{"id":"https://openalex.org/W2162667876","doi":"https://doi.org/10.1093/bioinformatics/btv401","title":"Error filtering, pair assembly and error correction for next-generation sequencing reads","display_name":"Error filtering, pair assembly and error correction for next-generation sequencing reads","publication_year":2015,"publication_date":"2015-07-02","ids":{"openalex":"https://openalex.org/W2162667876","doi":"https://doi.org/10.1093/bioinformatics/btv401","mag":"2162667876","pmid":"https://pubmed.ncbi.nlm.nih.gov/26139637"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv401","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv401","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/21/3476/17122369/btv401.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/31/21/3476/17122369/btv401.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077667471","display_name":"R. C. Edgar","orcid":"https://orcid.org/0000-0001-7355-2541"},"institutions":[{"id":"https://openalex.org/I4210097329","display_name":"Tiburon Associates (United States)","ror":"https://ror.org/00wns3e34","country_code":"US","type":"company","lineage":["https://openalex.org/I4210097329"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert C. Edgar","raw_affiliation_strings":["1 Tiburon, CA 94920, USA and"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Tiburon, CA 94920, USA and","institution_ids":["https://openalex.org/I4210097329"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023339029","display_name":"Henrik Flyvbjerg","orcid":"https://orcid.org/0000-0002-1691-9367"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Henrik Flyvbjerg","raw_affiliation_strings":["2 Department of Micro- and Nanotechnology, Technical University of Denmark, DK-2800 Lyngby, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 Department of Micro- and Nanotechnology, Technical University of Denmark, DK-2800 Lyngby, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077667471"],"corresponding_institution_ids":["https://openalex.org/I4210097329"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":31.6978,"has_fulltext":true,"cited_by_count":1352,"citation_normalized_percentile":{"value":0.99857152,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"21","first_page":"3476","last_page":"3482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.878600001335144,"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":0.878600001335144,"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":0.07649999856948853,"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":0.020099999383091927,"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/computer-science","display_name":"Computer science","score":0.7247559428215027},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.618546187877655},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5476268529891968},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.514470100402832},{"id":"https://openalex.org/keywords/amplicon-sequencing","display_name":"Amplicon sequencing","score":0.502016544342041},{"id":"https://openalex.org/keywords/amplicon","display_name":"Amplicon","score":0.45134326815605164},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43894582986831665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41660842299461365},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33928871154785156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.206538587808609},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13805660605430603},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0786493718624115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0769006609916687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247559428215027},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.618546187877655},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5476268529891968},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.514470100402832},{"id":"https://openalex.org/C2993206177","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon sequencing","level":4,"score":0.502016544342041},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.45134326815605164},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43894582986831665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41660842299461365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33928871154785156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.206538587808609},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13805660605430603},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0786493718624115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0769006609916687},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.0},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"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/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"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":"D012984","descriptor_name":"Software","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":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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:10.1093/bioinformatics/btv401","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv401","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/21/3476/17122369/btv401.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:26139637","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26139637","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:open-archive.highwire.org:bioinfo:31/21/3476","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/31/21/3476","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"},{"id":"pmh:oai:pure.atira.dk:publications/d389ffb4-6602-496e-980c-ec3075c18abd","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/d389ffb4-6602-496e-980c-ec3075c18abd","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"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":"Edgar , R C &amp; Flyvbjerg , H 2015 , ' Error filtering, pair assembly and error correction for next-generation sequencing reads ' , Bioinformatics , vol. 31 , no. 21 , pp. 3476-3482 . https://doi.org/10.1093/bioinformatics/btv401","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btv401","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv401","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/21/3476/17122369/btv401.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2162667876.pdf","grobid_xml":"https://content.openalex.org/works/W2162667876.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1991486768","https://openalex.org/W2000072710","https://openalex.org/W2072970694","https://openalex.org/W2085786299","https://openalex.org/W2086865963","https://openalex.org/W2088833470","https://openalex.org/W2095575865","https://openalex.org/W2097816699","https://openalex.org/W2101120467","https://openalex.org/W2103412200","https://openalex.org/W2103828958","https://openalex.org/W2106308757","https://openalex.org/W2117457769","https://openalex.org/W2124351063","https://openalex.org/W2125418992","https://openalex.org/W2128711701","https://openalex.org/W2132548846","https://openalex.org/W2136879569","https://openalex.org/W2150914285","https://openalex.org/W2151671981","https://openalex.org/W2157107905","https://openalex.org/W2166755371"],"related_works":["https://openalex.org/W2506843120","https://openalex.org/W4390154386","https://openalex.org/W2306179760","https://openalex.org/W2945285105","https://openalex.org/W4206175384","https://openalex.org/W2890961259","https://openalex.org/W4256272196","https://openalex.org/W4404579815","https://openalex.org/W4411020226","https://openalex.org/W2951346714"],"abstract_inverted_index":{"MOTIVATION:":[0],"Next-generation":[1],"sequencing":[2],"produces":[3],"vast":[4],"amounts":[5],"of":[6,47],"data":[7,104],"with":[8],"errors":[9],"that":[10,71],"are":[11,87,94,105],"difficult":[12],"to":[13,43,64],"distinguish":[14],"from":[15],"true":[16],"biological":[17],"variation":[18],"when":[19],"coverage":[20],"is":[21],"low.":[22],"RESULTS:":[23],"We":[24,68],"demonstrate":[25],"large":[26],"reductions":[27],"in":[28,89],"error":[29,66],"frequencies,":[30],"especially":[31],"for":[32,56],"high-error-rate":[33],"reads,":[34,58],"by":[35,59],"three":[36],"independent":[37],"means:":[38],"(i)":[39],"filtering":[40],"reads":[41],"according":[42],"their":[44],"expected":[45],"number":[46],"errors,":[48],"(ii)":[49],"assembling":[50],"overlapping":[51],"read":[52,75],"pairs":[53],"and":[54],"(iii)":[55],"amplicon":[57],"exploiting":[60],"unique":[61],"sequence":[62],"abundances":[63],"perform":[65],"correction.":[67],"also":[69],"show":[70],"most":[72],"published":[73],"paired":[74],"assemblers":[76],"calculate":[77],"incorrect":[78],"posterior":[79],"quality":[80],"scores.":[81],"AVAILABILITY":[82],"AND":[83],"IMPLEMENTATION:":[84],"These":[85],"methods":[86],"implemented":[88],"the":[90],"USEARCH":[91],"package.":[92],"Binaries":[93],"freely":[95],"available":[96,106],"at":[97,107],"http://drive5.com/usearch.":[98],"CONTACT:":[99],"robert@drive5.com":[100],"SUPPLEMENTARY":[101],"INFORMATION:":[102],"Supplementary":[103],"Bioinformatics":[108],"online.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":60},{"year":2025,"cited_by_count":117},{"year":2024,"cited_by_count":138},{"year":2023,"cited_by_count":155},{"year":2022,"cited_by_count":122},{"year":2021,"cited_by_count":181},{"year":2020,"cited_by_count":206},{"year":2019,"cited_by_count":139},{"year":2018,"cited_by_count":114},{"year":2017,"cited_by_count":74},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
