{"id":"https://openalex.org/W2091273836","doi":"https://doi.org/10.1089/cmb.2005.12.407","title":"Space-Efficient Whole Genome Comparisons with Burrows\u2013Wheeler Transforms","display_name":"Space-Efficient Whole Genome Comparisons with Burrows\u2013Wheeler Transforms","publication_year":2005,"publication_date":"2005-05-01","ids":{"openalex":"https://openalex.org/W2091273836","doi":"https://doi.org/10.1089/cmb.2005.12.407","mag":"2091273836","pmid":"https://pubmed.ncbi.nlm.nih.gov/15882139"},"language":"en","primary_location":{"id":"doi:10.1089/cmb.2005.12.407","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2005.12.407","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},"type":"review","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/A5058579652","display_name":"Ross A. Lippert","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ross A. Lippert","raw_affiliation_strings":["Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139","Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. lippert@math.mit.edu"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Mathematics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. lippert@math.mit.edu","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058579652"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.3716,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.85077906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"12","issue":"4","first_page":"407","last_page":"415"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9986000061035156,"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":0.991599977016449,"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/compressed-suffix-array","display_name":"Compressed suffix array","score":0.7258782982826233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864439249038696},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.628313422203064},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5990080833435059},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5641106963157654},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5577799081802368},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5085512399673462},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.49654895067214966},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.4880591630935669},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4787415862083435},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4528653025627136},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4496614336967468},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.43497735261917114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.427146315574646},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4129948019981384},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.240786612033844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23437395691871643},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18830442428588867},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13253998756408691},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11125335097312927}],"concepts":[{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.7258782982826233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864439249038696},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.628313422203064},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5990080833435059},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5641106963157654},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5577799081802368},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5085512399673462},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.49654895067214966},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.4880591630935669},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4787415862083435},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4528653025627136},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4496614336967468},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.43497735261917114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.427146315574646},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4129948019981384},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.240786612033844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23437395691871643},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18830442428588867},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13253998756408691},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11125335097312927},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1089/cmb.2005.12.407","is_oa":false,"landing_page_url":"https://doi.org/10.1089/cmb.2005.12.407","pdf_url":null,"source":{"id":"https://openalex.org/S78571599","display_name":"Journal of Computational Biology","issn_l":"1066-5277","issn":["1066-5277","1557-8666"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320443","host_organization_name":"Mary Ann Liebert, Inc.","host_organization_lineage":["https://openalex.org/P4310320443"],"host_organization_lineage_names":["Mary Ann Liebert, Inc."],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Biology","raw_type":"journal-article"},{"id":"pmid:15882139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15882139","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":"Journal of computational biology : a journal of computational molecular cell biology","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":18,"referenced_works":["https://openalex.org/W1487662321","https://openalex.org/W1543263356","https://openalex.org/W1557034006","https://openalex.org/W1608371561","https://openalex.org/W2017808314","https://openalex.org/W2030962049","https://openalex.org/W2054984882","https://openalex.org/W2056707490","https://openalex.org/W2073313438","https://openalex.org/W2121252285","https://openalex.org/W2124281279","https://openalex.org/W2152331922","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2533248932","https://openalex.org/W2610179052","https://openalex.org/W3021727955"],"related_works":["https://openalex.org/W2063841356","https://openalex.org/W2405149725","https://openalex.org/W2003608043","https://openalex.org/W2049350043","https://openalex.org/W3113848129","https://openalex.org/W1746392762","https://openalex.org/W1756312659","https://openalex.org/W2159613260","https://openalex.org/W75168880","https://openalex.org/W1786707430"],"abstract_inverted_index":{"The":[0,123],"starting":[1],"point":[2],"for":[3,22,84],"any":[4,43],"alignment":[5],"of":[6,12,38,52,54,105,127,157,189,197,200],"mammalian":[7,178],"genomes":[8,40,107,179],"is":[9,60,111,117,164,173],"the":[10,27,36,39,70,77,106,141,198],"computation":[11],"exact":[13],"matches":[14],"satisfying":[15],"various":[16],"criteria.":[17],"Time-efficient,":[18],"O(n),":[19],"data":[20,68,129,159,202],"structures":[21],"this":[23,116,128,158],"computation,":[24],"such":[25],"as":[26],"suffix":[28,72],"tree,":[29],"require":[30],"O(n":[31,87],"log(n))":[32,88],"space,":[33,94],"several":[34],"times":[35],"space":[37,98,110],"themselves.":[41,108],"Thus,":[42],"reasonable":[44],"whole-genome":[45],"comparative":[46],"project":[47],"finds":[48],"itself":[49],"requiring":[50],"tens":[51],"Gigabytes":[53],"RAM":[55,191],"to":[56,103,121,137,149,166,195],"maintain":[57],"time-efficiency.":[58],"This":[59],"beyond":[61],"most":[62,124],"modern":[63],"workstations.":[64],"With":[65],"a":[66,155,181],"new":[67],"structure,":[69],"compressed":[71],"array":[73],"(CSA)":[74],"implemented":[75],"via":[76],"Burrows-Wheeler":[78],"transform,":[79],"we":[80],"can":[81],"trade":[82],"time-efficiency":[83],"space-efficiency,":[85],"taking":[86],"time,":[89,115],"but":[90],"running":[91],"in":[92,96,140,192],"O(n)":[93],"typically":[95],"total":[97],"less":[99],"than":[100,114],"or":[101],"equal":[102],"that":[104,196],"If":[109],"more":[112],"expensive":[113],"an":[118],"appropriate":[119],"approach":[120],"consider.":[122],"space-efficient":[125],"implementation":[126,170],"structure":[130,160],"requires":[131],"5":[132],"bits":[133,146],"per":[134,147],"nucleotide":[135],"character":[136,148],"build":[138],"on-line,":[139],"worst":[142],"case,":[143],"and":[144,161],"2.5":[145],"store":[150],"once":[151],"built.":[152],"We":[153],"present":[154],"description":[156],"how":[162],"it":[163],"used":[165],"obtain":[167],"matches.":[168],"An":[169],"(called":[171],"bbbwt)":[172],"demonstrated":[174],"by":[175],"aligning":[176],"two":[177],"on":[180],"modest":[182],"workstation":[183],"equipped":[184],"with":[185],"under":[186],"2":[187],"GB":[188],"free":[190],"time":[193],"superior":[194],"implementations":[199],"other":[201],"structures.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
