{"id":"https://openalex.org/W2062372788","doi":"https://doi.org/10.1089/10665270260518254","title":"Occurrence Probability of Structured Motifs in Random Sequences","display_name":"Occurrence Probability of Structured Motifs in Random Sequences","publication_year":2002,"publication_date":"2002-12-01","ids":{"openalex":"https://openalex.org/W2062372788","doi":"https://doi.org/10.1089/10665270260518254","mag":"2062372788","pmid":"https://pubmed.ncbi.nlm.nih.gov/12614545"},"language":"en","primary_location":{"id":"doi:10.1089/10665270260518254","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270260518254","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5083513343","display_name":"Stephane S. Robin","orcid":null},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S. Robin","raw_affiliation_strings":["INA-PG / INRA, UMR Biom\u00e9trie et Intelligence Artificielle, 16, rue Claude Bernard, F-75005 Paris, France;INRA, Unit\u00e9 Math\u00e9matique, Informatique          and G\u00e9nome, F-78026 Versailles Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INA-PG / INRA, UMR Biom\u00e9trie et Intelligence Artificielle, 16, rue Claude Bernard, F-75005 Paris, France;INRA, Unit\u00e9 Math\u00e9matique, Informatique          and G\u00e9nome, F-78026 Versailles Cedex, France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104534588","display_name":"J.J. Daudin","orcid":null},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-J. Daudin","raw_affiliation_strings":["INA-PG / INRA, UMR Biom\u00e9trie et Intelligence Artificielle, 16, rue Claude Bernard, F-75005 Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INA-PG / INRA, UMR Biom\u00e9trie et Intelligence Artificielle, 16, rue Claude Bernard, F-75005 Paris, France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087944743","display_name":"Hugues Richard","orcid":"https://orcid.org/0000-0001-7776-1340"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"H. Richard","raw_affiliation_strings":["CNRS-UPRESA 8071, Laboratoire Statistique et G\u00e9nomes, 523, place des Terrasses de l'Agora, Tour Evry 2, F-9100 \u00c9vry, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS-UPRESA 8071, Laboratoire Statistique et G\u00e9nomes, 523, place des Terrasses de l'Agora, Tour Evry 2, F-9100 \u00c9vry, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111353768","display_name":"M.-F. Sagot","orcid":null},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210135640","display_name":"Laboratoire de Biom\u00e9trie et Biologie Evolutive","ror":"https://ror.org/03skt0t88","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I203339264","https://openalex.org/I4210100596","https://openalex.org/I4210104684","https://openalex.org/I4210107625","https://openalex.org/I4210135640"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"M.-F. Sagot","raw_affiliation_strings":["INRIA Rh\u00f4nes-Alpes, Laboratoire de Biom\u00e9trie \u00c9volutive, University Claude Bernard, 43 bd du 11 novembre 16918, F-69622, Villeurbanes cedex,          France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Rh\u00f4nes-Alpes, Laboratoire de Biom\u00e9trie \u00c9volutive, University Claude Bernard, 43 bd du 11 novembre 16918, F-69622, Villeurbanes cedex,          France","institution_ids":["https://openalex.org/I4210135640","https://openalex.org/I1326498283","https://openalex.org/I100532134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068389518","display_name":"Sophie Schbath","orcid":"https://orcid.org/0000-0003-3574-8222"},"institutions":[{"id":"https://openalex.org/I4210159481","display_name":"Math\u00e9matiques et Informatique Appliqu\u00e9es du G\u00e9nome \u00e0 l'Environnement","ror":"https://ror.org/05qdnns64","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210088668","https://openalex.org/I4210159481"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"S. Schbath","raw_affiliation_strings":["INRA, Unit\u00e9 Math\u00e9matique, Informatique and G\u00e9nome, F-78026 Versailles Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRA, Unit\u00e9 Math\u00e9matique, Informatique and G\u00e9nome, F-78026 Versailles Cedex, France","institution_ids":["https://openalex.org/I4210159481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9205,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.73081942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"6","first_page":"761","last_page":"773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9994999766349792,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9994999766349792,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9983999729156494,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9983999729156494,"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/sequence-motif","display_name":"Sequence motif","score":0.5709857940673828},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.5621492862701416},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5055861473083496},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.4530694782733917},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4461280107498169},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4369143843650818},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4191567897796631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3679593503475189},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.320914626121521},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2980141341686249},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15039488673210144},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11683019995689392},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07105621695518494}],"concepts":[{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5709857940673828},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.5621492862701416},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5055861473083496},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.4530694782733917},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4461280107498169},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4369143843650818},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4191567897796631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3679593503475189},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.320914626121521},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2980141341686249},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15039488673210144},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11683019995689392},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07105621695518494},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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":"D001412","descriptor_name":"Bacillus subtilis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001412","descriptor_name":"Bacillus subtilis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001412","descriptor_name":"Bacillus subtilis","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"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":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011401","descriptor_name":"Promoter Regions, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014158","descriptor_name":"Transcription, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1089/10665270260518254","is_oa":false,"landing_page_url":"https://doi.org/10.1089/10665270260518254","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:12614545","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12614545","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":"Journal of computational biology : a journal of computational molecular cell biology","raw_type":null},{"id":"pmh:oai:HAL:hal-00427461v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00427461","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Computational Biology, 2002, 9 (6), pp.761-773. &#x27E8;10.1089/10665270260518254&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:HAL:hal-02682672v1","is_oa":false,"landing_page_url":"https://hal.inrae.fr/hal-02682672","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1066-5277","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1509938542","https://openalex.org/W1542835570","https://openalex.org/W1985986400","https://openalex.org/W2021809202","https://openalex.org/W2045894772","https://openalex.org/W2054984882","https://openalex.org/W2096041943","https://openalex.org/W2147055980","https://openalex.org/W2162114340","https://openalex.org/W2332523405","https://openalex.org/W2610179052","https://openalex.org/W2611477341"],"related_works":["https://openalex.org/W3170299350","https://openalex.org/W2073661767","https://openalex.org/W2152844235","https://openalex.org/W2376454312","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2159636084","https://openalex.org/W2610941444"],"abstract_inverted_index":{"The":[0],"problem":[1],"of":[2,7,46,69,72,74,85,104],"extracting":[3],"from":[4],"a":[5,52,76,80],"set":[6],"nucleic":[8],"acid":[9],"sequences":[10],"motifs":[11,30],"which":[12],"may":[13,32],"have":[14],"biological":[15],"function":[16],"is":[17,98],"more":[18,20],"and":[19,55,95],"important.":[21],"In":[22,59],"this":[23],"paper,":[24],"we":[25,66],"are":[26,44],"interested":[27],"in":[28,35,79,92],"particular":[29],"that":[31],"be":[33],"implicated":[34],"the":[36,70,102,105],"transcription":[37],"process.":[38],"These":[39],"motifs,":[40,43],"called":[41],"structured":[42,77],"composed":[45],"two":[47],"ordered":[48],"parts":[49],"separated":[50],"by":[51],"variable":[53],"distance":[54],"allowing":[56],"for":[57],"substitutions.":[58],"order":[60],"to":[61,88],"assess":[62],"their":[63],"statistical":[64],"significance,":[65],"propose":[67],"approximations":[68],"probability":[71],"occurrences":[73],"such":[75],"motif":[78],"given":[81],"sequence.":[82],"An":[83],"application":[84],"our":[86],"method":[87],"evaluate":[89],"candidate":[90],"promoters":[91],"E.":[93],"coli":[94],"B.":[96],"subtilis":[97],"presented.":[99],"Simulations":[100],"show":[101],"goodness":[103],"approximations.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
