{"id":"https://openalex.org/W2105656684","doi":"https://doi.org/10.1186/1748-7188-8-22","title":"Space-efficient and exact de Bruijn graph representation based on a Bloom filter","display_name":"Space-efficient and exact de Bruijn graph representation based on a Bloom filter","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2105656684","doi":"https://doi.org/10.1186/1748-7188-8-22","mag":"2105656684","pmid":"https://pubmed.ncbi.nlm.nih.gov/24040893"},"language":"en","primary_location":{"id":"doi:10.1186/1748-7188-8-22","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-8-22","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-8-22","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-8-22","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058310668","display_name":"Rayan Chikhi","orcid":"https://orcid.org/0000-0003-1099-8735"},"institutions":[{"id":"https://openalex.org/I11559806","display_name":"\u00c9cole Normale Sup\u00e9rieure Paris-Saclay","ror":"https://ror.org/00hx6zz33","country_code":"FR","type":"education","lineage":["https://openalex.org/I11559806","https://openalex.org/I277688954"]},{"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Rayan Chikhi","raw_affiliation_strings":["Computer Science department, ENS Cachan / IRISA / INRIA, Rennes 35042, France. chikhi@irisa.fr","ENS Cachan Bretagne - \u00c9cole normale sup\u00e9rieure - Cachan, antenne de Bretagne (Campus de Ker Lann - Avenue Robert Schuman - 35170 Bruz - France)","GenScale - Scalable, Optimized and Parallel Algorithms for Genomics (Campus de Beaulieu 35042 Rennes cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science department, ENS Cachan / IRISA / INRIA, Rennes 35042, France. chikhi@irisa.fr","institution_ids":["https://openalex.org/I2802519937"]},{"raw_affiliation_string":"ENS Cachan Bretagne - \u00c9cole normale sup\u00e9rieure - Cachan, antenne de Bretagne (Campus de Ker Lann - Avenue Robert Schuman - 35170 Bruz - France)","institution_ids":["https://openalex.org/I11559806"]},{"raw_affiliation_string":"GenScale - Scalable, Optimized and Parallel Algorithms for Genomics (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070626642","display_name":"Guillaume Rizk","orcid":"https://orcid.org/0000-0002-1642-2625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guillaume Rizk","raw_affiliation_strings":["Algorizk, Paris, 75013, France","Algorizk [Paris] (22 Avenue de Choisy 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Algorizk, Paris, 75013, France","institution_ids":[]},{"raw_affiliation_string":"Algorizk [Paris] (22 Avenue de Choisy 75013 Paris - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058310668"],"corresponding_institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":12.5053,"has_fulltext":true,"cited_by_count":385,"citation_normalized_percentile":{"value":0.99245828,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"22","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4453999996185303,"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":0.4453999996185303,"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/T11478","display_name":"Caching and Content Delivery","score":0.16920000314712524,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12029","display_name":"DNA and Biological Computing","score":0.10199999809265137,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.9610092639923096},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.9314297437667847},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.8235454559326172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6336073279380798},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.576535701751709},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5399250388145447},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.528431236743927},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.4942319691181183},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4711514711380005},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3658922612667084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3267233669757843},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29447704553604126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19528469443321228},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.18284377455711365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14246255159378052},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0770508348941803}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.9610092639923096},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9314297437667847},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8235454559326172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6336073279380798},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.576535701751709},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5399250388145447},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.528431236743927},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.4942319691181183},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4711514711380005},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3658922612667084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3267233669757843},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29447704553604126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19528469443321228},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.18284377455711365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14246255159378052},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0770508348941803}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1186/1748-7188-8-22","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-8-22","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-8-22","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:24040893","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24040893","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:europepmc.org:2835748","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3848682","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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3848682","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3848682","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.400.3879","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.400.3879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/86/88/05/PDF/1748-7188-8-22.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.469.8030","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.469.8030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://minia.genouest.org/files/minia.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.592.5413","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.592.5413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/75/39/30/PDF/minia.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00868805v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00868805","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, 2013, 8 (1), pp.22. &#x27E8;10.1186/1748-7188-8-22&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/1748-7188-8-22","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-8-22","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-8-22","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"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":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G580176235","display_name":"New sequential and distributed approaches in algorithmics and computational biology for the analysis of data generated by Next Generation Sequencers.","funder_award_id":"ANR-10-COSI-0004","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"},{"id":"https://openalex.org/G7240651115","display_name":null,"funder_award_id":"ANR-10","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2105656684.pdf","grobid_xml":"https://content.openalex.org/works/W2105656684.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W30658801","https://openalex.org/W1532744586","https://openalex.org/W1547576067","https://openalex.org/W1966822396","https://openalex.org/W1972924519","https://openalex.org/W2009119978","https://openalex.org/W2010361633","https://openalex.org/W2022910024","https://openalex.org/W2047665315","https://openalex.org/W2057253402","https://openalex.org/W2063544484","https://openalex.org/W2069074882","https://openalex.org/W2096128575","https://openalex.org/W2103635790","https://openalex.org/W2113915152","https://openalex.org/W2126419817","https://openalex.org/W2127768708","https://openalex.org/W2128524432","https://openalex.org/W2133531097","https://openalex.org/W2151674273","https://openalex.org/W2153124929","https://openalex.org/W2161546116","https://openalex.org/W2163830511"],"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/W3215786367","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W1908987670","https://openalex.org/W2025111520"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,70],"de":[2,17,33,56,98],"Bruijn":[3,34,57],"graph":[4,35],"data":[5],"structure":[6,81],"is":[7,72],"widely":[8],"used":[9],"in":[10,111],"next-generation":[11],"sequencing":[12],"(NGS).":[13],"Many":[14],"programs,":[15],"e.g.":[16],"novo":[18,99],"assemblers,":[19],"rely":[20],"on":[21,74],"in-memory":[22],"representation":[23],"of":[24,36,44,54,63,101,109],"this":[25,92],"graph.":[26],"However,":[27],"current":[28,68],"techniques":[29],"for":[30],"representing":[31],"the":[32,55],"a":[37,41,51,75,96],"human":[38,102],"genome":[39,103],"require":[40],"large":[42],"amount":[43],"memory":[45,110],"(\u226530":[46],"GB).":[47],"RESULTS:":[48],"We":[49],"propose":[50],"new":[52],"encoding":[53,71],"graph,":[58],"which":[59],"occupies":[60],"an":[61,79],"order":[62],"magnitude":[64],"less":[65],"space":[66],"than":[67],"representations.":[69],"based":[73],"Bloom":[76],"filter,":[77],"with":[78],"additional":[80],"to":[82],"remove":[83],"critical":[84],"false":[85],"positives.":[86],"CONCLUSIONS:":[87],"An":[88],"assembly":[89,100],"software":[90],"implementing":[91],"structure,":[93],"Minia,":[94],"performed":[95],"complete":[97],"short":[104],"reads":[105],"using":[106],"5.7":[107],"GB":[108],"23":[112],"hours.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":37},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":45},{"year":2016,"cited_by_count":36},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":7}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
