{"id":"https://openalex.org/W3142668023","doi":"https://doi.org/10.1093/bioinformatics/btab217","title":"BLight: efficient exact associative structure for k-mers","display_name":"BLight: efficient exact associative structure for k-mers","publication_year":2021,"publication_date":"2021-04-02","ids":{"openalex":"https://openalex.org/W3142668023","doi":"https://doi.org/10.1093/bioinformatics/btab217","mag":"3142668023","pmid":"https://pubmed.ncbi.nlm.nih.gov/33821954"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab217","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab217","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048303382","display_name":"Camille Marchet","orcid":"https://orcid.org/0000-0002-7235-7346"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Camille Marchet","raw_affiliation_strings":["University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France"],"raw_orcid":"https://orcid.org/0000-0002-7235-7346","affiliations":[{"raw_affiliation_string":"University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107332376","display_name":"Mael Kerbiriou","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mael Kerbiriou","raw_affiliation_strings":["University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001793115","display_name":"Antoine Limasset","orcid":"https://orcid.org/0000-0002-0669-4141"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Antoine Limasset","raw_affiliation_strings":["University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille , CRIStAL CNRS, UMR 9189 - F-59000 Lille, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001793115","https://openalex.org/A5048303382"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970","https://openalex.org/I4387153239"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.0731,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.87907223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"37","issue":"18","first_page":"2858","last_page":"2865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.34529998898506165,"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":0.34529998898506165,"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/T11269","display_name":"Algorithms and Data Compression","score":0.09139999747276306,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.05299999937415123,"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":0.7630493640899658},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.6027445197105408},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5987434387207031},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5260693430900574},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5011944770812988},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.47505709528923035},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4139694273471832},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4075855314731598},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3737240433692932},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1830759048461914},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17776638269424438},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13211151957511902},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12868958711624146},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11896371841430664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630493640899658},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.6027445197105408},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5987434387207031},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5260693430900574},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5011944770812988},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.47505709528923035},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4139694273471832},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4075855314731598},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3737240433692932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1830759048461914},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17776638269424438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13211151957511902},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12868958711624146},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11896371841430664},{"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":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","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":"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":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","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":"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":3,"locations":[{"id":"doi:10.1093/bioinformatics/btab217","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab217","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33821954","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33821954","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:HAL:hal-03443183v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03443183","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2021, 37 (18), pp.2858-2865. &#x27E8;10.1093/bioinformatics/btab217&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2404422535","display_name":"Transcriptional signatures for global RNA-seq analysis","funder_award_id":"ANR-18-CE45-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2010361633","https://openalex.org/W2057970678","https://openalex.org/W2105656684","https://openalex.org/W2113679889","https://openalex.org/W2116041602","https://openalex.org/W2120902911","https://openalex.org/W2122316710","https://openalex.org/W2123845384","https://openalex.org/W2125266506","https://openalex.org/W2133531097","https://openalex.org/W2144560237","https://openalex.org/W2159647614","https://openalex.org/W2194172909","https://openalex.org/W2266239166","https://openalex.org/W2323326409","https://openalex.org/W2438121987","https://openalex.org/W2589379462","https://openalex.org/W2589404674","https://openalex.org/W2592760774","https://openalex.org/W2759261668","https://openalex.org/W2784936077","https://openalex.org/W2809649683","https://openalex.org/W2949074212","https://openalex.org/W2949667635","https://openalex.org/W2951822379","https://openalex.org/W2952379095","https://openalex.org/W2963158913","https://openalex.org/W3043153155","https://openalex.org/W6734070449","https://openalex.org/W6734145011"],"related_works":["https://openalex.org/W4378651134","https://openalex.org/W1979633005","https://openalex.org/W2352307597","https://openalex.org/W2163724607","https://openalex.org/W1980092392","https://openalex.org/W2608983118","https://openalex.org/W4318812462","https://openalex.org/W37347591","https://openalex.org/W2118976126","https://openalex.org/W2278452282"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1],"plethora":[2],"of":[3,24,43,142,162],"methods":[4],"and":[5,74,85,123,151,208,246],"applications":[6],"share":[7],"the":[8,133,136,152,155,176,223,233],"fundamental":[9],"need":[10],"to":[11,14,47,58,61,79,83,97,131,212],"associate":[12,59,80],"information":[13,60],"words":[15],"for":[16,22],"high-throughput":[17],"sequence":[18],"analysis.":[19],"Doing":[20],"so":[21],"billions":[23],"k-mers":[25,46,62,84,134,153],"is":[26,121,240],"commonly":[27],"a":[28,72,90,102,179,189,243],"scalability":[29],"problem,":[30],"as":[31,226,242],"exact":[32,75],"associative":[33],"indexes":[34],"can":[35,204],"be":[36],"memory":[37,104,163,174],"expensive.":[38],"Recent":[39],"works":[40],"take":[41],"advantage":[42],"overlaps":[44],"between":[45],"leverage":[48],"this":[49],"challenge.":[50],"Yet,":[51],"existing":[52],"data":[53,76,211],"structures":[54],"are":[55,64],"either":[56],"unable":[57],"or":[63,192],"not":[65],"lightweight":[66],"enough.":[67],"RESULTS:":[68],"We":[69,221],"present":[70,201],"BLight,":[71],"static":[73],"structure":[77],"able":[78],"unique":[81],"identifiers":[82],"determine":[86],"their":[87],"membership":[88],"in":[89],"set":[91],"without":[92],"false":[93],"positive":[94],"that":[95],"scales":[96],"huge":[98],"k-mer":[99],"sets":[100],"with":[101,114,249],"low":[103],"cost.":[105],"This":[106],"index":[107,132,177,225],"combines":[108],"an":[109,227],"extremely":[110],"compact":[111],"representation":[112],"along":[113,248],"very":[115,180],"fast":[116],"queries.":[117],"Besides,":[118],"its":[119,214],"construction":[120],"efficient":[122],"needs":[124],"no":[125],"additional":[126],"memory.":[127],"Our":[128],"implementation":[129],"achieves":[130],"from":[135,154],"human":[137],"genome":[138,158],"using":[139,159,195],"8":[140],"GB":[141,161],"RAM":[143],"(23":[144],"bits":[145,165],"per":[146,166,186],"k-mer)":[147,167],"within":[148,168],"10":[149],"min":[150],"large":[156],"axolotl":[157],"63":[160],"(27":[164],"76":[169],"min.":[170],"Furthermore,":[171],"while":[172],"being":[173],"efficient,":[175],"provides":[178],"high":[181],"throughput:":[182],"1.4":[183],"million":[184,194],"queries":[185],"second":[187],"on":[188],"single":[190],"CPU":[191],"16.1":[193],"12":[196],"cores.":[197],"Finally,":[198],"we":[199],"also":[200],"how":[202],"BLight":[203,224],"practically":[205],"represent":[206],"metagenomic":[207],"transcriptomic":[209],"sequencing":[210],"highlight":[213],"wide":[215],"applicative":[216],"range.":[217],"AVAILABILITY":[218],"AND":[219],"IMPLEMENTATION:":[220],"wrote":[222],"open":[228],"source":[229],"C++":[230],"library":[231,245],"under":[232],"AGPL3":[234],"license":[235],"available":[236],"at":[237],"github.com/Malfoy/BLight.":[238],"It":[239],"designed":[241],"user-friendly":[244],"comes":[247],"code":[250],"usage":[251],"samples.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-25T17:18:41.151588","created_date":"2025-10-10T00:00:00"}
