{"id":"https://openalex.org/W2564448515","doi":"https://doi.org/10.1109/cibcb.2016.7758117","title":"A fast and scalable high-throughput sequencing data error correction via oligomers","display_name":"A fast and scalable high-throughput sequencing data error correction via oligomers","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2564448515","doi":"https://doi.org/10.1109/cibcb.2016.7758117","mag":"2564448515"},"language":"en","primary_location":{"id":"doi:10.1109/cibcb.2016.7758117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2016.7758117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5017152835","display_name":"Franco Milicchio","orcid":"https://orcid.org/0000-0002-4875-4894"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Franco Milicchio","raw_affiliation_strings":["Dept. of Engineering, Roma Tre University, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Engineering, Roma Tre University, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011177296","display_name":"Iain Buchan","orcid":"https://orcid.org/0000-0003-3392-1650"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I2799725268","display_name":"Manchester Academic Health Science Centre","ror":"https://ror.org/04rrkhs81","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799725268"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Iain E. Buchan","raw_affiliation_strings":["Centre for Health Informatics, University of Manchester, United Kingdom","Centre for Health Informatics, University of Manchester, Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre for Health Informatics, University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I2799725268","https://openalex.org/I28407311"]},{"raw_affiliation_string":"Centre for Health Informatics, University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I2799725268","https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039419132","display_name":"Mattia Prosperi","orcid":"https://orcid.org/0000-0002-9021-5595"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]},{"id":"https://openalex.org/I2800717037","display_name":"University of Florida Health","ror":"https://ror.org/04tk2gy88","country_code":"US","type":"education","lineage":["https://openalex.org/I2800717037"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattia C.F. Prosperi","raw_affiliation_strings":["Dept. of Epidemiology, University of Florida, Gainesville, USA","Dept. of Epidemiology, University of Florida, Gainesville, Florida, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Epidemiology, University of Florida, Gainesville, USA","institution_ids":["https://openalex.org/I33213144","https://openalex.org/I2800717037"]},{"raw_affiliation_string":"Dept. of Epidemiology, University of Florida, Gainesville, Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017152835"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":0.3335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68688234,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9965999722480774,"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":0.9965999722480774,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9957000017166138,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.9836000204086304,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143723607063293},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5905230045318604},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.572350263595581},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.5639685392379761},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45329469442367554},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.44300946593284607},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34613996744155884},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2726794183254242},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25561031699180603},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.2505943775177002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14605900645256042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143723607063293},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5905230045318604},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.572350263595581},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.5639685392379761},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45329469442367554},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.44300946593284607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34613996744155884},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2726794183254242},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25561031699180603},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2505943775177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14605900645256042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cibcb.2016.7758117","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cibcb.2016.7758117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/320474","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/320474","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1513515886","https://openalex.org/W1543636183","https://openalex.org/W1873162485","https://openalex.org/W1977618577","https://openalex.org/W1980667059","https://openalex.org/W1985831638","https://openalex.org/W2014099509","https://openalex.org/W2023918737","https://openalex.org/W2042869111","https://openalex.org/W2059529172","https://openalex.org/W2074231493","https://openalex.org/W2075013491","https://openalex.org/W2084821192","https://openalex.org/W2092167436","https://openalex.org/W2101250487","https://openalex.org/W2114931329","https://openalex.org/W2119745866","https://openalex.org/W2129276621","https://openalex.org/W2131088968","https://openalex.org/W2133956160","https://openalex.org/W2134007392","https://openalex.org/W2136651963","https://openalex.org/W2142403957","https://openalex.org/W2155845142","https://openalex.org/W2159192122","https://openalex.org/W2160665949","https://openalex.org/W2162667876","https://openalex.org/W2163314170","https://openalex.org/W2163326395"],"related_works":["https://openalex.org/W2562683361","https://openalex.org/W3087469195","https://openalex.org/W2354744388","https://openalex.org/W3125399386","https://openalex.org/W2949121831","https://openalex.org/W3215786367","https://openalex.org/W1908987670","https://openalex.org/W2756186577","https://openalex.org/W2735897904","https://openalex.org/W3021341025"],"abstract_inverted_index":{"Next-generation":[0],"sequencing":[1,8],"(NGS)":[2],"technologies":[3,46],"have":[4],"superseded":[5],"traditional":[6],"Sanger":[7],"approach":[9,153],"in":[10,42,74,114,159],"many":[11],"experimental":[12],"settings,":[13],"given":[14],"their":[15],"tremendous":[16],"yield":[17],"and":[18,35,64,69,83,128,144,166],"affordable":[19],"cost.":[20],"Nowadays":[21],"it":[22],"is":[23,51],"possible":[24,146],"to":[25,36,55],"sequence":[26],"any":[27],"microbial":[28],"organism":[29],"or":[30],"meta-genomic":[31],"sample":[32],"within":[33],"hours,":[34],"obtain":[37],"a":[38,52],"whole":[39],"human":[40],"genome":[41,112],"weeks.":[43],"Nonetheless,":[44],"NGS":[45,75],"are":[47],"error-prone.":[48],"Correcting":[49],"errors":[50],"challenge":[53],"due":[54],"multiple":[56],"factors,":[57],"including":[58],"the":[59,62,70,79,94,115,138,149],"data":[60,81,104],"sizes,":[61],"machine-specific":[63],"non-at-random":[65],"characteristics":[66],"of":[67,125,161],"errors,":[68],"error":[71,89,135],"distributions.":[72],"Errors":[73],"experiments":[76],"can":[77],"hamper":[78],"subsequent":[80],"analysis":[82],"inference.":[84],"This":[85],"work":[86],"proposes":[87],"an":[88,130,141],"correction":[90],"method":[91],"based":[92],"on":[93,102],"de":[95],"Bruijn":[96],"graph":[97],"that":[98],"permits":[99],"its":[100,145],"execution":[101],"Gigabyte-sized":[103],"sets":[105],"using":[106],"normal":[107],"desktop/laptop":[108],"computers,":[109],"ideal":[110],"for":[111,133],"sizes":[113],"Megabase":[116],"range,":[117],"e.g.":[118],"bacteria.":[119],"The":[120],"implementation":[121],"makes":[122],"extensive":[123],"use":[124],"hashing":[126],"techniques,":[127],"implements":[129],"A*":[131],"algorithm":[132],"optimal":[134],"correction,":[136],"minimizing":[137],"distance":[139],"between":[140],"erroneous":[142],"read":[143],"replacement":[147],"with":[148],"Needleman-Wunsch":[150],"score.":[151],"Our":[152],"outperforms":[154],"other":[155],"popular":[156],"methods":[157],"both":[158],"terms":[160],"random":[162],"access":[163],"memory":[164],"usage":[165],"computing":[167],"times.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}