{"id":"https://openalex.org/W3080775042","doi":"https://doi.org/10.1093/bioinformatics/btaa738","title":"CARE: context-aware sequencing read error correction","display_name":"CARE: context-aware sequencing read error correction","publication_year":2020,"publication_date":"2020-08-14","ids":{"openalex":"https://openalex.org/W3080775042","doi":"https://doi.org/10.1093/bioinformatics/btaa738","mag":"3080775042","pmid":"https://pubmed.ncbi.nlm.nih.gov/32818262"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa738","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa738","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/A5075168236","display_name":"Felix Kallenborn","orcid":"https://orcid.org/0000-0003-4516-6357"},"institutions":[{"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":["DE"],"is_corresponding":true,"raw_author_name":"Felix Kallenborn","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4516-6357","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015934308","display_name":"Andreas Hildebrandt","orcid":"https://orcid.org/0000-0003-2180-6516"},"institutions":[{"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":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Hildebrandt","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany","institution_ids":["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/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johannes Gutenberg University , Mainz 55122, Germany","institution_ids":["https://openalex.org/I197323543"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020388832","https://openalex.org/A5075168236"],"corresponding_institution_ids":["https://openalex.org/I197323543"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.6574,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.67255285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"37","issue":"7","first_page":"889","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9739000201225281,"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":0.9739000201225281,"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":0.006300000008195639,"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":0.006000000052154064,"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":0.7926197648048401},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.572632908821106},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5639378428459167},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5454145669937134},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5102646350860596},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5090674757957458},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5020174980163574},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4950961172580719},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4815245270729065},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4501946270465851},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.4171803593635559},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4123598337173462},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38338539004325867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2957373857498169},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.25305092334747314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1518729329109192},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10099637508392334},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09283798933029175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926197648048401},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.572632908821106},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5639378428459167},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5454145669937134},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5102646350860596},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5090674757957458},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5020174980163574},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4950961172580719},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4815245270729065},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4501946270465851},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.4171803593635559},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4123598337173462},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38338539004325867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2957373857498169},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.25305092334747314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1518729329109192},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10099637508392334},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09283798933029175},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btaa738","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa738","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:32818262","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32818262","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1493629236","https://openalex.org/W1579534339","https://openalex.org/W1879624628","https://openalex.org/W1980667059","https://openalex.org/W1990061958","https://openalex.org/W2001079689","https://openalex.org/W2014099509","https://openalex.org/W2096128575","https://openalex.org/W2107772251","https://openalex.org/W2113154626","https://openalex.org/W2115501618","https://openalex.org/W2120902911","https://openalex.org/W2121716038","https://openalex.org/W2129276621","https://openalex.org/W2148885851","https://openalex.org/W2157539385","https://openalex.org/W2160665949","https://openalex.org/W2167469524","https://openalex.org/W2168602018","https://openalex.org/W2266786540","https://openalex.org/W2317095975","https://openalex.org/W2333007030","https://openalex.org/W2587940257","https://openalex.org/W2745994342","https://openalex.org/W2948188025","https://openalex.org/W2950150251","https://openalex.org/W2952803933","https://openalex.org/W2953339515","https://openalex.org/W2980597348","https://openalex.org/W2983055179","https://openalex.org/W2986786507","https://openalex.org/W3010020071","https://openalex.org/W4240302460","https://openalex.org/W6634542447"],"related_works":["https://openalex.org/W4210830088","https://openalex.org/W2767590279","https://openalex.org/W3011183076","https://openalex.org/W2794893153","https://openalex.org/W2721624558","https://openalex.org/W2079322808","https://openalex.org/W2216477337","https://openalex.org/W2772185703","https://openalex.org/W2584868213","https://openalex.org/W2619753084"],"abstract_inverted_index":{"MOTIVATION:":[0],"Error":[1],"correction":[2,24,60],"is":[3,148,158,182,196],"a":[4,122,142,162,173],"fundamental":[5],"pre-processing":[6],"step":[7],"in":[8,14,168,186,191],"many":[9],"Next-Generation":[10],"Sequencing":[11,89],"(NGS)":[12],"pipelines,":[13],"particular":[15],"for":[16,62,72,141],"de":[17,137],"novo":[18,138],"genome":[19,164],"assembly.":[20],"However,":[21],"existing":[22],"error":[23,59,155],"methods":[25],"either":[26],"suffer":[27],"from":[28],"high":[29],"false-positive":[30,109],"rates":[31],"since":[32],"they":[33],"break":[34],"reads":[35,49],"into":[36],"independent":[37],"k-mers":[38],"or":[39],"do":[40],"not":[41],"scale":[42],"efficiently":[43],"to":[44,131,160],"large":[45,77],"amounts":[46],"of":[47,68,85,96,125,144],"sequencing":[48,78],"and":[50,190,200],"complex":[51],"genomes.":[52],"RESULTS:":[53],"We":[54],"present":[55],"CARE-an":[56],"alignment-based":[57,154],"scalable":[58],"algorithm":[61],"Illumina":[63,165],"data":[64,209],"using":[65,176],"the":[66,97,150],"concept":[67],"minhashing.":[69],"Minhashing":[70],"allows":[71],"efficient":[73],"similarity":[74],"search":[75],"within":[76],"read":[79],"collections":[80],"which":[81],"enables":[82],"fast":[83],"computation":[84],"high-quality":[86],"multiple":[87,152],"alignments.":[88,99],"errors":[90],"are":[91,210],"corrected":[92],"by":[93],"detailed":[94],"inspection":[95],"corresponding":[98],"Our":[100],"performance":[101],"evaluation":[102],"shows":[103],"that":[104,157],"CARE":[105,147,181],"generates":[106],"significantly":[107],"fewer":[108],"corrections":[110],"than":[111],"state-of-the-art":[112],"tools":[113],"(Musket,":[114],"SGA,":[115],"BFC,":[116],"Lighter,":[117],"Bcool,":[118],"Karect)":[119],"while":[120],"maintaining":[121],"competitive":[123],"number":[124,143],"true":[126],"positives.":[127],"When":[128],"used":[129],"prior":[130],"assembly":[132,139],"it":[133],"can":[134,201],"achieve":[135],"superior":[136],"results":[140],"real":[145],"datasets.":[146],"also":[149],"first":[151],"sequence":[153],"corrector":[156],"able":[159],"process":[161],"human":[163],"NGS":[166],"dataset":[167],"only":[169],"4":[170],"h":[171],"on":[172],"single":[174],"workstation":[175],"GPU":[177],"acceleration.":[178],"AVAILABILITYAND":[179],"IMPLEMENTATION:":[180],"open-source":[183],"software":[184],"written":[185],"C++":[187],"(CPU":[188],"version)":[189],"CUDA/C++":[192],"(GPU":[193],"version).":[194],"It":[195],"licensed":[197],"under":[198],"GPLv3":[199],"be":[202],"downloaded":[203],"at":[204,212],"https://github.com/fkallen/CARE.":[205],"SUPPLEMENTARY":[206],"INFORMATION:":[207],"Supplementary":[208],"available":[211],"Bioinformatics":[213],"online.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}
