{"id":"https://openalex.org/W1601619414","doi":"https://doi.org/10.1109/csb.2003.1227367","title":"CUBIC: identification of regulatory binding sites through data clustering","display_name":"CUBIC: identification of regulatory binding sites through data clustering","publication_year":2004,"publication_date":"2004-03-30","ids":{"openalex":"https://openalex.org/W1601619414","doi":"https://doi.org/10.1109/csb.2003.1227367","mag":"1601619414"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2003.1227367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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":true,"raw_author_name":"V. Olman","raw_affiliation_strings":["Life Sciences Division, Protein Informatics Group","Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA"],"affiliations":[{"raw_affiliation_string":"Life Sciences Division, Protein Informatics Group","institution_ids":[]},{"raw_affiliation_string":"Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068858927","display_name":"Don Xu","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":"D. Xu","raw_affiliation_strings":["Life Sciences Division, Protein Informatics Group","Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA"],"affiliations":[{"raw_affiliation_string":"Life Sciences Division, Protein Informatics Group","institution_ids":[]},{"raw_affiliation_string":"Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075489504","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-2881-7093"},"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":"Y. Xu","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Protein Informatics Group, Oak Ridge Nat. Lab., TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026918414"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.04739244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"448","last_page":"448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10604","display_name":"RNA Research and Splicing","score":0.9958999752998352,"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/T10604","display_name":"RNA Research and Splicing","score":0.9958999752998352,"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":0.9951000213623047,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9800000190734863,"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":0.7369270920753479},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.654825747013092},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6443542838096619},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5651993751525879},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5058833956718445},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.49064651131629944},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.43762025237083435},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4347429871559143},{"id":"https://openalex.org/keywords/parameter-identification-problem","display_name":"Parameter identification problem","score":0.4241184890270233},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2980639934539795},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2651033103466034},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2590201795101166},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2549351751804352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2061651349067688},{"id":"https://openalex.org/keywords/promoter","display_name":"Promoter","score":0.15950360894203186}],"concepts":[{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.7369270920753479},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.654825747013092},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6443542838096619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5651993751525879},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5058833956718445},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.49064651131629944},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.43762025237083435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4347429871559143},{"id":"https://openalex.org/C79610928","wikidata":"https://www.wikidata.org/wiki/Q1656743","display_name":"Parameter identification problem","level":3,"score":0.4241184890270233},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2980639934539795},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2651033103466034},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2590201795101166},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2549351751804352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2061651349067688},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.15950360894203186},{"id":"https://openalex.org/C2983447341","wikidata":"https://www.wikidata.org/wiki/Q1413083","display_name":"Model parameter","level":2,"score":0.0},{"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":[],"locations_count":1,"locations":[{"id":"doi:10.1109/csb.2003.1227367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2003.1227367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Systems Bioinformatics. CSB2003. Proceedings of the 2003 IEEE Bioinformatics Conference. CSB2003","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W1542422837","https://openalex.org/W1974038726","https://openalex.org/W2998448420","https://openalex.org/W2379997263","https://openalex.org/W2367493320","https://openalex.org/W2131580913","https://openalex.org/W2125854412","https://openalex.org/W3083097828","https://openalex.org/W2796029694"],"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],"coregulated":[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":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}