{"id":"https://openalex.org/W2561544479","doi":"https://doi.org/10.1093/bioinformatics/btw683","title":"Fast motif matching revisited: high-order PWMs, SNPs and indels","display_name":"Fast motif matching revisited: high-order PWMs, SNPs and indels","publication_year":2016,"publication_date":"2016-10-27","ids":{"openalex":"https://openalex.org/W2561544479","doi":"https://doi.org/10.1093/bioinformatics/btw683","mag":"2561544479","pmid":"https://pubmed.ncbi.nlm.nih.gov/28011774"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/4/514/25146739/btw683.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":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/4/514/25146739/btw683.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085809864","display_name":"Janne H. Korhonen","orcid":"https://orcid.org/0009-0000-5494-1218"},"institutions":[{"id":"https://openalex.org/I123185442","display_name":"Reykjav\u00edk University","ror":"https://ror.org/05d2kyx68","country_code":"IS","type":"education","lineage":["https://openalex.org/I123185442"]},{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI","IS"],"is_corresponding":true,"raw_author_name":"Janne H Korhonen","raw_affiliation_strings":["Department of Computer Science, Faculty of Medicine, University of Helsinki, Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Helsinki, Finland","School of Computer Science, Reykjav\u00edk University, Reykjav\u00edk, Iceland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Medicine, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Helsinki, Finland","institution_ids":["https://openalex.org/I32943570"]},{"raw_affiliation_string":"School of Computer Science, Reykjav\u00edk University, Reykjav\u00edk, Iceland","institution_ids":["https://openalex.org/I123185442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011030520","display_name":"Kimmo Palin","orcid":"https://orcid.org/0000-0002-4621-6128"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kimmo Palin","raw_affiliation_strings":["Genome-Scale Biology Research Program, Research Programs Unit, Faculty of Medicine, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome-Scale Biology Research Program, Research Programs Unit, Faculty of Medicine, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031611528","display_name":"Jussi Taipale","orcid":"https://orcid.org/0000-0003-4204-0951"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jussi Taipale","raw_affiliation_strings":["Department of Biosciences and Nutrition, Karolinska Institutet, Genome Scale Biology Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosciences and Nutrition, Karolinska Institutet, Genome Scale Biology Program, Faculty of Medicine, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058284151","display_name":"Esko Ukkonen","orcid":"https://orcid.org/0000-0002-5978-1505"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]},{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esko Ukkonen","raw_affiliation_strings":["Department of Computer Science, Faculty of Medicine, University of Helsinki, Helsinki, Finland","Helsinki Institute for Information Technology HIIT, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Medicine, University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]},{"raw_affiliation_string":"Helsinki Institute for Information Technology HIIT, Helsinki, Finland","institution_ids":["https://openalex.org/I32943570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085809864"],"corresponding_institution_ids":["https://openalex.org/I123185442","https://openalex.org/I133731052","https://openalex.org/I32943570"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.7408,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.85387093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"514","last_page":"521"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9083999991416931,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9083999991416931,"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/T11213","display_name":"Genomic variations and chromosomal abnormalities","score":0.019600000232458115,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.017400000244379044,"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":0.7163635492324829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6378907561302185},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5189468860626221},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.4425974488258362},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36547261476516724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3537636995315552},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34932202100753784},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1798672378063202},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16820213198661804},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1375236213207245},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11002200841903687}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.7163635492324829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6378907561302185},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5189468860626221},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.4425974488258362},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36547261476516724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3537636995315552},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34932202100753784},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1798672378063202},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16820213198661804},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1375236213207245},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11002200841903687},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":"D002892","descriptor_name":"Chromosomes, Human, Pair 22","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002892","descriptor_name":"Chromosomes, Human, Pair 22","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002892","descriptor_name":"Chromosomes, Human, Pair 22","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":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020641","descriptor_name":"Polymorphism, Single Nucleotide","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054643","descriptor_name":"INDEL Mutation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btw683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/4/514/25146739/btw683.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:28011774","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28011774","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/btw683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/4/514/25146739/btw683.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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W159319308","https://openalex.org/W1498440332","https://openalex.org/W1561333746","https://openalex.org/W1589115128","https://openalex.org/W1594294324","https://openalex.org/W1685101501","https://openalex.org/W1783247684","https://openalex.org/W1900337607","https://openalex.org/W1963778673","https://openalex.org/W1969051510","https://openalex.org/W1977632740","https://openalex.org/W1994122295","https://openalex.org/W2002122781","https://openalex.org/W2005546833","https://openalex.org/W2012114217","https://openalex.org/W2024122679","https://openalex.org/W2026690931","https://openalex.org/W2029201460","https://openalex.org/W2033781392","https://openalex.org/W2033991385","https://openalex.org/W2034145535","https://openalex.org/W2040756306","https://openalex.org/W2046976590","https://openalex.org/W2051640319","https://openalex.org/W2057000344","https://openalex.org/W2071753700","https://openalex.org/W2085289814","https://openalex.org/W2087342608","https://openalex.org/W2099964107","https://openalex.org/W2104549677","https://openalex.org/W2105318270","https://openalex.org/W2111234263","https://openalex.org/W2116405705","https://openalex.org/W2131164829","https://openalex.org/W2137428312","https://openalex.org/W2149769193","https://openalex.org/W2159324718","https://openalex.org/W2167296922","https://openalex.org/W2168909179","https://openalex.org/W2170964754","https://openalex.org/W2176034226","https://openalex.org/W2258472384","https://openalex.org/W2413160504","https://openalex.org/W6650815201","https://openalex.org/W6680709261","https://openalex.org/W6715486265"],"related_works":["https://openalex.org/W3170299350","https://openalex.org/W2368410102","https://openalex.org/W2368037387","https://openalex.org/W2073661767","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2610941444","https://openalex.org/W2159636084"],"abstract_inverted_index":{"Motivation:":[0],"While":[1],"the":[2,8,20,58,65,70,92,95,100,119,153,206,221,226,233],"position":[3,130],"weight":[4,131],"matrix":[5],"(PWM)":[6],"is":[7,16,84],"most":[9],"popular":[10],"model":[11,71],"for":[12,105,118,133,199],"sequence":[13,93,166,195],"motifs,":[14],"there":[15],"growing":[17],"evidence":[18],"of":[19,22,46,48,60,64,136,165,220],"usefulness":[21],"more":[23],"advanced":[24],"models":[25,33,53,138],"such":[26,32,169],"as":[27,170,217],"first-order":[28],"Markov":[29],"representations,":[30],"and":[31,146,172,174,197,212,232],"are":[34,198,215],"also":[35],"becoming":[36],"available":[37,216],"in":[38,91,191],"well-known":[39],"motif":[40,81,106,115,137,201],"databases.":[41],"There":[42],"has":[43,75],"been":[44,76,109],"lots":[45],"research":[47],"how":[49,88,160],"to":[50,152,161],"learn":[51],"these":[52],"from":[54],"training":[55],"data":[56],"but":[57],"problem":[59],"predicting":[61],"putative":[62],"sites":[63],"learned":[66],"motifs":[67],"by":[68],"matching":[69,107,116,150,181],"against":[72],"new":[73],"sequences":[74],"given":[77],"less":[78],"attention.":[79],"Moreover,":[80],"site":[82],"analysis":[83],"often":[85],"concerned":[86],"about":[87],"different":[89,163],"variants":[90,167],"affect":[94],"sites.":[96],"So":[97],"far,":[98],"though,":[99],"corresponding":[101],"efficient":[102,179],"software":[103,223],"tools":[104],"have":[108],"lacking.":[110],"Results:":[111],"We":[112],"develop":[113],"fast":[114,148],"algorithms":[117,151,188],"aforementioned":[120],"tasks.":[121],"First,":[122],"we":[123,158],"formalize":[124],"a":[125,218],"framework":[126],"based":[127],"on":[128,193],"high-order":[129,154],"matrices":[132],"generic":[134],"representation":[135],"with":[139],"dinucleotide":[140],"or":[141],"general":[142],"q":[143],"-mer":[144],"dependencies,":[145],"adapt":[147],"PWM":[149,155,180],"framework.":[156],"Second,":[157],"show":[159,185],"incorporate":[162],"types":[164],",":[168],"SNPs":[171],"indels,":[173],"their":[175],"combined":[176],"effects":[177],"into":[178],"workflows.":[182],"Benchmark":[183],"results":[184],"that":[186],"our":[187],"perform":[189],"well":[190],"practice":[192],"genome-sized":[194],"sets":[196],"multiple":[200],"search":[202],"much":[203],"faster":[204],"than":[205],"basic":[207],"sliding":[208],"window":[209],"algorithm.":[210],"Availability":[211],"Implementation:":[213],"Implementations":[214],"part":[219],"MOODS":[222],"package":[224],"under":[225],"GNU":[227],"General":[228],"Public":[229],"License":[230],"v3.0":[231],"Biopython":[234],"license":[235],"(":[236],"http://www.cs.helsinki.fi/group/pssmfind":[237],").":[238],"Contact:":[239],"janne.h.korhonen@gmail.com.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}
