{"id":"https://openalex.org/W2114916707","doi":"https://doi.org/10.1177/0165551506059229","title":"An efficient approach for sequence matching in large DNA databases","display_name":"An efficient approach for sequence matching in large DNA databases","publication_year":2006,"publication_date":"2006-02-01","ids":{"openalex":"https://openalex.org/W2114916707","doi":"https://doi.org/10.1177/0165551506059229","mag":"2114916707"},"language":"en","primary_location":{"id":"doi:10.1177/0165551506059229","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551506059229","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-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/A5068972746","display_name":"Jung-Im Won","orcid":"https://orcid.org/0000-0003-3591-7735"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Im Won","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322270","display_name":"Sanghyun Park","orcid":"https://orcid.org/0000-0002-5196-6193"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyun Park","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027497636","display_name":"Jeehee Yoon","orcid":"https://orcid.org/0000-0002-4327-3135"},"institutions":[{"id":"https://openalex.org/I146824383","display_name":"Hallym University","ror":"https://ror.org/03sbhge02","country_code":"KR","type":"education","lineage":["https://openalex.org/I146824383"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-Hee Yoon","raw_affiliation_strings":["Division of Information Engineering and Telecommunications, Hallym                         University, Korea","Division of Information Engineering and Telecommunications, Hallym University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Information Engineering and Telecommunications, Hallym                         University, Korea","institution_ids":["https://openalex.org/I146824383"]},{"raw_affiliation_string":"Division of Information Engineering and Telecommunications, Hallym University, Korea","institution_ids":["https://openalex.org/I146824383"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100656150","display_name":"Sang\u2010Wook Kim","orcid":"https://orcid.org/0000-0002-6345-9084"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Wook Kim","raw_affiliation_strings":["College of Information and Communications, Hanyang University, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Communications, Hanyang University, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.12683404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"1","first_page":"88","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9853000044822693,"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/trie","display_name":"Trie","score":0.8752630949020386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767927348613739},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.6812626719474792},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6334536671638489},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6242308616638184},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5691474676132202},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5581294298171997},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5013628005981445},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.49333468079566956},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.4929630756378174},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.48328807950019836},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.46816346049308777},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.44727614521980286},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.4219023287296295},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4200045168399811},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.415600061416626},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4139879047870636},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.40755927562713623},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3597763776779175},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.21980655193328857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1556551456451416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14839622378349304},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08343350887298584},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07614371180534363}],"concepts":[{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.8752630949020386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767927348613739},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.6812626719474792},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6334536671638489},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6242308616638184},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5691474676132202},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5581294298171997},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5013628005981445},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.49333468079566956},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.4929630756378174},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.48328807950019836},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.46816346049308777},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.44727614521980286},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4219023287296295},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4200045168399811},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.415600061416626},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4139879047870636},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.40755927562713623},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3597763776779175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.21980655193328857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1556551456451416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14839622378349304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08343350887298584},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07614371180534363},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551506059229","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551506059229","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1529615245","https://openalex.org/W1545078296","https://openalex.org/W1557257771","https://openalex.org/W1592614241","https://openalex.org/W1764926552","https://openalex.org/W1834151548","https://openalex.org/W1863405838","https://openalex.org/W1971428680","https://openalex.org/W1986324942","https://openalex.org/W2008907996","https://openalex.org/W2016995838","https://openalex.org/W2021809202","https://openalex.org/W2030428223","https://openalex.org/W2055043387","https://openalex.org/W2062393514","https://openalex.org/W2068421750","https://openalex.org/W2087064593","https://openalex.org/W2103014446","https://openalex.org/W2103487267","https://openalex.org/W2103934658","https://openalex.org/W2108235229","https://openalex.org/W2109034006","https://openalex.org/W2109464129","https://openalex.org/W2114699799","https://openalex.org/W2116628377","https://openalex.org/W2124281279","https://openalex.org/W2128591967","https://openalex.org/W2131702282","https://openalex.org/W2151135734","https://openalex.org/W2152331922","https://openalex.org/W2157812308","https://openalex.org/W2158714788","https://openalex.org/W2158874082","https://openalex.org/W2161845984","https://openalex.org/W2175671778","https://openalex.org/W4236611442","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2032737507","https://openalex.org/W2355763156","https://openalex.org/W2082932857","https://openalex.org/W4293872904","https://openalex.org/W3157818565","https://openalex.org/W2124852384","https://openalex.org/W1786707430","https://openalex.org/W4300504307","https://openalex.org/W2395836737","https://openalex.org/W2138454694"],"abstract_inverted_index":{"In":[0,33],"molecular":[1],"biology,":[2],"DNA":[3,14,30,51,129],"sequence":[4,31,52,130],"matching":[5],"is":[6],"one":[7],"of":[8,20,29,42,56,84,136,147,166],"the":[9,40,43,87,91,101,108,134,137,153,170],"most":[10],"crucial":[11],"operations.":[12],"Since":[13],"databases":[15],"contain":[16],"a":[17,71,145,163],"huge":[18],"volume":[19],"sequences,":[21],"fast":[22,105],"indexes":[23],"are":[24],"essential":[25],"for":[26,50,117,128],"efficient":[27,122],"processing":[28],"matching.":[32,131],"this":[34],"paper,":[35],"we":[36,69,140],"first":[37],"point":[38],"out":[39],"problems":[41],"suffix":[44,171],"tree,":[45],"an":[46],"index":[47,73,81,127],"structure":[48,74,82],"widely-used":[49],"matching,":[53],"in":[54,63],"respect":[55],"storage":[57,159],"overhead,":[58],"search":[59],"performance,":[60],"and":[61,100],"difficulty":[62],"seamless":[64],"integration":[65],"with":[66],"DBMS.":[67],"Then,":[68],"propose":[70],"new":[72],"that":[75,112,126,152],"resolves":[76],"such":[77],"problems.":[78],"The":[79,149],"proposed":[80,138,154],"consists":[83],"two":[85],"parts:":[86],"primary":[88],"part":[89,103],"realizes":[90],"trie":[92],"as":[93],"binary":[94],"bit-string":[95],"representation":[96],"without":[97],"any":[98],"pointers,":[99],"secondary":[102],"helps":[104],"access":[106],"to":[107,114],"trie's":[109],"leaf":[110],"nodes":[111],"need":[113],"be":[115,162],"accessed":[116],"post-processing.":[118],"We":[119],"also":[120],"suggest":[121],"algorithms":[123],"based":[124],"on":[125],"To":[132],"verify":[133],"superiority":[135],"approach,":[139,155],"conduct":[141],"performance":[142],"evaluation":[143],"via":[144],"series":[146],"experiments.":[148],"results":[150],"reveal":[151],"which":[156],"requires":[157],"smaller":[158],"space,":[160],"can":[161],"few":[164],"orders":[165],"magnitude":[167],"faster":[168],"than":[169],"tree.":[172]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}