{"id":"https://openalex.org/W1931027898","doi":"https://doi.org/10.1186/s12859-015-0709-7","title":"Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph","display_name":"Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph","publication_year":2015,"publication_date":"2015-09-14","ids":{"openalex":"https://openalex.org/W1931027898","doi":"https://doi.org/10.1186/s12859-015-0709-7","mag":"1931027898","pmid":"https://pubmed.ncbi.nlm.nih.gov/26370285"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-015-0709-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0709-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0709-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0709-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065622224","display_name":"Ga\u00ebtan Benoit","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210099593","display_name":"Computer Algorithms for Medicine","ror":"https://ror.org/00zky6d38","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210099593"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["AT","FR","GB"],"is_corresponding":false,"raw_author_name":"Ga\u00ebtan Benoit","raw_affiliation_strings":["INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. gaetan.benoit@inria.fr","Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. gaetan.benoit@inria.fr","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210133778","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":["https://openalex.org/I4210099593","https://openalex.org/I4210151791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087524785","display_name":"Claire Lemaitre","orcid":"https://orcid.org/0000-0001-8675-170X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210099593","display_name":"Computer Algorithms for Medicine","ror":"https://ror.org/00zky6d38","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210099593"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["AT","FR","GB"],"is_corresponding":false,"raw_author_name":"Claire Lemaitre","raw_affiliation_strings":["INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. claire.lemaitre@inria.fr","Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. claire.lemaitre@inria.fr","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210133778","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":["https://openalex.org/I4210099593","https://openalex.org/I4210151791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008215565","display_name":"Dominique Lavenier","orcid":"https://orcid.org/0000-0003-2557-680X"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210099593","display_name":"Computer Algorithms for Medicine","ror":"https://ror.org/00zky6d38","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210099593"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["AT","FR","GB"],"is_corresponding":false,"raw_author_name":"Dominique Lavenier","raw_affiliation_strings":["INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. dominique.lavenier@irisa.fr","Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. dominique.lavenier@irisa.fr","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":["https://openalex.org/I4210099593","https://openalex.org/I4210151791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015197047","display_name":"Erwan Dr\u00e9zen","orcid":"https://orcid.org/0000-0002-4054-5668"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210099593","display_name":"Computer Algorithms for Medicine","ror":"https://ror.org/00zky6d38","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210099593"]},{"id":"https://openalex.org/I4210133778","display_name":"Centre Inria de l'Universit\u00e9 de Rennes","ror":"https://ror.org/04040yw90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["AT","FR","GB"],"is_corresponding":false,"raw_author_name":"Erwan Drezen","raw_affiliation_strings":["INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. erwan.drezen@inria.fr","Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. erwan.drezen@inria.fr","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210133778","https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":["https://openalex.org/I4210099593","https://openalex.org/I4210151791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073204917","display_name":"Thibault Dayris","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/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thibault Dayris","raw_affiliation_strings":["University of Bordeaux, CNRS/LaBRI, Talence, F-33405, France. thibault.dayris@outlook.fr","Laboratoire Bordelais de Recherche en Informatique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bordeaux, CNRS/LaBRI, Talence, F-33405, France. thibault.dayris@outlook.fr","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I1294671590","https://openalex.org/I4210142254"]},{"raw_affiliation_string":"Laboratoire Bordelais de Recherche en Informatique","institution_ids":["https://openalex.org/I4210142254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008422748","display_name":"Raluca Uricaru","orcid":"https://orcid.org/0000-0002-5730-6428"},"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/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Raluca Uricaru","raw_affiliation_strings":["University of Bordeaux, CBiB, Bordeaux, F-33000, France. ruricaru@labri.fr","University of Bordeaux, CNRS/LaBRI, Talence, F-33405, France. ruricaru@labri.fr","Laboratoire Bordelais de Recherche en Informatique","Centre de Bioinformatique de Bordeaux"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bordeaux, CBiB, Bordeaux, F-33000, France. ruricaru@labri.fr","institution_ids":["https://openalex.org/I15057530"]},{"raw_affiliation_string":"University of Bordeaux, CNRS/LaBRI, Talence, F-33405, France. ruricaru@labri.fr","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I1294671590","https://openalex.org/I4210142254"]},{"raw_affiliation_string":"Laboratoire Bordelais de Recherche en Informatique","institution_ids":["https://openalex.org/I4210142254"]},{"raw_affiliation_string":"Centre de Bioinformatique de Bordeaux","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070626642","display_name":"Guillaume Rizk","orcid":"https://orcid.org/0000-0002-1642-2625"},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210099593","display_name":"Computer Algorithms for Medicine","ror":"https://ror.org/00zky6d38","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210099593"]},{"id":"https://openalex.org/I4210151791","display_name":"Genomics (United Kingdom)","ror":"https://ror.org/053a6xa29","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210151791"]}],"countries":["AT","FR","GB"],"is_corresponding":true,"raw_author_name":"Guillaume Rizk","raw_affiliation_strings":["INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. guillaume.rizk@gmail.com","Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA/IRISA/GenScale, Campus de Beaulieu, Rennes, 35042, France. guillaume.rizk@gmail.com","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":["https://openalex.org/I4210099593","https://openalex.org/I4210151791"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070626642"],"corresponding_institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I4210099593","https://openalex.org/I4210151791"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":7.3801,"has_fulltext":true,"cited_by_count":111,"citation_normalized_percentile":{"value":0.9783018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"288","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.891700029373169,"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":0.891700029373169,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.017400000244379044,"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":0.014600000344216824,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.8413889408111572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717353105545044},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5942498445510864},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5149696469306946},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.4682924151420593},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.4657056927680969},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4640952944755554},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44094857573509216},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4407346248626709},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4260193407535553},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.32659289240837097},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3001326322555542},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12900379300117493},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12544551491737366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11192378401756287}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8413889408111572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717353105545044},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5942498445510864},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5149696469306946},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.4682924151420593},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.4657056927680969},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4640952944755554},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44094857573509216},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4407346248626709},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4260193407535553},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.32659289240837097},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3001326322555542},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12900379300117493},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12544551491737366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11192378401756287},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","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":"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":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011336","descriptor_name":"Probability","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":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017173","descriptor_name":"Caenorhabditis elegans","qualifier_ui":"Q000235","qualifier_name":"genetics","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},{"descriptor_ui":"D029742","descriptor_name":"Caenorhabditis elegans Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029742","descriptor_name":"Caenorhabditis elegans Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D029742","descriptor_name":"Caenorhabditis elegans Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044962","descriptor_name":"Data Compression","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"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:10.1186/s12859-015-0709-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0709-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0709-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26370285","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26370285","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:HAL:hal-01214682v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01214682","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":"BMC Bioinformatics, 2015, 16 (1), &#x27E8;10.1186/s12859-015-0709-7&#x27E9;","raw_type":"Journal articles"},{"id":"pmh:oai:europepmc.org:3546170","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4570262","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:10.1186/s12859-015-0709-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0709-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-015-0709-7","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[{"id":"https://openalex.org/G5275960024","display_name":null,"funder_award_id":"ANR-12-BS02-0008","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5869189860","display_name":"Genomic Assembly Tool Box","funder_award_id":"ANR-12-EMMA-0019","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6702880738","display_name":null,"funder_award_id":"ANR-12","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1931027898.pdf","grobid_xml":"https://content.openalex.org/works/W1931027898.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W109642580","https://openalex.org/W2010361633","https://openalex.org/W2057253402","https://openalex.org/W2069066547","https://openalex.org/W2092880969","https://openalex.org/W2101247207","https://openalex.org/W2103441770","https://openalex.org/W2104677379","https://openalex.org/W2105656684","https://openalex.org/W2108234281","https://openalex.org/W2109153336","https://openalex.org/W2110800670","https://openalex.org/W2111044311","https://openalex.org/W2116041602","https://openalex.org/W2125266506","https://openalex.org/W2129652681","https://openalex.org/W2129949113","https://openalex.org/W2131106408","https://openalex.org/W2138196010","https://openalex.org/W2143423077","https://openalex.org/W2151752966","https://openalex.org/W2153707226","https://openalex.org/W2156660460","https://openalex.org/W2157836505","https://openalex.org/W2159084616","https://openalex.org/W2159906372","https://openalex.org/W2163830511","https://openalex.org/W2166588423","https://openalex.org/W2170727800","https://openalex.org/W2179064901","https://openalex.org/W2186783357","https://openalex.org/W2198888083","https://openalex.org/W2890128382"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W2354744388","https://openalex.org/W3125399386","https://openalex.org/W2949121831","https://openalex.org/W2991626973","https://openalex.org/W4387083702","https://openalex.org/W4318940746","https://openalex.org/W2133531097","https://openalex.org/W2079322808"],"abstract_inverted_index":{"BACKGROUND:":[0],"Data":[1],"volumes":[2],"generated":[3],"by":[4,106,189],"next-generation":[5],"sequencing":[6,55,154,181],"(NGS)":[7],"technologies":[8],"is":[9,73,98,122,194],"now":[10],"a":[11,43,76,93,101,112,126,176],"major":[12],"concern":[13],"for":[14,24,144,206],"both":[15],"data":[16,50],"storage":[17],"and":[18,90,111],"transmission.":[19],"This":[20],"triggered":[21],"the":[22,35,61,86,130,185],"need":[23],"more":[25,190],"efficient":[26],"methods":[27],"than":[28,171,191],"general":[29],"purpose":[30],"compression":[31,138,169,173],"tools,":[32],"such":[33],"as":[34,100],"widely":[36],"used":[37,123],"gzip":[38],"method.":[39],"RESULTS:":[40],"We":[41],"present":[42],"novel":[44],"reference-free":[45],"method":[46,72],"meant":[47],"to":[48,124,135],"compress":[49],"issued":[51],"from":[52,67,85],"high":[53],"throughput":[54],"technologies.":[56],"Our":[57],"approach,":[58],"implemented":[59],"in":[60,92,103],"software":[62],"LEON,":[63],"employs":[64],"techniques":[65],"derived":[66],"existing":[68],"assembly":[69],"principles.":[70],"The":[71,116],"based":[74],"on":[75,151],"reference":[77],"probabilistic":[78,118],"de":[79,83,119],"Bruijn":[80,120],"Graph,":[81],"built":[82],"novo":[84],"set":[87],"of":[88,114,129],"reads":[89],"stored":[91],"Bloom":[94],"filter.":[95],"Each":[96],"read":[97],"encoded":[99],"path":[102],"this":[104],"graph,":[105],"memorizing":[107],"an":[108,195],"anchoring":[109],"kmer":[110],"list":[113],"bifurcations.":[115],"same":[117],"Graph":[121],"perform":[125],"lossy":[127],"transformation":[128],"quality":[131],"scores,":[132],"which":[133],"allows":[134],"obtain":[136],"higher":[137,167],"rates":[139],"without":[140],"losing":[141],"pertinent":[142],"information":[143],"downstream":[145],"analyses.":[146],"CONCLUSIONS:":[147],"LEON":[148,165,183,193],"was":[149],"run":[150],"various":[152],"real":[153],"datasets":[155],"(whole":[156],"genome,":[157],"exome,":[158],"RNA-seq":[159],"or":[160],"metagenomics).":[161],"In":[162],"all":[163],"cases,":[164],"showed":[166],"overall":[168],"ratios":[170],"state-of-the-art":[172],"software.":[174],"On":[175],"C.":[177],"elegans":[178],"whole":[179],"genome":[180],"dataset,":[182],"divided":[184],"original":[186],"file":[187],"size":[188],"20.":[192],"open":[196],"source":[197],"software,":[198],"distributed":[199],"under":[200],"GNU":[201],"affero":[202],"GPL":[203],"License,":[204],"available":[205],"download":[207],"at":[208],"http://gatb.inria.fr/software/leon/.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":8}],"updated_date":"2026-06-17T08:01:34.144755","created_date":"2025-10-10T00:00:00"}
