{"id":"https://openalex.org/W7155534331","doi":"https://doi.org/10.1145/3799830.3799866","title":"A fast method for clustering regulatory DNA regions","display_name":"A fast method for clustering regulatory DNA regions","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7155534331","doi":"https://doi.org/10.1145/3799830.3799866"},"language":null,"primary_location":{"id":"doi:10.1145/3799830.3799866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799866","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799830.3799866","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134468764","display_name":"Akash Dileep K","orcid":"https://orcid.org/0009-0005-7458-690X"},"institutions":[{"id":"https://openalex.org/I181996519","display_name":"Indian Institute of Science Education and Research Pune","ror":"https://ror.org/028qa3n13","country_code":"IN","type":"education","lineage":["https://openalex.org/I181996519"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Akash Dileep K","raw_affiliation_strings":["Indian Institute of Science Education and Research Pune, Pune, India"],"raw_orcid":"https://orcid.org/0009-0005-7458-690X","affiliations":[{"raw_affiliation_string":"Indian Institute of Science Education and Research Pune, Pune, India","institution_ids":["https://openalex.org/I181996519"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078875370","display_name":"Leelavati Narlikar","orcid":"https://orcid.org/0000-0001-6820-1878"},"institutions":[{"id":"https://openalex.org/I181996519","display_name":"Indian Institute of Science Education and Research Pune","ror":"https://ror.org/028qa3n13","country_code":"IN","type":"education","lineage":["https://openalex.org/I181996519"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Leelavati Narlikar","raw_affiliation_strings":["Departments of Data Science and of Biology, Indian Institute of Science Education and Research Pune, Pune, India"],"raw_orcid":"https://orcid.org/0000-0001-6820-1878","affiliations":[{"raw_affiliation_string":"Departments of Data Science and of Biology, Indian Institute of Science Education and Research Pune, Pune, India","institution_ids":["https://openalex.org/I181996519"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5134468764"],"corresponding_institution_ids":["https://openalex.org/I181996519"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65674212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"402","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9879999756813049,"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":0.9879999756813049,"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/T10885","display_name":"Gene expression and cancer classification","score":0.003599999938160181,"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/T10268","display_name":"Developmental Biology and Gene Regulation","score":0.0013000000035390258,"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/enhancer","display_name":"Enhancer","score":0.6859999895095825},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6801999807357788},{"id":"https://openalex.org/keywords/dna-binding-site","display_name":"DNA binding site","score":0.5480999946594238},{"id":"https://openalex.org/keywords/regulatory-sequence","display_name":"Regulatory sequence","score":0.5257999897003174},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.5184000134468079},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.48080000281333923},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.44589999318122864},{"id":"https://openalex.org/keywords/cis-regulatory-module","display_name":"Cis-regulatory module","score":0.42080000042915344},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.400299996137619}],"concepts":[{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.6859999895095825},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6801999807357788},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.671999990940094},{"id":"https://openalex.org/C3662595","wikidata":"https://www.wikidata.org/wiki/Q5205743","display_name":"DNA binding site","level":5,"score":0.5480999946594238},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.5257999897003174},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.5184000134468079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4851999878883362},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.48080000281333923},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4341999888420105},{"id":"https://openalex.org/C190796033","wikidata":"https://www.wikidata.org/wiki/Q1093165","display_name":"Cis-regulatory module","level":5,"score":0.42080000042915344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.38339999318122864},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.37220001220703125},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C101762097","wikidata":"https://www.wikidata.org/wiki/Q224093","display_name":"Promoter","level":4,"score":0.33329999446868896},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C107824862","wikidata":"https://www.wikidata.org/wiki/Q616005","display_name":"Binding site","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C38764148","wikidata":"https://www.wikidata.org/wiki/Q17098245","display_name":"Interaction information","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799830.3799866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799866","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799830.3799866","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799830.3799866","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM IKDD International Conference on Data Science","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1519266993","https://openalex.org/W1987971958","https://openalex.org/W2014677321","https://openalex.org/W2055043387","https://openalex.org/W2060563775","https://openalex.org/W2075485921","https://openalex.org/W2109719547","https://openalex.org/W2114703458","https://openalex.org/W2115979107","https://openalex.org/W2123861597","https://openalex.org/W2129795133","https://openalex.org/W2133120537","https://openalex.org/W2147055980","https://openalex.org/W2155472755","https://openalex.org/W2156247618","https://openalex.org/W2158094337","https://openalex.org/W2159325249","https://openalex.org/W2170064419","https://openalex.org/W2173100207","https://openalex.org/W2551141605","https://openalex.org/W2596084707","https://openalex.org/W2770178180","https://openalex.org/W2899616402","https://openalex.org/W3078948712","https://openalex.org/W3175931262","https://openalex.org/W3183220284","https://openalex.org/W4225108987","https://openalex.org/W4384126859","https://openalex.org/W4388822209"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"identification":[1],"of":[2,21,138,149],"regulatory":[3,22,114],"motifs":[4,41,49,84],"in":[5,124,152],"promoter":[6],"and":[7,68,80,89,97],"enhancer":[8],"sequences":[9],"is":[10],"crucial":[11],"for":[12],"understanding":[13],"gene":[14],"regulation.":[15],"High-throughput":[16],"assays":[17],"provide":[18],"genome-wide":[19],"maps":[20],"regions,":[23],"anchored":[24],"to":[25,64,77,82,111,132],"biological":[26],"signals":[27],"such":[28],"as":[29],"transcription":[30,34,139],"start":[31],"sites":[32],"or":[33,53,120],"factor":[35],"binding":[36,144],"sites.":[37],"However,":[38],"detecting":[39],"DNA":[40],"within":[42],"these":[43],"regions":[44],"remains":[45],"challenging,":[46],"especially":[47],"when":[48],"are":[50,72,86],"short,":[51],"context-dependent,":[52],"weakly":[54],"conserved.":[55],"Few":[56],"existing":[57],"methods":[58,123],"leverage":[59],"the":[60,65,147],"positional":[61],"information":[62],"relative":[63],"anchor":[66],"point,":[67],"those":[69],"that":[70,85,101],"do":[71],"often":[73],"slow,":[74],"lack":[75],"scalability":[76],"large":[78],"datasets,":[79],"struggle":[81],"identify":[83],"both":[87],"weak":[88],"positionally":[90],"invariant.":[91],"We":[92],"present":[93],"InstaClust,":[94],"a":[95,103],"fast":[96],"deterministic":[98],"clustering":[99,110],"algorithm":[100],"employs":[102],"simple":[104],"Hamming":[105],"distance":[106],"combined":[107],"with":[108],"hierarchical":[109],"group":[112],"related":[113],"sequences.":[115],"Across":[116],"benchmarks,":[117],"InstaClust":[118],"matches":[119],"exceeds":[121],"state-of-the-art":[122],"accuracy,":[125],"while":[126],"having":[127],"substantially":[128],"faster":[129],"runtimes.":[130],"Application":[131],"real":[133],"datasets":[134],"reveals":[135],"potential":[136],"co-factors":[137],"factors,":[140],"which":[141],"exhibit":[142],"position-dependent":[143],"patterns,":[145],"demonstrating":[146],"utility":[148],"our":[150],"approach":[151],"uncovering":[153],"biologically":[154],"relevant":[155],"sequence":[156],"motifs.":[157]},"counts_by_year":[],"updated_date":"2026-04-25T06:06:54.107920","created_date":"2026-04-25T00:00:00"}