{"id":"https://openalex.org/W2159670689","doi":"https://doi.org/10.1109/bibm.2010.5706593","title":"A generalized sequence pattern matching algorithm using complementary dual-seeding","display_name":"A generalized sequence pattern matching algorithm using complementary dual-seeding","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2159670689","doi":"https://doi.org/10.1109/bibm.2010.5706593","mag":"2159670689"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2010.5706593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5053483219","display_name":"Bing Ni","orcid":"https://orcid.org/0000-0002-4297-5346"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing Ni","raw_affiliation_strings":["Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108202621","display_name":"Leung-Yau Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leung Yau Lo","raw_affiliation_strings":["Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082233800","display_name":"Kwong\u2010Sak Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kwong Sak Leung","raw_affiliation_strings":["Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053483219"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.14934225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9958000183105469,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9952999949455261,"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/substring","display_name":"Substring","score":0.7660582065582275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6813257932662964},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.6324599385261536},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47150105237960815},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4499569237232208},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4434017837047577},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36773958802223206},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36634132266044617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3427169919013977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2821722626686096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23061200976371765},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.11402016878128052}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7660582065582275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6813257932662964},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.6324599385261536},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47150105237960815},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4499569237232208},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4434017837047577},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36773958802223206},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36634132266044617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3427169919013977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2821722626686096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23061200976371765},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.11402016878128052},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2010.5706593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1525642766","https://openalex.org/W1955121107","https://openalex.org/W2027447543","https://openalex.org/W2053773712","https://openalex.org/W2055043387","https://openalex.org/W2087064593","https://openalex.org/W2101664494","https://openalex.org/W2105972044","https://openalex.org/W2128591967","https://openalex.org/W2131989567","https://openalex.org/W2136145671","https://openalex.org/W2148315173","https://openalex.org/W4236236547","https://openalex.org/W6682040500"],"related_works":["https://openalex.org/W2902555313","https://openalex.org/W2731201547","https://openalex.org/W2135574162","https://openalex.org/W2890359459","https://openalex.org/W4249054680","https://openalex.org/W2055497872","https://openalex.org/W2902482624","https://openalex.org/W2943461603","https://openalex.org/W2218650848","https://openalex.org/W2091929432"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"define":[4],"generalized":[5,39,54,77,92,130,151],"(sequence)":[6],"patterns,":[7],"which":[8,64,81],"is":[9,41,65,82],"based":[10],"on":[11,153,158],"several":[12,44],"real":[13,121],"Biological":[14],"problems,":[15,122],"including":[16],"transcription":[17,22],"factors":[18],"(TFs)":[19],"binding":[20,24],"to":[21,67,83,119,169],"factor":[23],"sites":[25],"(TFBSs),":[26],"cis-regulatory":[27],"modules,":[28],"protein":[29],"domain":[30],"analysis,":[31],"and":[32,71,108,116,148,161,164],"alternative":[33,115],"splicing":[34],"etc.":[35],"Simply":[36],"speaking,":[37],"a":[38,53,60,76,170],"pattern":[40,55,78,93],"composed":[42],"of":[43,140],"substrings":[45],"with":[46],"gaps":[47],"in-between":[48],"two":[49],"substrings.":[50],"We":[51,73,132],"propose":[52],"matching":[56,79,102],"algorithm":[57],"that":[58,125],"uses":[59],"complementary":[61],"dualseeding":[62],"strategy,":[63],"sensitive":[66],"errors":[68],"(both":[69],"mismatches":[70],"indels).":[72],"also":[74],"develop":[75],"tool,":[80],"our":[84,111],"knowledge":[85],"the":[86,98,165],"first":[87],"ever":[88],"developed":[89],"specially":[90],"for":[91],"matching.":[94],"Rather":[95],"than":[96,174],"replacing":[97],"existing":[99],"general":[100],"purpose":[101],"tools,":[103],"such":[104],"as":[105,129],"BLAST,":[106],"BLAT,":[107],"PatternHunter":[109],"etc,":[110],"tool":[112,156],"provides":[113],"an":[114],"helps":[117],"users":[118],"solve":[120],"especially":[123],"those":[124],"can":[126],"be":[127],"modeled":[128],"patterns.":[131],"use":[133],"data":[134],"randomly":[135],"sampled":[136],"from":[137],"reference":[138],"sequences":[139],"human":[141],"genome":[142],"(NCBI":[143],"build":[144],"v18)":[145],"in":[146],"experiments,":[147],"hit":[149],"98.74%":[150],"patterns":[152],"average.":[154],"The":[155],"runs":[157],"both":[159],"LINUX":[160],"Windows":[162],"platforms,":[163],"memory":[166],"peak":[167],"goes":[168],"little":[171],"bit":[172],"larger":[173],"1GB":[175],"only.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}