{"id":"https://openalex.org/W2171791108","doi":"https://doi.org/10.1093/bioinformatics/bts456","title":"YAHA: fast and flexible long-read alignment with optimal breakpoint detection","display_name":"YAHA: fast and flexible long-read alignment with optimal breakpoint detection","publication_year":2012,"publication_date":"2012-07-24","ids":{"openalex":"https://openalex.org/W2171791108","doi":"https://doi.org/10.1093/bioinformatics/bts456","mag":"2171791108","pmid":"https://pubmed.ncbi.nlm.nih.gov/22829624"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bts456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts456","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/19/2417/48877729/bioinformatics_28_19_2417.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/28/19/2417/48877729/bioinformatics_28_19_2417.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091480053","display_name":"Gregory G. Faust","orcid":"https://orcid.org/0000-0002-8233-9408"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory G. Faust","raw_affiliation_strings":["1 Department of Computer Science, 2Department of Biochemistry and Molecular Genetics and 3Center for Public Health Genomics, University of Virginia, Charlottesville, 22908 VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Department of Biochemistry and Molecular Genetics and 3Center for Public Health Genomics, University of Virginia, Charlottesville, 22908 VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026920706","display_name":"Ira M. Hall","orcid":"https://orcid.org/0000-0003-4442-6655"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ira M. Hall","raw_affiliation_strings":["1 Department of Computer Science, 2Department of Biochemistry and Molecular Genetics and 3Center for Public Health Genomics, University of Virginia, Charlottesville, 22908 VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, 2Department of Biochemistry and Molecular Genetics and 3Center for Public Health Genomics, University of Virginia, Charlottesville, 22908 VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026920706"],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.1187,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.87584325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"19","first_page":"2417","last_page":"2424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9538999795913696,"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":0.9538999795913696,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.0044999998062849045,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/computer-science","display_name":"Computer science","score":0.8253848552703857},{"id":"https://openalex.org/keywords/breakpoint","display_name":"Breakpoint","score":0.7152689695358276},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6059345006942749},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.5514050722122192},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48948538303375244},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.4711880683898926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3909296691417694},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3540652394294739},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3465542793273926},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14598649740219116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253848552703857},{"id":"https://openalex.org/C206936463","wikidata":"https://www.wikidata.org/wiki/Q634179","display_name":"Breakpoint","level":4,"score":0.7152689695358276},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6059345006942749},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.5514050722122192},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48948538303375244},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.4711880683898926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3909296691417694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3540652394294739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3465542793273926},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14598649740219116},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138626823","wikidata":"https://www.wikidata.org/wiki/Q916504","display_name":"Chromosomal translocation","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":"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":"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":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bts456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts456","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/19/2417/48877729/bioinformatics_28_19_2417.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22829624","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22829624","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:europepmc.org:2460804","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3463118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bts456","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts456","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/28/19/2417/48877729/bioinformatics_28_19_2417.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3070476645","display_name":null,"funder_award_id":"DP2OD006493-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4246930347","display_name":null,"funder_award_id":"DP2 OD006493","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G441298149","display_name":null,"funder_award_id":"T32 GM008715","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G6752462419","display_name":null,"funder_award_id":"T32 GM08715","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2171791108.pdf","grobid_xml":"https://content.openalex.org/works/W2171791108.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W2015292449","https://openalex.org/W2042272913","https://openalex.org/W2045040686","https://openalex.org/W2055043387","https://openalex.org/W2068448872","https://openalex.org/W2103011829","https://openalex.org/W2103441770","https://openalex.org/W2107688500","https://openalex.org/W2108215151","https://openalex.org/W2108234281","https://openalex.org/W2109948920","https://openalex.org/W2132341951","https://openalex.org/W2134800079","https://openalex.org/W2136145671","https://openalex.org/W2142619120","https://openalex.org/W2150356570","https://openalex.org/W2611102567","https://openalex.org/W4247053599","https://openalex.org/W4293196852","https://openalex.org/W6675949863","https://openalex.org/W6842402754"],"related_works":["https://openalex.org/W2391366911","https://openalex.org/W2056763800","https://openalex.org/W2138588808","https://openalex.org/W69216466","https://openalex.org/W1988408736","https://openalex.org/W2355995003","https://openalex.org/W2391206957","https://openalex.org/W2375712659","https://openalex.org/W2352031993","https://openalex.org/W2146912220"],"abstract_inverted_index":{"MOTIVATION:":[0],"With":[1],"improved":[2],"short-read":[3],"assembly":[4],"algorithms":[5],"and":[6,42,50,62,66,72,149,168],"the":[7,18,56,106,131],"recent":[8],"development":[9],"of":[10,109,130],"long-read":[11],"sequencers,":[12],"split":[13],"mapping":[14],"will":[15],"soon":[16],"be":[17],"preferred":[19],"method":[20],"for":[21,34,174],"structural":[22],"variant":[23],"(SV)":[24],"detection.":[25],"Yet,":[26],"current":[27],"alignment":[28,59,87],"tools":[29],"are":[30,171],"not":[31],"well":[32],"suited":[33],"this.":[35],"RESULTS:":[36],"We":[37,133],"present":[38],"YAHA,":[39],"a":[40,100,113,116],"fast":[41,49],"flexible":[43],"hash-based":[44],"aligner.":[45],"YAHA":[46,98,121,136,159],"is":[47,63,160],"as":[48,52],"accurate":[51],"BWA-SW":[53,144],"at":[54,74,152],"finding":[55,75],"single":[57],"best":[58],"per":[60,88,127],"query":[61,114],"dramatically":[64],"faster":[65],"more":[67,138],"sensitive":[68],"than":[69,143],"both":[70],"SSAHA2":[71],"MegaBLAST":[73],"all":[76,146],"possible":[77],"alignments.":[78],"Unlike":[79],"other":[80],"aligners":[81],"that":[82,91,111,135],"report":[83,124],"all,":[84],"or":[85,90],"one,":[86],"query,":[89],"use":[92],"simple":[93],"heuristics":[94],"to":[95,104],"select":[96],"alignments,":[97],"uses":[99],"directed":[101],"acyclic":[102],"graph":[103],"find":[105],"optimal":[107],"set":[108],"alignments":[110],"cover":[112],"using":[115],"biologically":[117],"relevant":[118],"breakpoint":[119],"penalty.":[120],"can":[122],"also":[123],"multiple":[125,156],"mappings":[126],"defined":[128],"segment":[129],"query.":[132],"show":[134],"detects":[137],"breakpoints":[139],"in":[140],"less":[141],"time":[142],"across":[145],"SV":[147],"classes,":[148],"especially":[150],"excels":[151],"complex":[153],"SVs":[154],"comprising":[155],"breakpoints.":[157],"AVAILABILITY:":[158],"currently":[161],"supported":[162],"on":[163],"64-bit":[164],"Linux":[165],"systems.":[166],"Binaries":[167],"sample":[169],"data":[170],"freely":[172],"available":[173],"download":[175],"from":[176],"http://faculty.virginia.edu/irahall/YAHA.":[177],"CONTACT:":[178],"imh4y@virginia.edu.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2025-10-10T00:00:00"}
