{"id":"https://openalex.org/W1986105390","doi":"https://doi.org/10.1142/s0219720003000162","title":"CUBIC: IDENTIFICATION OF REGULATORY BINDING SITES THROUGH DATA CLUSTERING","display_name":"CUBIC: IDENTIFICATION OF REGULATORY BINDING SITES THROUGH DATA CLUSTERING","publication_year":2003,"publication_date":"2003-04-01","ids":{"openalex":"https://openalex.org/W1986105390","doi":"https://doi.org/10.1142/s0219720003000162","mag":"1986105390","pmid":"https://pubmed.ncbi.nlm.nih.gov/15290780"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720003000162","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720003000162","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and 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/A5026918414","display_name":"Victor Olman","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"VICTOR OLMAN","raw_affiliation_strings":["Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082428303","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0002-4809-0514"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DONG XU","raw_affiliation_strings":["Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020171946","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-7856-3343"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YING XU","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA","Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Protein Informatics Group, Life Sciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831-6480, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6039,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.81896322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"01","issue":"01","first_page":"21","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9983000159263611,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9983000159263611,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9976000189781189,"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/T10604","display_name":"RNA Research and Splicing","score":0.9965000152587891,"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/dna-binding-site","display_name":"DNA binding site","score":0.7390551567077637},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7065480351448059},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6381096839904785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5081281661987305},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5043498277664185},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.5026531219482422},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49813246726989746},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4200730621814728},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3460462689399719},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.32662710547447205},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.31741222739219666},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3168467581272125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2025434672832489},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.16631367802619934}],"concepts":[{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.7390551567077637},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7065480351448059},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6381096839904785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5081281661987305},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5043498277664185},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.5026531219482422},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49813246726989746},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4200730621814728},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3460462689399719},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.32662710547447205},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.31741222739219666},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3168467581272125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2025434672832489},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.16631367802619934},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001665","descriptor_name":"Binding Sites","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"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":"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":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012333","descriptor_name":"RNA, Messenger","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D012441","descriptor_name":"Saccharomyces cerevisiae","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"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":"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":"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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720003000162","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720003000162","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:15290780","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15290780","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 bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337509","display_name":"Biological and Environmental Research","ror":"https://ror.org/0114b2m14"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W108464071","https://openalex.org/W1529802779","https://openalex.org/W1706518069","https://openalex.org/W1970472404","https://openalex.org/W1972544340","https://openalex.org/W1975924111","https://openalex.org/W1986698569","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2017200304","https://openalex.org/W2028903194","https://openalex.org/W2029316600","https://openalex.org/W2029589204","https://openalex.org/W2048869777","https://openalex.org/W2074703985","https://openalex.org/W2084290450","https://openalex.org/W2114332734","https://openalex.org/W2133241531","https://openalex.org/W2142204199","https://openalex.org/W2150926065","https://openalex.org/W2168157737","https://openalex.org/W2800394774","https://openalex.org/W2888871578","https://openalex.org/W4229921563","https://openalex.org/W4245999760","https://openalex.org/W4405648826"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W2998448420","https://openalex.org/W1974038726","https://openalex.org/W1953626159","https://openalex.org/W2379997263","https://openalex.org/W2367493320","https://openalex.org/W2131580913","https://openalex.org/W3083097828","https://openalex.org/W1576021314","https://openalex.org/W2125854412"],"abstract_inverted_index":{"Transcription":[0],"factor":[1,30,85],"binding":[2,31,63,86,95,276],"sites":[3,32,64,96],"are":[4],"short":[5],"fragments":[6],"in":[7,209],"the":[8,20,48,135,162,221,241,246],"upstream":[9,69],"regions":[10,70],"of":[11,22,28,42,50,62,68,71,93,164,224,270,275],"genes,":[12,72],"to":[13,18,108,124,232],"which":[14,228],"transcription":[15,21,29,84],"factors":[16],"bind":[17],"regulate":[19],"genes":[23],"into":[24,47,144],"mRNA.":[25],"Computational":[26],"identification":[27,61,120,191,243],"remains":[33],"an":[34],"unsolved":[35],"challenging":[36,273],"problem":[37,116,139,163],"though":[38],"a":[39,57,66,118,131,141,169,177,183,189,210,217,252,267],"great":[40],"amount":[41],"effort":[43],"has":[44,151,260],"been":[45,152,261],"put":[46],"study":[49],"this":[51,115,173],"problem.":[52,121,184],"We":[53,185,213,238,264],"have":[54,113,186,214,239],"recently":[55],"developed":[56,216],"novel":[58,178],"technique":[59],"for":[60,160,180,204,219],"from":[65,130,168],"set":[67,143],"that":[73,188],"could":[74],"possibly":[75],"be":[76,197,230],"transcriptionally":[77],"co-regulated":[78],"and":[79,102,126,199,245],"hence":[80],"might":[81],"share":[82],"similar":[83,149],"sites.":[87],"By":[88],"utilizing":[89],"two":[90],"key":[91],"features":[92],"such":[94,182],"(i.e.":[97],"their":[98,103],"high":[99,105],"sequence":[100,110],"similarities":[101],"relatively":[104],"frequencies":[106],"compared":[107],"other":[109],"fragments),":[111],"we":[112,175],"formulated":[114],"as":[117,251],"cluster":[119,190,242],"That":[122],"is":[123,156],"identify":[125],"extract":[127],"data":[128,137,142,166,236],"clusters":[129,145,167],"noisy":[132,170],"background.":[133,171],"While":[134],"classical":[136],"clustering":[138],"(partitioning":[140],"sharing":[146],"common":[147],"or":[148],"features)":[150],"extensively":[153],"studied,":[154],"there":[155],"no":[157],"general":[158],"algorithm":[159,179,244],"solving":[161,181],"identifying":[165],"In":[172],"paper,":[174],"present":[176,265],"proved":[187],"problem,":[192],"under":[193],"our":[194],"definition,":[195],"can":[196,229],"rigorously":[198],"efficiently":[200],"solved":[201],"through":[202],"searching":[203],"substrings":[205],"with":[206],"special":[207],"properties":[208],"linear":[211],"sequence.":[212],"also":[215],"method":[218,250],"assessing":[220],"statistical":[222,247],"significance":[223,248],"each":[225],"identified":[226],"cluster,":[227],"used":[231],"rule":[233],"out":[234],"accidental":[235],"clusters.":[237],"implemented":[240],"analysis":[249],"computer":[253],"software":[254],"CUBIC.":[255],"Extensive":[256],"testing":[257],"on":[258,272],"CUBIC":[259,271],"carried":[262],"out.":[263],"here":[266],"few":[268],"applications":[269],"cases":[274],"site":[277],"identification.":[278]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}