{"id":"https://openalex.org/W2057253402","doi":"https://doi.org/10.1093/bioinformatics/btt020","title":"DSK: <i>k</i> -mer counting with very low memory usage","display_name":"DSK: <i>k</i> -mer counting with very low memory usage","publication_year":2013,"publication_date":"2013-01-16","ids":{"openalex":"https://openalex.org/W2057253402","doi":"https://doi.org/10.1093/bioinformatics/btt020","mag":"2057253402","pmid":"https://pubmed.ncbi.nlm.nih.gov/23325618"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btt020","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt020","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/5/652/50335664/bioinformatics_29_5_652.pdf","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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/29/5/652/50335664/bioinformatics_29_5_652.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070626642","display_name":"Guillaume Rizk","orcid":"https://orcid.org/0000-0002-1642-2625"},"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":false,"raw_author_name":"Guillaume Rizk","raw_affiliation_strings":["1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France","institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"]}]},{"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/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":false,"raw_author_name":"Dominique Lavenier","raw_affiliation_strings":["1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France","institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"]}]},{"author_position":"last","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":["1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Algorizk, 75013 Paris and 2ENS Cachan Brittany/IRISA, Campus de Beaulieu, 35700 Rennes, France","institution_ids":["https://openalex.org/I11559806","https://openalex.org/I2802519937"]}]}],"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":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":10.5614,"has_fulltext":true,"cited_by_count":316,"citation_normalized_percentile":{"value":0.98977078,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":"5","first_page":"652","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8141999840736389,"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":0.8141999840736389,"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/T10885","display_name":"Gene expression and cancer classification","score":0.0210999995470047,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.01759999990463257,"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/k-mer","display_name":"k-mer","score":0.7363408207893372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235119342803955},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.6411501169204712},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.615969181060791},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.48701173067092896},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.4757021367549896},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.451255202293396},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.43210458755493164},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4141797423362732},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34765520691871643},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2010766863822937},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.18082726001739502},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.1619446873664856},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14467191696166992}],"concepts":[{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.7363408207893372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235119342803955},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.6411501169204712},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.615969181060791},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.48701173067092896},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.4757021367549896},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.451255202293396},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.43210458755493164},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4141797423362732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34765520691871643},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2010766863822937},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.18082726001739502},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.1619446873664856},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14467191696166992},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btt020","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt020","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/5/652/50335664/bioinformatics_29_5_652.pdf","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:23325618","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23325618","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-00778473v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00778473","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":"Bioinformatics, 2013, 29 (5), pp.652-653. &#x27E8;10.1093/bioinformatics/btt020&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btt020","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btt020","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/29/5/652/50335664/bioinformatics_29_5_652.pdf","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"},"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"}],"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/W2057253402.pdf","grobid_xml":"https://content.openalex.org/works/W2057253402.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2096128575","https://openalex.org/W2163584430"],"related_works":["https://openalex.org/W2411730464","https://openalex.org/W2563930566","https://openalex.org/W2188499136","https://openalex.org/W1694672787","https://openalex.org/W2154749946","https://openalex.org/W2922326376","https://openalex.org/W2069197195","https://openalex.org/W1606491530","https://openalex.org/W2129541134","https://openalex.org/W2057253402"],"abstract_inverted_index":{"SUMMARY:":[0],"Counting":[1],"all":[2,89,141],"the":[3,14,24,43,93,133,142],"k-mers":[4,47,90,127],"(substrings":[5],"of":[6,17,23,45,63,72,88,144,153],"length":[7],"k)":[8],"in":[9,36,92,109,111,161],"DNA/RNA":[10],"sequencing":[11],"reads":[12,94],"is":[13,95,106,132,137],"preliminary":[15],"step":[16],"many":[18],"bioinformatics":[19],"applications.":[20],"However,":[21],"state":[22],"art":[25],"k-mer":[26,57,117,169],"counting":[27,170],"methods":[28],"require":[29],"that":[30,136],"a":[31,52,68,80,112,145,167],"large":[32],"data":[33],"structure":[34,39],"resides":[35],"memory.":[37],"Such":[38],"typically":[40],"grows":[41],"with":[42],"number":[44],"distinct":[46],"to":[48,101,139],"count.":[49],"We":[50],"present":[51,91],"new":[53],"streaming":[54,62],"algorithm":[55],"for":[56],"counting,":[58],"called":[59],"DSK":[60,131,164],"(disk":[61],"k-mers),":[64],"which":[65],"only":[66,150],"requires":[67],"fixed":[69],"user-defined":[70],"amount":[71],"memory":[73,110,154],"and":[74,83,97,155],"disk":[75,84,157],"space.":[76],"This":[77],"approach":[78,135],"realizes":[79],"memory,":[81],"time":[82],"trade-off.":[85],"The":[86,116],"multi-set":[87],"partitioned,":[96],"partitions":[98],"are":[99,119,128],"saved":[100],"disk.":[102],"Then,":[103],"each":[104,123],"partition":[105],"separately":[107],"loaded":[108],"temporary":[113],"hash":[114,124],"table.":[115,125],"counts":[118],"returned":[120],"by":[121],"traversing":[122],"Low-abundance":[126],"optionally":[129],"filtered.":[130],"first":[134],"able":[138],"count":[140],"27-mers":[143],"human":[146],"genome":[147],"dataset":[148],"using":[149],"4.0":[151],"GB":[152],"moderate":[156],"space":[158],"(160":[159],"GB),":[160],"17.9":[162],"h.":[163],"can":[165],"replace":[166],"popular":[168],"software":[171],"(Jellyfish)":[172],"on":[173],"small-memory":[174],"servers.":[175],"AVAILABILITY:":[176],"http://minia.genouest.org/dsk":[177]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":30},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2016-06-24T00:00:00"}
