{"id":"https://openalex.org/W2147477044","doi":"https://doi.org/10.1093/bioinformatics/btu014","title":"Efficient haplotype matching and storage using the positional Burrows\u2013Wheeler transform (PBWT)","display_name":"Efficient haplotype matching and storage using the positional Burrows\u2013Wheeler transform (PBWT)","publication_year":2014,"publication_date":"2014-01-09","ids":{"openalex":"https://openalex.org/W2147477044","doi":"https://doi.org/10.1093/bioinformatics/btu014","mag":"2147477044","pmid":"https://pubmed.ncbi.nlm.nih.gov/24413527"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btu014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/9/1266/647197/btu014.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/30/9/1266/647197/btu014.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082040351","display_name":"Richard Durbin","orcid":"https://orcid.org/0000-0002-9130-1006"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Richard Durbin","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge CB10 1SA, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082040351"],"corresponding_institution_ids":["https://openalex.org/I2802476451"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":{"value":3989,"currency":"USD","value_usd":3989},"fwci":14.1087,"has_fulltext":true,"cited_by_count":520,"citation_normalized_percentile":{"value":0.99212185,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":"9","first_page":"1266","last_page":"1272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.4749000072479248,"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"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.4749000072479248,"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/T11269","display_name":"Algorithms and Data Compression","score":0.21060000360012054,"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/T10751","display_name":"Forensic and Genetic Research","score":0.0722000002861023,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6573747396469116},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5841861367225647},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.5002269744873047},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4707515835762024},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45706596970558167},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45527926087379456},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.44280096888542175},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41213545203208923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3939821124076843},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32150018215179443},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.2832784950733185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2590632140636444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.233108252286911},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.135860413312912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6573747396469116},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5841861367225647},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.5002269744873047},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4707515835762024},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45706596970558167},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45527926087379456},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.44280096888542175},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41213545203208923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3939821124076843},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32150018215179443},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2832784950733185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2590632140636444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.233108252286911},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.135860413312912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000483","descriptor_name":"Alleles","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006239","descriptor_name":"Haplotypes","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btu014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/9/1266/647197/btu014.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:24413527","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24413527","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":"Journal Article"},{"id":"pmh:oai:europepmc.org:2975781","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3998136","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.786.4574","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.786.4574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ncbi.nlm.nih.gov/pub/pmc/0c/41/btu014.PMC3998136.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btu014","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btu014","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/30/9/1266/647197/btu014.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/G8666890344","display_name":"Wellcome Trust Sanger Institute - generic account for deposition of all core- funded research papers","funder_award_id":"098051","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"}],"funders":[{"id":"https://openalex.org/F4320308963","display_name":"Oak Ridge Associated Universities","ror":"https://ror.org/0526p1y61"},{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147477044.pdf","grobid_xml":"https://content.openalex.org/works/W2147477044.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W9498632","https://openalex.org/W2061539393","https://openalex.org/W2080613667","https://openalex.org/W2087036932","https://openalex.org/W2096791516","https://openalex.org/W2097341408","https://openalex.org/W2103441770","https://openalex.org/W2107121611","https://openalex.org/W2110887924","https://openalex.org/W2124985265","https://openalex.org/W2129713651","https://openalex.org/W2138345444","https://openalex.org/W2139760555","https://openalex.org/W2158322625","https://openalex.org/W2161488606","https://openalex.org/W2165141658","https://openalex.org/W6683030939","https://openalex.org/W6683504902"],"related_works":["https://openalex.org/W2010725720","https://openalex.org/W4310066305","https://openalex.org/W1746392762","https://openalex.org/W2159613260","https://openalex.org/W2003608043","https://openalex.org/W2549663625","https://openalex.org/W1975060495","https://openalex.org/W2741342861","https://openalex.org/W2039208882","https://openalex.org/W1990262198"],"abstract_inverted_index":{"MOTIVATION:":[0],"Over":[1],"the":[2,12,34,44,73,127,139,165,182,219],"last":[3],"few":[4],"years,":[5],"methods":[6,58],"based":[7,63,129],"on":[8,38,56,64,130,164],"suffix":[9,91],"arrays":[10,133],"using":[11,90,162],"Burrows-Wheeler":[13,141],"Transform":[14],"have":[15],"been":[16],"widely":[17],"used":[18,232],"for":[19,51,59,208,233],"DNA":[20],"sequence":[21,217],"read":[22],"matching":[23,66,89],"and":[24,61,196,218,235],"assembly.":[25],"These":[26],"provide":[27],"very":[28],"fast":[29,199],"search":[30,35],"algorithms,":[31],"linear":[32],"in":[33,184],"pattern":[36],"size,":[37],"a":[39,85,124,155,158,171,198,215],"highly":[40],"compressible":[41],"representation":[42,125,170],"of":[43,72,87,126,157,203],"dataset":[45],"being":[46],"searched.":[47],"Meanwhile,":[48],"algorithmic":[49],"development":[50],"genotype":[52,108],"data":[53,128],"has":[54],"concentrated":[55],"statistical":[57],"phasing":[60],"imputation,":[62],"probabilistic":[65],"to":[67,122,175,210],"hidden":[68],"Markov":[69],"model":[70],"representations":[71],"reference":[74],"data,":[75],"which":[76,96,136],"while":[77],"powerful":[78],"are":[79],"much":[80,100],"less":[81],"computationally":[82],"efficient.":[83],"Here":[84],"theory":[86],"haplotype":[88,179],"array":[92],"ideas":[93],"is":[94,134,137,173],"developed,":[95],"should":[97],"scale":[98],"too":[99],"larger":[101],"datasets":[102,146],"than":[103,154,161,188],"those":[104],"currently":[105],"handled":[106],"by":[107,152],"algorithms.":[109],"RESULTS:":[110],"Given":[111],"M":[112,204],"sequences":[113],"with":[114,149],"N":[115],"bi-allelic":[116],"variable":[117],"sites,":[118],"an":[119],"O(NM)":[120,185],"algorithm":[121],"derive":[123],"positional":[131,140],"prefix":[132],"given,":[135],"termed":[138],"transform":[142],"(PBWT).":[143],"On":[144],"large":[145],"this":[147,169],"compresses":[148],"run-length":[150],"encoding":[151],"more":[153],"factor":[156],"hundred":[159],"smaller":[160],"gzip":[163],"raw":[166],"data.":[167],"Using":[168],"method":[172],"given":[174,205],"find":[176,211],"all":[177],"maximal":[178,212],"matches":[180,213],"within":[181],"set":[183],"time":[186],"rather":[187],"O(NM(2))":[189],"as":[190],"expected":[191],"from":[192],"naive":[193],"pairwise":[194],"comparison,":[195],"also":[197],"algorithm,":[200],"empirically":[201],"independent":[202],"sufficient":[206],"memory":[207],"indexes,":[209],"between":[214],"new":[216],"set.":[220],"The":[221],"discussion":[222],"includes":[223],"some":[224],"proposals":[225],"about":[226],"how":[227],"these":[228],"approaches":[229],"could":[230],"be":[231],"imputation":[234],"phasing.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":62},{"year":2022,"cited_by_count":48},{"year":2021,"cited_by_count":57},{"year":2020,"cited_by_count":74},{"year":2019,"cited_by_count":56},{"year":2018,"cited_by_count":44},{"year":2017,"cited_by_count":37},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}