{"id":"https://openalex.org/W2160265768","doi":"https://doi.org/10.1093/bioinformatics/btr208","title":"Error correction of high-throughput sequencing datasets with non-uniform coverage","display_name":"Error correction of high-throughput sequencing datasets with non-uniform coverage","publication_year":2011,"publication_date":"2011-06-14","ids":{"openalex":"https://openalex.org/W2160265768","doi":"https://doi.org/10.1093/bioinformatics/btr208","mag":"2160265768","pmid":"https://pubmed.ncbi.nlm.nih.gov/21685062"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btr208","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr208","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/i137/48874088/bioinformatics_27_13_i137.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/27/13/i137/48874088/bioinformatics_27_13_i137.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861947","display_name":"Eric Scott","orcid":"https://orcid.org/0000-0001-7301-0152"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Scott","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018000323","display_name":"Boyko Kakaradov","orcid":"https://orcid.org/0000-0002-6109-7390"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyko Kakaradov","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027480961","display_name":"Pavel A. Pevzner","orcid":"https://orcid.org/0000-0002-0418-165X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavel Pevzner","raw_affiliation_strings":["1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science and Engineering and 2Bioinformatics Program, University of California, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":4.839,"has_fulltext":true,"cited_by_count":125,"citation_normalized_percentile":{"value":0.95379914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"27","issue":"13","first_page":"i137","last_page":"i141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9926000237464905,"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"}},"topics":[{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9926000237464905,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.9921000003814697,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9606999754905701,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7441518902778625},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.6684904098510742},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5698535442352295},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5144262909889221},{"id":"https://openalex.org/keywords/hamming-graph","display_name":"Hamming graph","score":0.4882092773914337},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45429885387420654},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.4394637942314148},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.42997297644615173},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38599109649658203},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.10310199856758118},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08703368902206421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7441518902778625},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.6684904098510742},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5698535442352295},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5144262909889221},{"id":"https://openalex.org/C29696283","wikidata":"https://www.wikidata.org/wiki/Q369440","display_name":"Hamming graph","level":5,"score":0.4882092773914337},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45429885387420654},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.4394637942314148},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.42997297644615173},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38599109649658203},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.10310199856758118},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08703368902206421},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059010","descriptor_name":"Single-Cell Analysis","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},{"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/btr208","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr208","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/i137/48874088/bioinformatics_27_13_i137.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:21685062","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21685062","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:27/13/i137","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/27/13/i137","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:pubmedcentral.nih.gov:3117386","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3117386","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btr208","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btr208","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/27/13/i137/48874088/bioinformatics_27_13_i137.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/G2345535094","display_name":null,"funder_award_id":"P41 RR024851","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G7911358210","display_name":null,"funder_award_id":"3P41RR024851-02S1","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160265768.pdf","grobid_xml":"https://content.openalex.org/works/W2160265768.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1791999417","https://openalex.org/W1921457844","https://openalex.org/W1998663222","https://openalex.org/W2023621259","https://openalex.org/W2031189156","https://openalex.org/W2046594687","https://openalex.org/W2059529172","https://openalex.org/W2117945751","https://openalex.org/W2119745866","https://openalex.org/W2122812051","https://openalex.org/W2124985265","https://openalex.org/W2128114769","https://openalex.org/W2128591967","https://openalex.org/W2131776122","https://openalex.org/W2132978620","https://openalex.org/W2133537846","https://openalex.org/W2133956160","https://openalex.org/W2136651963","https://openalex.org/W2142702487","https://openalex.org/W2145336165","https://openalex.org/W2149770991","https://openalex.org/W2151017710","https://openalex.org/W2152246890","https://openalex.org/W2160770624","https://openalex.org/W2160969485","https://openalex.org/W3145128584","https://openalex.org/W6679676508"],"related_works":["https://openalex.org/W2105471374","https://openalex.org/W2740543340","https://openalex.org/W2008960744","https://openalex.org/W2067417168","https://openalex.org/W2057936276","https://openalex.org/W4283763810","https://openalex.org/W1519122282","https://openalex.org/W2098310607","https://openalex.org/W153182557","https://openalex.org/W1582340598"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"continuing":[2],"improvements":[3],"to":[4,11,46],"high-throughput":[5],"sequencing":[6,24,98],"(HTS)":[7],"platforms":[8],"have":[9],"begun":[10],"unfold":[12],"a":[13,19,86,89,93,102],"myriad":[14],"of":[15,23,37,50,88],"new":[16],"applications.":[17],"As":[18],"result,":[20],"error":[21,76],"correction":[22,77],"reads":[25,42,52],"remains":[26,64],"an":[27,34],"important":[28],"problem.":[29],"Though":[30],"several":[31],"tools":[32,111],"do":[33],"excellent":[35],"job":[36],"correcting":[38,51],"datasets":[39],"where":[40],"the":[41,48,72],"are":[43],"sampled":[44],"close":[45],"uniformly,":[47],"problem":[49],"coming":[53],"from":[54,61],"drastically":[55],"non-uniform":[56,113],"datasets,":[57],"such":[58],"as":[59],"those":[60],"single-cell":[62,114],"sequencing,":[63],"open.":[65],"RESULTS:":[66],"In":[67],"this":[68],"article,":[69],"we":[70],"develop":[71],"method":[73],"Hammer":[74,82],"for":[75,97],"without":[78],"any":[79],"uniformity":[80],"assumptions.":[81],"is":[83,101],"based":[84],"on":[85,109,112,120],"combination":[87],"Hamming":[90],"graph":[91],"and":[92,104],"simple":[94,103],"probabilistic":[95],"model":[96],"errors.":[99],"It":[100],"adaptable":[105],"algorithm":[106],"that":[107],"improves":[108],"other":[110],"data,":[115],"while":[116],"achieving":[117],"comparable":[118],"results":[119],"normal":[121],"multi-cell":[122],"data.":[123],"AVAILABILITY:":[124],"http://www.cs.toronto.edu/~pashadag.":[125],"CONTACT:":[126],"pmedvedev@cs.ucsd.edu.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":11}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
