{"id":"https://openalex.org/W2125723560","doi":"https://doi.org/10.1093/bioinformatics/btn525","title":"Faster exact Markovian probability functions for motif occurrences: a DFA-only approach","display_name":"Faster exact Markovian probability functions for motif occurrences: a DFA-only approach","publication_year":2008,"publication_date":"2008-10-09","ids":{"openalex":"https://openalex.org/W2125723560","doi":"https://doi.org/10.1093/bioinformatics/btn525","mag":"2125723560","pmid":"https://pubmed.ncbi.nlm.nih.gov/18845582"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn525","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn525","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/24/2839/49056491/bioinformatics_24_24_2839.pdf","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":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/24/2839/49056491/bioinformatics_24_24_2839.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031469755","display_name":"Paolo Ribeca","orcid":"https://orcid.org/0000-0001-5599-3933"},"institutions":[{"id":"https://openalex.org/I4210137962","display_name":"Centre for Genomic Regulation","ror":"https://ror.org/03wyzt892","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210132884","https://openalex.org/I4210137962","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Paolo Ribeca","raw_affiliation_strings":["Bioinformatics and Genomics Unit, Center for Genomic Regulation, C/ Dr.Aiguader 88, E08003 Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics Unit, Center for Genomic Regulation, C/ Dr.Aiguader 88, E08003 Barcelona, Spain","institution_ids":["https://openalex.org/I4210137962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058015129","display_name":"Emanuele Raineri","orcid":"https://orcid.org/0000-0003-1932-311X"},"institutions":[{"id":"https://openalex.org/I4210137962","display_name":"Centre for Genomic Regulation","ror":"https://ror.org/03wyzt892","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210132884","https://openalex.org/I4210137962","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Emanuele Raineri","raw_affiliation_strings":["Bioinformatics and Genomics Unit, Center for Genomic Regulation, C/ Dr.Aiguader 88, E08003 Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Genomics Unit, Center for Genomic Regulation, C/ Dr.Aiguader 88, E08003 Barcelona, Spain","institution_ids":["https://openalex.org/I4210137962"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031469755"],"corresponding_institution_ids":["https://openalex.org/I4210137962"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":5.2533,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95270645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"24","issue":"24","first_page":"2839","last_page":"2848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.243599995970726,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.243599995970726,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.23000000417232513,"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/T12162","display_name":"Cellular Automata and Applications","score":0.0737999975681305,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6225691437721252},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.573901355266571},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.498307466506958},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.49262839555740356},{"id":"https://openalex.org/keywords/cellular-automaton","display_name":"Cellular automaton","score":0.47485780715942383},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4637497067451477},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44486480951309204},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4428861439228058},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33411169052124023},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1622609794139862},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09245383739471436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6225691437721252},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.573901355266571},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.498307466506958},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.49262839555740356},{"id":"https://openalex.org/C35527583","wikidata":"https://www.wikidata.org/wiki/Q189156","display_name":"Cellular automaton","level":2,"score":0.47485780715942383},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4637497067451477},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44486480951309204},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4428861439228058},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33411169052124023},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1622609794139862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09245383739471436}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008390","descriptor_name":"Markov Chains","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020816","descriptor_name":"Amino Acid Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btn525","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn525","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/24/2839/49056491/bioinformatics_24_24_2839.pdf","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:18845582","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18845582","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},{"id":"pmh:oai:arXiv.org:0801.3675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0801.3675","pdf_url":"https://arxiv.org/pdf/0801.3675","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn525","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn525","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/24/2839/49056491/bioinformatics_24_24_2839.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2125723560.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1592870802","https://openalex.org/W1979353384","https://openalex.org/W1990987722","https://openalex.org/W2002220902","https://openalex.org/W2011079334","https://openalex.org/W2102122585","https://openalex.org/W2102182691","https://openalex.org/W2107901234","https://openalex.org/W2111322461","https://openalex.org/W2148315211","https://openalex.org/W2159507861","https://openalex.org/W2163964760","https://openalex.org/W2167281811","https://openalex.org/W2170120409","https://openalex.org/W2225480587","https://openalex.org/W2510854709","https://openalex.org/W2970344678","https://openalex.org/W4296472334","https://openalex.org/W4298365428","https://openalex.org/W4390808053","https://openalex.org/W6635200387"],"related_works":["https://openalex.org/W2164619678","https://openalex.org/W2113544496","https://openalex.org/W2360313292","https://openalex.org/W1669105318","https://openalex.org/W2067777412","https://openalex.org/W2359527201","https://openalex.org/W2353714615","https://openalex.org/W9202957","https://openalex.org/W2370307662","https://openalex.org/W3091867061"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"computation":[2],"of":[3,7,55,87,106,112,117,127,153,164,175,181,198,224,230,297,313],"the":[4,33,43,56,85,104,108,113,129,136,151,158,162,172,176,202,228,272,311,314],"statistical":[5,295],"properties":[6],"motif":[8,45,120],"occurrences":[9,166],"has":[10],"an":[11,93,279],"obviously":[12],"relevant":[13,110],"application:":[14],"patterns":[15],"that":[16,58,197],"are":[17,26,73,77,216,220,243],"significantly":[18],"over-":[19],"or":[20,24,160,186,190,255],"under-represented":[21],"in":[22,53,84,121,157,210,234],"genomes":[23,300],"proteins":[25],"interesting":[27,70],"candidates":[28],"for":[29,178,227,293],"biological":[30],"roles.":[31],"However,":[32],"problem":[34,105],"is":[35,144,167,193,282],"computationally":[36],"hard;":[37],"as":[38,246,304],"a":[39,118,122,221,247,252,258],"result,":[40],"virtually":[41],"all":[42],"existing":[44],"finders":[46],"use":[47],"fast":[48],"but":[49,75,240],"approximate":[50,214],"scoring":[51],"functions,":[52],"spite":[54],"fact":[57],"they":[59,76,242],"have":[60],"been":[61],"shown":[62],"to":[63,103,150,208,250,256,270,277],"produce":[64],"systematically":[65],"incorrect":[66],"results.":[67],"A":[68],"few":[69],"exact":[71,94,205,294],"approaches":[72],"known,":[74],"very":[78,298],"slow":[79],"and":[80,286,301],"hence":[81],"not":[82,145],"practical":[83],"case":[86],"realistic":[88],"sequences.":[89],"RESULTS:":[90],"We":[91],"give":[92],"solution,":[95],"solely":[96],"based":[97],"on":[98,268,310],"deterministic":[99],"finite-state":[100],"automata":[101],"(DFA),":[102],"finding":[107],"whole":[109],"part":[111],"probability":[114],"distribution":[115],"function":[116],"simple-word":[119],"homogeneous":[123],"(biological)":[124],"sequence.":[125],"Out":[126],"that,":[128],"z-value":[130],"can":[131,138,290],"always":[132],"be":[133,139,291],"computed,":[134],"while":[135],"P-value":[137],"obtained":[140],"either":[141],"when":[142,161],"it":[143],"too":[146],"extreme":[147],"with":[148,307],"respect":[149],"number":[152,163],"floating-point":[154],"digits":[155],"available":[156],"implementation,":[159],"pattern":[165],"moderately":[168],"low.":[169],"In":[170,263],"particular,":[171],"time":[173],"complexity":[174],"algorithms":[177,237],"Markov":[179],"models":[180],"moderate":[182],"order":[183],"(0":[184],"<":[185,189],"=":[187,191],"m":[188],"2)":[192],"far":[194],"better":[195],"than":[196],"Nuel,":[199],"which":[200,281],"was":[201],"fastest":[203],"similar":[204],"algorithm":[206,280],"known":[207],"date;":[209],"many":[211],"cases,":[212],"even":[213],"methods":[215],"outperformed.":[217],"CONCLUSIONS:":[218],"DFA":[219,269],"standard":[222],"tool":[223],"computer":[225],"science":[226],"study":[229],"patterns;":[231],"previous":[232],"works":[233],"biology":[235],"propose":[236],"involving":[238],"automata,":[239],"there":[241],"used,":[244],"respectively,":[245],"first":[248],"step":[249],"write":[251],"generating":[253],"function,":[254],"build":[257],"finite":[259],"Markov-chain":[260],"imbedding":[261],"(FMCI).":[262],"contrast,":[264],"we":[265,275,305],"directly":[266],"rely":[267],"perform":[271],"calculations;":[273],"thus":[274],"manage":[276],"obtain":[278],"both":[283],"easily":[284],"interpretable":[285],"efficient.":[287],"This":[288],"approach":[289],"used":[292],"studies":[296],"long":[299],"protein":[302],"sequences,":[303],"illustrate":[306],"some":[308],"examples":[309],"scale":[312],"human":[315],"genome.":[316]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
