{"id":"https://openalex.org/W2014099509","doi":"https://doi.org/10.1093/bioinformatics/bts690","title":"Musket: a multistage <i>k-</i>mer spectrum-based error corrector for Illumina sequence data","display_name":"Musket: a multistage <i>k-</i>mer spectrum-based error corrector for Illumina sequence data","publication_year":2012,"publication_date":"2012-11-29","ids":{"openalex":"https://openalex.org/W2014099509","doi":"https://doi.org/10.1093/bioinformatics/bts690","mag":"2014099509","pmid":"https://pubmed.ncbi.nlm.nih.gov/23202746"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bts690","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts690","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100617992","display_name":"Yongchao Liu","orcid":"https://orcid.org/0000-0003-3440-9675"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["AU","DE"],"is_corresponding":true,"raw_author_name":"Yongchao Liu","raw_affiliation_strings":["1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108605263","display_name":"Jan Schr\u00f6der","orcid":"https://orcid.org/0000-0001-5270-0605"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["AU","DE"],"is_corresponding":false,"raw_author_name":"Jan Schr\u00f6der","raw_affiliation_strings":["1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["AU","DE"],"is_corresponding":true,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Institut f\u00fcr Informatik, Johannes Gutenberg Universit\u00e4t Mainz, Mainz 55099, Germany and 2Department of Computing and Information Systems, The University of Melbourne, Parkville 3010, Australia","institution_ids":["https://openalex.org/I165779595","https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020388832","https://openalex.org/A5100617992"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I197323543"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":7.2411,"has_fulltext":false,"cited_by_count":309,"citation_normalized_percentile":{"value":0.98138408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"29","issue":"3","first_page":"308","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9857000112533569,"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":0.9857000112533569,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6643370389938354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5249645113945007},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4962170720100403},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46686840057373047},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.438112735748291},{"id":"https://openalex.org/keywords/illumina-dye-sequencing","display_name":"Illumina dye sequencing","score":0.432400643825531},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.2468961477279663},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.163510262966156},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.155948668718338},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13347852230072021},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.06323361396789551}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6643370389938354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5249645113945007},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4962170720100403},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46686840057373047},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.438112735748291},{"id":"https://openalex.org/C106337198","wikidata":"https://www.wikidata.org/wiki/Q13564012","display_name":"Illumina dye sequencing","level":4,"score":0.432400643825531},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2468961477279663},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.163510262966156},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.155948668718338},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13347852230072021},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.06323361396789551},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":"D002877","descriptor_name":"Chromosomes, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002877","descriptor_name":"Chromosomes, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002877","descriptor_name":"Chromosomes, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bts690","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bts690","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:23202746","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23202746","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}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1966822396","https://openalex.org/W1980667059","https://openalex.org/W2022986961","https://openalex.org/W2046594687","https://openalex.org/W2054226908","https://openalex.org/W2084134542","https://openalex.org/W2097529842","https://openalex.org/W2101250487","https://openalex.org/W2105708056","https://openalex.org/W2107824361","https://openalex.org/W2115501618","https://openalex.org/W2119745866","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2122812051","https://openalex.org/W2123845384","https://openalex.org/W2127768708","https://openalex.org/W2131088968","https://openalex.org/W2133956160","https://openalex.org/W2136651963","https://openalex.org/W2142702487","https://openalex.org/W2142749416","https://openalex.org/W2152246890","https://openalex.org/W2155845142","https://openalex.org/W2159647614","https://openalex.org/W2159946869","https://openalex.org/W2160265768","https://openalex.org/W2160665949","https://openalex.org/W2160969485","https://openalex.org/W2161488606","https://openalex.org/W2161546116","https://openalex.org/W2163584430","https://openalex.org/W2799140574","https://openalex.org/W6675137652","https://openalex.org/W6683504902"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W4243495532","https://openalex.org/W1570863047","https://openalex.org/W2544131529","https://openalex.org/W2593875055","https://openalex.org/W2092772380","https://openalex.org/W2272685092","https://openalex.org/W1977321866","https://openalex.org/W2773451817","https://openalex.org/W3090794301"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,24],"imperfect":[2],"sequence":[3],"data":[4,42],"produced":[5,43],"by":[6,44],"next-generation":[7],"sequencing":[8,46],"technologies":[9],"have":[10],"motivated":[11],"the":[12,30,37,86,130],"development":[13],"of":[14,17,26,32,55,65,114,129],"a":[15,96,140,157],"number":[16],"short-read":[18,82],"error":[19,39],"correctors":[20,153],"in":[21,41,53,63,95,112],"recent":[22],"years.":[23],"majority":[25],"methods":[27],"focus":[28],"on":[29],"correction":[31,93,104,115],"substitution":[33],"errors,":[34],"which":[35],"are":[36],"dominant":[38],"source":[40],"Illumina":[45,81],"technology.":[47],"Existing":[48],"tools":[49],"either":[50],"score":[51],"high":[52,62],"terms":[54,64,113],"recall":[56],"or":[57],"precision":[58],"but":[59],"not":[60],"consistently":[61,127],"both":[66],"measures.":[67],"RESULTS:":[68],"In":[69,134],"this":[70],"article,":[71],"we":[72],"present":[73],"Musket,":[74],"an":[75],"efficient":[76],"multistage":[77,97],"k-mer-based":[78],"corrector":[79],"for":[80],"data.":[83],"We":[84],"use":[85],"k-mer":[87],"spectrum":[88],"approach":[89],"and":[90,105,117,143],"introduce":[91],"three":[92],"techniques":[94],"workflow:":[98],"two-sided":[99],"conservative":[100],"correction,":[101],"one-sided":[102],"aggressive":[103],"voting-based":[106],"refinement.":[107],"Our":[108],"performance":[109],"evaluation":[110],"results,":[111],"quality":[116],"de":[118],"novo":[119],"genome":[120],"assembly":[121],"measures,":[122],"reveal":[123],"that":[124],"Musket":[125,136,164],"is":[126,137,165],"one":[128],"top":[131],"performing":[132],"correctors.":[133],"addition,":[135],"multi-threaded":[138],"using":[139],"master-slave":[141],"model":[142],"demonstrates":[144],"superior":[145],"parallel":[146],"scalability":[147],"compared":[148],"with":[149],"all":[150],"other":[151],"evaluated":[152],"as":[154,156],"well":[155],"highly":[158],"competitive":[159],"overall":[160],"execution":[161],"time.":[162],"AVAILABILITY:":[163],"available":[166],"at":[167],"http://musket.sourceforge.net.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":32},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":33},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":25},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-06-24T00:00:00"}
