{"id":"https://openalex.org/W2414876472","doi":"https://doi.org/10.1109/tcbb.2015.2430314","title":"Parallel and Space-Efficient Construction of Burrows-Wheeler Transform and Suffix Array for Big Genome Data","display_name":"Parallel and Space-Efficient Construction of Burrows-Wheeler Transform and Suffix Array for Big Genome Data","publication_year":2015,"publication_date":"2015-05-06","ids":{"openalex":"https://openalex.org/W2414876472","doi":"https://doi.org/10.1109/tcbb.2015.2430314","mag":"2414876472","pmid":"https://pubmed.ncbi.nlm.nih.gov/27295644"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2015.2430314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2015.2430314","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","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/A5100617992","display_name":"Yongchao Liu","orcid":"https://orcid.org/0000-0003-3440-9675"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongchao Liu","raw_affiliation_strings":["School of Computational Science & Engineering, Georgia Institute of Technology, GA, Atlanta"],"raw_orcid":"https://orcid.org/0000-0003-3440-9675","affiliations":[{"raw_affiliation_string":"School of Computational Science & Engineering, Georgia Institute of Technology, GA, Atlanta","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003394017","display_name":"Thomas Hankeln","orcid":"https://orcid.org/0000-0002-0677-8417"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Hankeln","raw_affiliation_strings":["Institut f\u00fcr Molekulargenetik, Johannes Gutenberg Universit\u00e4t Mainz, Germany","[Institut f\u00fcr Molekulargenetik, Johannes Gutenberg Universit\u00e4t Mainz, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Molekulargenetik, Johannes Gutenberg Universit\u00e4t Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"[Institut f\u00fcr Molekulargenetik, Johannes Gutenberg Universit\u00e4t Mainz, Germany]","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Germany","Institut f\u00fcr Informatik, Johannes Gutenberg-Universit\u00e4t,#N#Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Institut f\u00fcr Informatik, Johannes Gutenberg-Universit\u00e4t,#N#Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.689,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94114264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"13","issue":"3","first_page":"592","last_page":"598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9921000003814697,"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":0.9584000110626221,"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/suffix","display_name":"Suffix","score":0.5708542466163635},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.5588854551315308},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5412795543670654},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5155056118965149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4912826418876648},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.48030298948287964},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4794984459877014},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2809235453605652},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.2514936327934265},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2253287136554718},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1616382896900177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11196613311767578},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.086005300283432},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0772750973701477}],"concepts":[{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.5708542466163635},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.5588854551315308},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5412795543670654},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5155056118965149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4912826418876648},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.48030298948287964},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4794984459877014},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2809235453605652},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.2514936327934265},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2253287136554718},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1616382896900177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11196613311767578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.086005300283432},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0772750973701477},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":"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":"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":2,"locations":[{"id":"doi:10.1109/tcbb.2015.2430314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2015.2430314","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:27295644","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27295644","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G7469405548","display_name":null,"funder_award_id":"IIS-1416259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322301","display_name":"Johannes Gutenberg-Universit\u00e4t Mainz","ror":"https://ror.org/023b0x485"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W9498632","https://openalex.org/W1489909987","https://openalex.org/W1557034006","https://openalex.org/W1826264422","https://openalex.org/W1987760161","https://openalex.org/W2011699809","https://openalex.org/W2014099509","https://openalex.org/W2063431258","https://openalex.org/W2067974452","https://openalex.org/W2103441770","https://openalex.org/W2105708056","https://openalex.org/W2107824361","https://openalex.org/W2111217142","https://openalex.org/W2115501618","https://openalex.org/W2117683095","https://openalex.org/W2118703123","https://openalex.org/W2124985265","https://openalex.org/W2127465481","https://openalex.org/W2128016314","https://openalex.org/W2131581981","https://openalex.org/W2139749722","https://openalex.org/W2157460239","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2161488606","https://openalex.org/W2170899819","https://openalex.org/W2171196697","https://openalex.org/W3016205154","https://openalex.org/W6683504902"],"related_works":["https://openalex.org/W2576782855","https://openalex.org/W2359436045","https://openalex.org/W153119118","https://openalex.org/W2143531254","https://openalex.org/W2608759984","https://openalex.org/W363060408","https://openalex.org/W2003608043","https://openalex.org/W2055795184","https://openalex.org/W2123393931","https://openalex.org/W2295072202"],"abstract_inverted_index":{"Next-generation":[0],"sequencing":[1,7],"technologies":[2],"have":[3,45],"led":[4],"to":[5,51,125,138,145,163,169,193],"the":[6,17,53,85,87,112,118,182],"of":[8,19,55,98,184,190],"more":[9,11],"and":[10,33,117,127,143,161,176,200],"genomes,":[12],"propelling":[13],"related":[14],"research":[15],"into":[16],"era":[18],"big":[20,39],"data.":[21,41],"In":[22,42],"this":[23],"paper,":[24],"we":[25,44],"present":[26],"ParaBWT,":[27,43],"a":[28,47,65,79,93],"parallelized":[29,74],"Burrows-Wheeler":[30],"transform":[31],"(BWT)":[32],"suffix":[34,88],"array":[35,89],"construction":[36,49,151],"algorithm":[37],"for":[38,153],"genome":[40,57,110],"investigated":[46],"progressive":[48],"approach":[50,70],"constructing":[52],"BWT":[54,150],"single":[56],"sequences":[58,105,157],"in":[59,92,198],"linear":[60],"space":[61],"complexity,":[62],"but":[63],"with":[64],"small":[66,179],"constant":[67],"factor.":[68],"This":[69],"has":[71,100],"been":[72,101],"further":[73],"using":[75,103],"multi-threading":[76],"based":[77],"on":[78,131],"master-slave":[80],"coprocessing":[81],"model.":[82],"After":[83],"gaining":[84],"BWT,":[86],"is":[90,174,196,201],"constructed":[91],"memory-efficient":[94],"manner.":[95],"The":[96],"performance":[97,123],"ParaBWT":[99,135,195],"evaluated":[102],"two":[104,108],"generated":[106],"from":[107],"human":[109,119],"assemblies:":[111],"Ensembl":[113],"Homo":[114],"sapiens":[115],"assembly":[116],"reference":[120],"genome.":[121],"Our":[122],"comparison":[124],"FMD-index":[126,142,188],"Bwt-disk":[128],"reveals":[129],"that":[130],"12":[132],"CPU":[133],"cores,":[134],"runs":[136],"up":[137,144],"2.2\u00d7":[139],"faster":[140,147],"than":[141,148],"99.0\u00d7":[146],"Bwt-disk.":[149],"algorithms":[152],"very":[154],"long":[155],"genomic":[156],"are":[158,189],"time":[159],"consuming":[160],"(due":[162],"their":[164,172],"incremental":[165],"nature)":[166],"inherently":[167],"difficult":[168],"parallelize.":[170],"Thus,":[171],"parallelization":[173],"challenging":[175],"even":[177],"relatively":[178],"speedups":[180],"like":[181],"ones":[183],"our":[185],"method":[186],"over":[187],"high":[191],"importance":[192],"research.":[194],"written":[197],"C++,":[199],"freely":[202],"available":[203],"at":[204],"http://parabwt.sourceforge.net.":[205]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
