{"id":"https://openalex.org/W3082608226","doi":"https://doi.org/10.1186/s13015-021-00192-7","title":"Disk compression of k-mer sets","display_name":"Disk compression of k-mer sets","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3082608226","doi":"https://doi.org/10.1186/s13015-021-00192-7","mag":"3082608226","pmid":"https://pubmed.ncbi.nlm.nih.gov/34154632"},"language":"en","primary_location":{"id":"doi:10.1186/s13015-021-00192-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-021-00192-7","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-021-00192-7","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","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-021-00192-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055479093","display_name":"Amatur Rahman","orcid":"https://orcid.org/0000-0002-9166-1220"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amatur Rahman","raw_affiliation_strings":["Penn State University, State College, PA, USA. aur1111@psu.edu","Pennsylvania State University"],"raw_orcid":"https://orcid.org/0000-0002-9166-1220","affiliations":[{"raw_affiliation_string":"Penn State University, State College, PA, USA. aur1111@psu.edu","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058310668","display_name":"Rayan Chikhi","orcid":"https://orcid.org/0000-0003-1099-8735"},"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/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I157536573"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rayan Chikhi","raw_affiliation_strings":["Department of Computational Biology, C3BI USR 3756 CNRS, Institut Pasteur, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Biology, C3BI USR 3756 CNRS, Institut Pasteur, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I157536573"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Penn State University, State College, PA, USA","Pennsylvania State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055479093"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00777642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"1","first_page":"10","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9991999864578247,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10885","display_name":"Gene expression and cancer classification","score":0.9923999905586243,"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/compression","display_name":"Compression (physics)","score":0.5725265145301819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5720367431640625},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.42619380354881287},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21976974606513977},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.18079987168312073},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.13606828451156616}],"concepts":[{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5725265145301819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720367431640625},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.42619380354881287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21976974606513977},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.18079987168312073},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.13606828451156616}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/s13015-021-00192-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-021-00192-7","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-021-00192-7","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:34154632","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34154632","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:HAL:hal-03165270v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03165270","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":"WABI 2020, Sep 2020, Pisa, Italy","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:doaj.org/article:7126c47cc903415d9ed68f00ae1e8d99","is_oa":true,"landing_page_url":"https://doaj.org/article/7126c47cc903415d9ed68f00ae1e8d99","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 16, Iss 1, Pp 1-14 (2021)","raw_type":"article"},{"id":"pmh:oai:drops-oai.dagstuhl.de:12805","is_oa":true,"landing_page_url":"https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.WABI.2020.16","pdf_url":null,"source":{"id":"https://openalex.org/S4377196569","display_name":"DROPS (Schloss Dagstuhl \u2013 Leibniz Center for Informatics)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2799853480","host_organization_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","host_organization_lineage":["https://openalex.org/I2799853480"],"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":"InProceedings"},{"id":"pmh:oai:pubmedcentral.nih.gov:8218509","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8218509","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":"doi:10.4230/lipics.wabi.2020.16","is_oa":true,"landing_page_url":"https://doi.org/10.4230/lipics.wabi.2020.16","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1186/s13015-021-00192-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13015-021-00192-7","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/s13015-021-00192-7","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G1870429759","display_name":null,"funder_award_id":"T32GM102057","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3926047959","display_name":"XPS: FULL: DSD: End-to-end Acceleration of Genomic Workflows on Emerging Heterogeneous Supercomputers","funder_award_id":"1439057","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5196283127","display_name":"Institut Convergences pour l\u2019\u00e9tude de l\u2019Emergence des Pathologies au Travers des Individus et des populatiONs","funder_award_id":"ANR-16-CONV-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082608226.pdf","grobid_xml":"https://content.openalex.org/works/W3082608226.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W1964377951","https://openalex.org/W2057253402","https://openalex.org/W2096128575","https://openalex.org/W2120902911","https://openalex.org/W2127768708","https://openalex.org/W2158678815","https://openalex.org/W2159954944","https://openalex.org/W2266239166","https://openalex.org/W2438121987","https://openalex.org/W2531091319","https://openalex.org/W2538355508","https://openalex.org/W2543131432","https://openalex.org/W2583363792","https://openalex.org/W2809649683","https://openalex.org/W2883729812","https://openalex.org/W2884435343","https://openalex.org/W2903772466","https://openalex.org/W2913847081","https://openalex.org/W2922407406","https://openalex.org/W2949074212","https://openalex.org/W2949503312","https://openalex.org/W2950150251","https://openalex.org/W2951230321","https://openalex.org/W2951594653","https://openalex.org/W2959670948","https://openalex.org/W2964150838","https://openalex.org/W2969627863","https://openalex.org/W2979522844","https://openalex.org/W2994050678","https://openalex.org/W3000185529","https://openalex.org/W3013820283","https://openalex.org/W3147478436","https://openalex.org/W4392493223"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W1967080779","https://openalex.org/W2612632602","https://openalex.org/W2321805087"],"abstract_inverted_index":{"K-mer":[0],"based":[1],"methods":[2,102],"have":[3],"become":[4],"prevalent":[5],"in":[6,63],"many":[7],"areas":[8],"of":[9,91,106,119,130,161,173],"bioinformatics.":[10],"In":[11,66,95],"applications":[12],"such":[13,25],"as":[14],"database":[15],"search,":[16],"they":[17,53,145],"often":[18],"work":[19,69],"with":[20],"large":[21,26],"multi-terabyte-sized":[22],"datasets.":[23,162],"Storing":[24],"datasets":[27],"is":[28],"a":[29,82,89,115,159],"detriment":[30],"to":[31,87,93,123,155,178],"tool":[32,34],"developers,":[33],"users,":[35],"and":[36,71,111,138],"reproducibility":[37],"efforts.":[38],"General":[39],"purpose":[40],"compressors":[41],"like":[42],"gzip,":[43],"or":[44],"those":[45],"designed":[46],"for":[47,103],"read":[48],"data,":[49],"are":[50],"sub-optimal":[51],"because":[52],"do":[54],"not":[55],"take":[56],"into":[57],"account":[58],"the":[59,128,147],"specific":[60],"redundancy":[61,126],"pattern":[62],"k-mer":[64,107],"sets.":[65],"our":[67],"earlier":[68],"(Rahman":[70],"Medvedev,":[72],"RECOMB":[73],"2020),":[74],"we":[75,98],"presented":[76],"an":[77],"algorithm":[78],"UST-Compress":[79,152],"that":[80,144],"uses":[81],"spectrum-preserving":[83],"string":[84,120],"set":[85,90,121],"representation":[86,122,129],"compress":[88],"k-mers":[92],"disk.":[94],"this":[96,171],"paper,":[97],"present":[99],"two":[100],"improved":[101],"disk":[104],"compression":[105,148,174],"sets,":[108],"called":[109],"ESS-Compress":[110],"ESS-Tip-Compress.":[112],"They":[113],"use":[114],"more":[116],"relaxed":[117],"notion":[118],"further":[124],"remove":[125],"from":[127],"UST-Compress.":[131],"We":[132,142,163],"explore":[133],"their":[134],"behavior":[135],"both":[136],"theoretically":[137],"on":[139,168],"real":[140],"data.":[141],"show":[143],"improve":[146],"sizes":[149],"achieved":[150],"by":[151,153],"up":[154],"27":[156],"percent,":[157],"across":[158],"breadth":[160],"also":[164],"derive":[165],"lower":[166],"bounds":[167],"how":[169],"well":[170],"type":[172],"strategy":[175],"can":[176],"hope":[177],"do.":[179]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
