{"id":"https://openalex.org/W2134411445","doi":"https://doi.org/10.1109/csb.2002.1039343","title":"Accelerating approximate subsequence search on large protein sequence databases","display_name":"Accelerating approximate subsequence search on large protein sequence databases","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2134411445","doi":"https://doi.org/10.1109/csb.2002.1039343","mag":"2134411445","pmid":"https://pubmed.ncbi.nlm.nih.gov/15838137"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2002.1039343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2002.1039343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101465493","display_name":"Jiong Yang","orcid":"https://orcid.org/0000-0003-0328-2317"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiong Yang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["CS Department"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS Department","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013754313","display_name":"Yi Xia","orcid":"https://orcid.org/0000-0002-2485-4188"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Xia","raw_affiliation_strings":["CS Department, University of California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P.S. Yu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"207","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503058910369873},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.730147659778595},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7055437564849854},{"id":"https://openalex.org/keywords/subsequence","display_name":"Subsequence","score":0.7025778889656067},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.6557621359825134},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.6519259214401245},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.534058690071106},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5333124995231628},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4754571318626404},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4517579972743988},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4373909533023834},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2952364683151245},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.24781212210655212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14452078938484192},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.08718404173851013}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503058910369873},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.730147659778595},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7055437564849854},{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.7025778889656067},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.6557621359825134},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.6519259214401245},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.534058690071106},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5333124995231628},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4754571318626404},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4517579972743988},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4373909533023834},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2952364683151245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24781212210655212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14452078938484192},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.08718404173851013},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1109/csb.2002.1039343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2002.1039343","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":"proceedings-article"},{"id":"pmid:15838137","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15838137","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":"Proceedings. IEEE Computer Society Bioinformatics Conference","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.11.3460","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.3460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucla.edu/~jyang/publications/csb02_2.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.77.7858","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.77.7858","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.unc.edu/~weiwang/paper/CSB02_2.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W109756832","https://openalex.org/W1540616176","https://openalex.org/W1557390898","https://openalex.org/W1659313070","https://openalex.org/W1714821586","https://openalex.org/W1754958282","https://openalex.org/W1990061958","https://openalex.org/W2001273972","https://openalex.org/W2026054568","https://openalex.org/W2028445324","https://openalex.org/W2028903194","https://openalex.org/W2028904582","https://openalex.org/W2033376980","https://openalex.org/W2035524445","https://openalex.org/W2043481183","https://openalex.org/W2055043387","https://openalex.org/W2059513841","https://openalex.org/W2087721273","https://openalex.org/W2089900521","https://openalex.org/W2121252285","https://openalex.org/W2134616089","https://openalex.org/W2140654616","https://openalex.org/W2158714788","https://openalex.org/W2165156013","https://openalex.org/W2295428206","https://openalex.org/W2320748401","https://openalex.org/W2610179052","https://openalex.org/W2751199251","https://openalex.org/W2752885492","https://openalex.org/W2753439427","https://openalex.org/W4231916799","https://openalex.org/W4236236547","https://openalex.org/W4245668478","https://openalex.org/W6604467028","https://openalex.org/W6632287593","https://openalex.org/W6633180349","https://openalex.org/W6637520298","https://openalex.org/W6657664104"],"related_works":["https://openalex.org/W4383749413","https://openalex.org/W2110723042","https://openalex.org/W1505866794","https://openalex.org/W4301000806","https://openalex.org/W4237510188","https://openalex.org/W2158269934","https://openalex.org/W2048379072","https://openalex.org/W1562055306","https://openalex.org/W2163864652","https://openalex.org/W2134411445"],"abstract_inverted_index":{"Bioinformatics":[0],"has":[1,20,28,37,87,98,200],"become":[2],"an":[3,148,213],"active":[4],"research":[5],"area":[6],"in":[7,157,189,203,212],"recent":[8],"years.":[9],"The":[10,84,129,177],"amount":[11],"of":[12,115,179,196,215],"mapped":[13],"sequences":[14,26,79,104],"doubles":[15],"every":[16,43],"fourteen":[17],"months.":[18],"BLAST":[19,36,223],"been":[21,88,99,201],"widely":[22],"employed":[23],"for":[24,77,134],"retrieving":[25],"which":[27],"similar":[29],"portion(s)":[30],"to":[31,38,71,80,93,125,138,153,186],"a":[32,46,73,91,126,139,161,193],"given":[33],"sequence.":[34],"However,":[35],"scan":[39],"the":[40,58,67,113,187,190,207,222,226],"entire":[41],"database":[42,59,96,136,191],"time":[44,54,159],"when":[45,57],"query":[47],"is":[48,60,211],"issued.":[49],"This":[50],"can":[51,182],"be":[52,183],"very":[53],"consuming":[55],"especially":[56],"large.":[61],"In":[62],"this":[63,167],"paper,":[64],"we":[65,146],"study":[66],"problem":[68,114],"on":[69,101,160],"how":[70],"build":[72],"persistent":[74],"index":[75,94,175],"structure":[76],"protein":[78,135,163],"support":[81,154],"approximate":[82,155,172,180],"match.":[83],"suffix":[85,227],"tree":[86],"proposed":[89],"as":[90,170,221],"solution":[92],"sequence":[95,171],"and":[97,225],"deployed":[100],"organizing":[102],"DNA":[103],"(Hunt":[105],"et":[106],"al.":[107],"2001).":[108],"Unfortunately,":[109],"it":[110,120],"suffers":[111],"from":[112,121],"\"memory":[116],"bottleneck\"":[117],"that":[118,206],"prevents":[119],"being":[122],"applied":[123],"efficiently":[124],"large":[127,162],"database.":[128,164],"performance":[130,209],"even":[131],"degrades":[132],"further":[133],"due":[137],"larger":[140],"fanout":[141],"at":[142],"each":[143],"node.":[144],"Here,":[145],"employ":[147],"indexing":[149,168],"structure,":[150],"called":[151],"BASS-tree,":[152],"match":[156,173],"sublinear":[158],"We":[165],"call":[166],"method":[169],"(SAM)":[174],"method.":[176],"search":[178],"matches":[181],"properly":[184],"directed":[185],"portion":[188],"with":[192],"high":[194],"potential":[195,208],"matching":[197],"quickly.":[198],"It":[199],"demonstrated":[202],"our":[204],"experiments":[205],"improvement":[210],"order":[214],"magnitude":[216],"over":[217],"alternative":[218],"methods":[219],"such":[220],"algorithm":[224],"tree.":[228]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}