[64],"significant":[65,148],"patterns":[66],"form":[69],"W(1)N(x)W(2),":[70],"where":[71],"W(1)":[72],"and":[73,84,123,144,193,215],"W(2)":[74],"are":[75,94,187],"oligonucleotides":[78],"separated":[79],"x":[81],"arbitrary":[82],"bases,":[83],"them":[86],"into":[87],"clusters":[88,93],"similar":[90],"patterns.":[91],"These":[92],"then":[95],"used":[96],"derive":[98,130],"quantitative":[99],"recognition":[100],"profiles":[101],"putative":[103,227],"proteins.":[105],"For":[106],"given":[108],"cluster,":[109],"finds":[112],"matching":[114],"sequences":[115],"plus":[116],"flanking":[118],"genome":[122,140],"performs":[124],"multiple":[126],"sequence":[127],"alignment":[128],"matrices.":[133,159],"have":[135],"analyzed":[136],"Escherichia":[138],"coli":[139],"this":[142],"found":[145],"approximately":[146,154,173],"1,500":[147],"patterns,":[149],"which":[150,241],"give":[151],"rise":[152],"160":[155],"distinct":[156],"A":[160],"fraction":[161],"these":[163,202],"matrices":[164,186,203],"match":[165],"one-third":[170],"60":[174],"characterized":[175],"high":[179],"statistical":[180],"significance.":[181],"Many":[182],"remaining":[185],"likely":[188],"describe":[190],"regulons":[194],"uncharacterized":[196],"factors.":[198],"significance":[200],"was":[204],"evaluated":[205],"their":[207],"specificity,":[208],"location":[210],"predicted":[213],"sites,":[214],"biological":[217],"functions":[218],"corresponding":[221],"regulons,":[222],"allowing":[223],"us":[224],"suggest":[226],"functions.":[229],"is":[232,243],"efficient":[233],"analyzing":[235],"newly":[236],"sequenced":[237],"bacterial":[238],"genomes":[239],"little":[242],"known":[244],"about":[245],"transcriptional":[246],"regulation.":[247]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}