{"id":"https://openalex.org/W2748123750","doi":"https://doi.org/10.1093/bioinformatics/btx539","title":"An improved compound Poisson model for the number of motif hits in DNA sequences","display_name":"An improved compound Poisson model for the number of motif hits in DNA sequences","publication_year":2017,"publication_date":"2017-08-25","ids":{"openalex":"https://openalex.org/W2748123750","doi":"https://doi.org/10.1093/bioinformatics/btx539","mag":"2748123750","pmid":"https://pubmed.ncbi.nlm.nih.gov/28961747"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btx539","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx539","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/24/3929/25168559/btx539.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/24/3929/25168559/btx539.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084108745","display_name":"Wolfgang Kopp","orcid":"https://orcid.org/0000-0003-0376-0032"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wolfgang Kopp","raw_affiliation_strings":["Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0376-0032","affiliations":[{"raw_affiliation_string":"Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009628707","display_name":"Martin Vingron","orcid":"https://orcid.org/0000-0002-1765-4241"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Vingron","raw_affiliation_strings":["Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Molecular Biology, Max Planck Institute for Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084108745"],"corresponding_institution_ids":["https://openalex.org/I4210142260"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.4557,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82005949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"33","issue":"24","first_page":"3929","last_page":"3937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9666000008583069,"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":0.9666000008583069,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.008100000210106373,"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/T10432","display_name":"DNA and Nucleic Acid Chemistry","score":0.006899999920278788,"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/motif","display_name":"Motif (music)","score":0.730629563331604},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.6057268381118774},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.583624005317688},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5185052156448364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4546040892601013},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.431805282831192},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.41992971301078796},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31081467866897583},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3062376379966736},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16306257247924805},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08412513136863708}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.730629563331604},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.6057268381118774},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.583624005317688},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5185052156448364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4546040892601013},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.431805282831192},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.41992971301078796},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31081467866897583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3062376379966736},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16306257247924805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08412513136863708},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","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":"D001665","descriptor_name":"Binding Sites","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D014157","descriptor_name":"Transcription Factors","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D016012","descriptor_name":"Poisson Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016012","descriptor_name":"Poisson Distribution","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016012","descriptor_name":"Poisson Distribution","qualifier_ui":null,"qualifier_name":null,"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056510","descriptor_name":"Position-Specific Scoring Matrices","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059372","descriptor_name":"Nucleotide Motifs","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btx539","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx539","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/24/3929/25168559/btx539.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:28961747","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28961747","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:escidoc.org:escidoc:2539175","is_oa":true,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0000-810C-1","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5860096","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5860096","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:pure.mpg.de:item_2539175","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0000-810C-1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btx539","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btx539","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/24/3929/25168559/btx539.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2748123750.pdf","grobid_xml":"https://content.openalex.org/works/W2748123750.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1600463518","https://openalex.org/W1815199292","https://openalex.org/W1964963969","https://openalex.org/W1986841498","https://openalex.org/W1988393300","https://openalex.org/W2026731344","https://openalex.org/W2031200646","https://openalex.org/W2041397659","https://openalex.org/W2041877620","https://openalex.org/W2053392780","https://openalex.org/W2077431563","https://openalex.org/W2084620487","https://openalex.org/W2118215072","https://openalex.org/W2123490534","https://openalex.org/W2127021450","https://openalex.org/W2128016314","https://openalex.org/W2133045519","https://openalex.org/W2136292095","https://openalex.org/W2140952049","https://openalex.org/W2148315211","https://openalex.org/W2149769193","https://openalex.org/W2153550523","https://openalex.org/W2156661861","https://openalex.org/W2157009395","https://openalex.org/W2165102934","https://openalex.org/W4240746805","https://openalex.org/W6669483617","https://openalex.org/W6683407323"],"related_works":["https://openalex.org/W2073661767","https://openalex.org/W2380185347","https://openalex.org/W2370034659","https://openalex.org/W2159636084","https://openalex.org/W2117168988","https://openalex.org/W2103777723","https://openalex.org/W2610941444","https://openalex.org/W2605190264","https://openalex.org/W1980429866","https://openalex.org/W2039465881"],"abstract_inverted_index":{"MOTIVATION:":[0],"Transcription":[1],"factors":[2],"play":[3],"a":[4,21,35,40,48,56,134,152,166],"crucial":[5],"role":[6],"in":[7,27,52,55,151],"gene":[8],"regulation":[9],"by":[10,20],"binding":[11],"to":[12,39,46,67,85],"specific":[13],"regulatory":[14],"sequences.":[15,157],"The":[16,143,161],"sequence":[17,36],"motifs":[18],"recognized":[19],"transcription":[22],"factor":[23],"can":[24],"be":[25],"described":[26],"terms":[28],"of":[29,59,71,75,78,112,123,136,145],"position":[30,41],"frequency":[31,42],"matrices.":[32],"When":[33],"scanning":[34],"for":[37],"matches":[38],"matrix,":[43],"one":[44],"needs":[45],"determine":[47],"cut-off,":[49],"which":[50,81,108],"then":[51],"turn":[53],"results":[54],"certain":[57],"number":[58,77,111],"hits.":[60],"In":[61],"this":[62],"paper":[63],"we":[64],"describe":[65],"how":[66],"compute":[68],"the":[69,76,83,110,121,124,141,146],"distribution":[70],"match":[72],"scores":[73],"and":[74,107,138],"motif":[79,87],"hits,":[80],"are":[82,178],"prerequisites":[84],"perform":[86],"hit":[88],"enrichment":[89],"analysis.":[90],"RESULTS:":[91],"We":[92,119],"put":[93],"forward":[94],"an":[95],"improved":[96,125],"compound":[97,126],"Poisson":[98,127],"model":[99,128,148],"that":[100],"supports":[101],"general":[102],"order-d":[103,147],"Markov":[104],"background":[105],"models":[106,132],"computes":[109],"motif-hits":[113],"more":[114],"accurately":[115],"than":[116],"earlier":[117],"models.":[118],"compared":[120],"accuracy":[122],"with":[129],"previously":[130],"proposed":[131],"across":[133],"range":[135],"parameters":[137],"motifs,":[139],"demonstrating":[140],"improvement.":[142],"importance":[144],"is":[149,163],"supported":[150],"case":[153],"study":[154],"using":[155],"CpG-island":[156],"AVAILABILITY":[158],"AND":[159],"IMPLEMENTATION:":[160],"method":[162],"available":[164,179],"as":[165],"Bioconductor":[167],"package":[168],"named":[169],"'motifcounter'":[170],"https://bioconductor.org/packages/motifcounter.":[171],"CONTACT:":[172],"kopp@molgen.mpg.de.":[173],"SUPPLEMENTARY":[174],"INFORMATION:":[175],"Supplementary":[176],"data":[177],"at":[180],"Bioinformatics":[181],"online.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
