{"id":"https://openalex.org/W2100406995","doi":"https://doi.org/10.1109/csb.2002.1039337","title":"Fast and sensitive alignment of large genomic sequences","display_name":"Fast and sensitive alignment of large genomic sequences","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2100406995","doi":"https://doi.org/10.1109/csb.2002.1039337","mag":"2100406995","pmid":"https://pubmed.ncbi.nlm.nih.gov/15838131"},"language":"en","primary_location":{"id":"doi:10.1109/csb.2002.1039337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2002.1039337","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/A5012113499","display_name":"Michael Brudno","orcid":"https://orcid.org/0000-0001-7947-2243"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Brudno","raw_affiliation_strings":["Gates Building, Computer Science Department, University of Stanford, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gates Building, Computer Science Department, University of Stanford, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220352","display_name":"Burkhard Morgenstern","orcid":"https://orcid.org/0000-0002-7431-2862"},"institutions":[{"id":"https://openalex.org/I20121455","display_name":"Bielefeld University","ror":"https://ror.org/02hpadn98","country_code":"DE","type":"education","lineage":["https://openalex.org/I20121455"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"B. Morgenstern","raw_affiliation_strings":["Lnternational Graduate School in Bioinformatics and Genome Research, Universitat Bielefeld, Bielefeld, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lnternational Graduate School in Bioinformatics and Genome Research, Universitat Bielefeld, Bielefeld, Germany","institution_ids":["https://openalex.org/I20121455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"138","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998999834060669,"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":0.9966999888420105,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9905999898910522,"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/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.7318994402885437},{"id":"https://openalex.org/keywords/synteny","display_name":"Synteny","score":0.6956779360771179},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.67792809009552},{"id":"https://openalex.org/keywords/chaos","display_name":"CHAOS (operating system)","score":0.6745156645774841},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6509112119674683},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5898236632347107},{"id":"https://openalex.org/keywords/smith\u2013waterman-algorithm","display_name":"Smith\u2013Waterman algorithm","score":0.5893203616142273},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5399447083473206},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5150372982025146},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.48958954215049744},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.4751553237438202},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4518054723739624},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43240368366241455},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4027017652988434},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36747950315475464},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3497845232486725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2564479112625122},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22723281383514404},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21968114376068115},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.11622235178947449},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09765163064002991}],"concepts":[{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.7318994402885437},{"id":"https://openalex.org/C53702515","wikidata":"https://www.wikidata.org/wiki/Q971246","display_name":"Synteny","level":4,"score":0.6956779360771179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67792809009552},{"id":"https://openalex.org/C2779374083","wikidata":"https://www.wikidata.org/wiki/Q5011038","display_name":"CHAOS (operating system)","level":2,"score":0.6745156645774841},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6509112119674683},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5898236632347107},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.5893203616142273},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5399447083473206},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5150372982025146},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.48958954215049744},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.4751553237438202},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4518054723739624},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43240368366241455},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4027017652988434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36747950315475464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3497845232486725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2564479112625122},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22723281383514404},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21968114376068115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.11622235178947449},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09765163064002991},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004252","descriptor_name":"DNA Mutational Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D051379","descriptor_name":"Mice","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/csb.2002.1039337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/csb.2002.1039337","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:15838131","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15838131","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W100731401","https://openalex.org/W938539187","https://openalex.org/W1597644352","https://openalex.org/W1964918240","https://openalex.org/W1965998064","https://openalex.org/W1977828801","https://openalex.org/W1986014242","https://openalex.org/W1990061958","https://openalex.org/W1999909705","https://openalex.org/W2015292449","https://openalex.org/W2018120747","https://openalex.org/W2034206030","https://openalex.org/W2038605324","https://openalex.org/W2041726559","https://openalex.org/W2052831012","https://openalex.org/W2055043387","https://openalex.org/W2059823654","https://openalex.org/W2070991879","https://openalex.org/W2078230568","https://openalex.org/W2094596493","https://openalex.org/W2099964107","https://openalex.org/W2107499729","https://openalex.org/W2116628377","https://openalex.org/W2116688916","https://openalex.org/W2125625789","https://openalex.org/W2139243714","https://openalex.org/W2142418779","https://openalex.org/W2143286856","https://openalex.org/W2149238618","https://openalex.org/W2152331922","https://openalex.org/W2161874991","https://openalex.org/W2165654401","https://openalex.org/W2170120590","https://openalex.org/W2337480916","https://openalex.org/W4236236547","https://openalex.org/W6604038179","https://openalex.org/W6635735125","https://openalex.org/W6676277162"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W1486249959","https://openalex.org/W2948014085","https://openalex.org/W4386770652","https://openalex.org/W2468116983","https://openalex.org/W2103737249","https://openalex.org/W2885386129","https://openalex.org/W2111937814","https://openalex.org/W2141530749","https://openalex.org/W2122131968"],"abstract_inverted_index":{"Comparative":[0],"analysis":[1],"of":[2,38,46,51,65,69,90,126,128,150,167,177],"syntenic":[3],"genome":[4],"sequences":[5,31],"can":[6,162],"be":[7],"used":[8,141],"to":[9,24,75,145],"identify":[10],"functional":[11],"sites":[12],"such":[13],"as":[14,96,142],"exons":[15],"and":[16,72,199],"regulatory":[17],"elements.":[18],"Here,":[19],"the":[20,63,147,151,164,175,178],"first":[21,82],"step":[22],"is":[23,60,74,189,201],"align":[25],"two":[26],"or":[27],"several":[28],"evolutionary":[29],"related":[30],"and,":[32],"in":[33],"recent":[34],"years,":[35],"a":[36,81,84,88,100,111,120],"number":[37],"computer":[39],"programs":[40,53],"have":[41],"been":[42],"developed":[43],"for":[44,123,187],"alignment":[45,153],"large":[47,133],"genomic":[48,134],"sequences.":[49,135],"Some":[50],"these":[52,105],"are":[54,108,140],"extremely":[55],"fast":[56,85],"but":[57,113],"often":[58],"time-efficiency":[59],"achieved":[61],"at":[62,191,203],"expense":[64],"sensitivity.":[66],"One":[67],"way":[68],"combining":[70],"speed":[71],"sensitivity":[73],"use":[76],"an":[77],"anchored-alignment":[78],"approach.":[79],"In":[80,99],"step,":[83,102],"heuristic":[86],"identifies":[87],"chain":[89],"strong":[91],"sequence":[92,130],"similarities":[93,131],"that":[94,159],"serve":[95],"anchor":[97,106,143],"points.":[98],"second":[101],"regions":[103],"between":[104],"points":[107,144],"aligned":[109],"using":[110],"slower":[112],"more":[114,170],"sensitive":[115],"method.":[116],"We":[117],"present":[118],"CHAOS,":[119],"novel":[121],"algorithm":[122],"rapid":[124],"identification":[125],"chains":[127],"local":[129],"among":[132],"Similarities":[136],"identified":[137],"by":[138,169,181],"CHAOS":[139,188,198],"improve":[146],"running":[148,165],"time":[149,166],"DIALIGN":[152,168,200],"program.":[154],"Systematic":[155],"test":[156],"runs":[157],"show":[158],"this":[160],"method":[161],"reduce":[163],"than":[171],"93%":[172],"while":[173],"affecting":[174],"quality":[176],"resulting":[179],"alignments":[180],"only":[182],"1%.":[183],"The":[184],"source":[185],"code":[186],"available":[190,202],"http://www.stanford.edu/~brudno/chaos/":[192],"An":[193],"integrated":[194],"program":[195],"package":[196],"containing":[197],"http://bibiserv.techfak.uni-bielefeld.de/dialign/":[204]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}