{"id":"https://openalex.org/W2150612336","doi":"https://doi.org/10.1093/nar/gkg540","title":"Cluster-Buster: finding dense clusters of motifs in DNA sequences","display_name":"Cluster-Buster: finding dense clusters of motifs in DNA sequences","publication_year":2003,"publication_date":"2003-06-24","ids":{"openalex":"https://openalex.org/W2150612336","doi":"https://doi.org/10.1093/nar/gkg540","mag":"2150612336","pmid":"https://pubmed.ncbi.nlm.nih.gov/12824389"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkg540","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkg540","pdf_url":"https://academic.oup.com/nar/article-pdf/31/13/3666/9487255/gkg540.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"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":"Nucleic Acids Research","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/nar/article-pdf/31/13/3666/9487255/gkg540.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055829507","display_name":"Martin C. Frith","orcid":"https://orcid.org/0000-0003-0998-2859"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. C. Frith","raw_affiliation_strings":["Bioinformatics Program, Boston University, 44 Cummington Street, Boston, MA 02215, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Program, Boston University, 44 Cummington Street, Boston, MA 02215, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055829507"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":{"value":3630,"currency":"USD","value_usd":3630},"apc_paid":null,"fwci":6.9554,"has_fulltext":false,"cited_by_count":341,"citation_normalized_percentile":{"value":0.97923696,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":"13","first_page":"3666","last_page":"3668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9994000196456909,"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/T10604","display_name":"RNA Research and Splicing","score":0.9987000226974487,"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/biology","display_name":"Biology","score":0.8486982583999634},{"id":"https://openalex.org/keywords/enhancer","display_name":"Enhancer","score":0.6343334317207336},{"id":"https://openalex.org/keywords/repeated-sequence","display_name":"Repeated sequence","score":0.622991681098938},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.551226019859314},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5494267344474792},{"id":"https://openalex.org/keywords/interspersed-repeat","display_name":"Interspersed repeat","score":0.548823893070221},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.5273345708847046},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5113808512687683},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.50799161195755},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4388417899608612},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4223003387451172},{"id":"https://openalex.org/keywords/consensus-sequence","display_name":"Consensus sequence","score":0.4136529564857483},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4010191857814789},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.3353385329246521},{"id":"https://openalex.org/keywords/base-sequence","display_name":"Base sequence","score":0.28194165229797363},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.1871497929096222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.12812325358390808}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.8486982583999634},{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.6343334317207336},{"id":"https://openalex.org/C169802333","wikidata":"https://www.wikidata.org/wiki/Q424473","display_name":"Repeated sequence","level":4,"score":0.622991681098938},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.551226019859314},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5494267344474792},{"id":"https://openalex.org/C117751501","wikidata":"https://www.wikidata.org/wiki/Q3456512","display_name":"Interspersed repeat","level":5,"score":0.548823893070221},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.5273345708847046},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5113808512687683},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.50799161195755},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4388417899608612},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4223003387451172},{"id":"https://openalex.org/C54985914","wikidata":"https://www.wikidata.org/wiki/Q1295754","display_name":"Consensus sequence","level":4,"score":0.4136529564857483},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4010191857814789},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.3353385329246521},{"id":"https://openalex.org/C3017666073","wikidata":"https://www.wikidata.org/wiki/Q1764062","display_name":"Base sequence","level":3,"score":0.28194165229797363},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.1871497929096222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.12812325358390808},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005815","descriptor_name":"Genetic Code","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005815","descriptor_name":"Genetic Code","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005815","descriptor_name":"Genetic Code","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":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012045","descriptor_name":"Regulatory Sequences, Nucleic Acid","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1093/nar/gkg540","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkg540","pdf_url":"https://academic.oup.com/nar/article-pdf/31/13/3666/9487255/gkg540.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"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":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:12824389","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12824389","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":"Nucleic acids research","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.7186","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.7186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://zlab.umassmed.edu/zlab/publications/Cluster-Buster.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.631.1513","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.631.1513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nar.oxfordjournals.org/content/31/13/3666.full.pdf","raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:168947","is_oa":true,"landing_page_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:168947","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/168947","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nucleic Acids Res","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/nar/gkg540","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkg540","pdf_url":"https://academic.oup.com/nar/article-pdf/31/13/3666/9487255/gkg540.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"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":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2501033700","display_name":null,"funder_award_id":"P20 GM066401","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6120813775","display_name":null,"funder_award_id":"1P20GM066401-01","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306082","display_name":"Howard Hughes Medical Institute","ror":"https://ror.org/006w34k90"},{"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/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150612336.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1822105579","https://openalex.org/W2001785106","https://openalex.org/W2034719432","https://openalex.org/W2062827192","https://openalex.org/W2068011423","https://openalex.org/W2075435641","https://openalex.org/W2077609634","https://openalex.org/W2104235495","https://openalex.org/W2107768450","https://openalex.org/W2117549173","https://openalex.org/W2124025352","https://openalex.org/W2136726922","https://openalex.org/W2142890842","https://openalex.org/W2148441137","https://openalex.org/W2149769193","https://openalex.org/W2154514071","https://openalex.org/W2165228646"],"related_works":["https://openalex.org/W2187207551","https://openalex.org/W2069184423","https://openalex.org/W2089696733","https://openalex.org/W1988509800","https://openalex.org/W2516911135","https://openalex.org/W2118671962","https://openalex.org/W3209353392","https://openalex.org/W2164240145","https://openalex.org/W1536808921","https://openalex.org/W2090139400"],"abstract_inverted_index":{"The":[0,31],"signals":[1],"that":[2,76],"determine":[3],"activation":[4],"and":[5,57,65],"repression":[6],"of":[7,17,25,62,79,92,98],"specific":[8],"genes":[9],"in":[10,28,46,101],"response":[11],"to":[12,52,59],"appropriate":[13],"stimuli":[14],"are":[15],"one":[16],"the":[18,89],"most":[19],"important,":[20],"but":[21],"least":[22],"understood,":[23],"types":[24],"information":[26],"encoded":[27],"genomic":[29],"DNA.":[30],"nucleotide":[32],"sequence":[33],"patterns,":[34],"or":[35],"motifs,":[36],"preferentially":[37],"bound":[38],"by":[39],"various":[40],"transcription":[41],"factors":[42],"have":[43,74],"been":[44],"collected":[45],"databases.":[47],"However,":[48],"these":[49],"motifs":[50,80,100],"appear":[51],"be":[53],"individually":[54],"too":[55],"short":[56],"degenerate":[58],"enable":[60],"detection":[61],"functional":[63],"enhancer":[64],"silencer":[66],"elements":[67],"within":[68],"a":[69,106],"large":[70],"genome.":[71],"Several":[72],"groups":[73],"proposed":[75],"dense":[77],"clusters":[78,97],"may":[81],"diagnose":[82],"regulatory":[83],"regions":[84],"more":[85],"accurately.":[86],"Cluster-Buster":[87,107],"is":[88],"third":[90],"incarnation":[91],"our":[93],"software":[94],"for":[95],"finding":[96],"pre-specified":[99],"DNA":[102],"sequences.":[103],"We":[104],"offer":[105],"web":[108],"server":[109],"at":[110],"http://zlab.bu.edu/cluster-buster/.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":19}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}