{"id":"https://openalex.org/W2517033688","doi":"https://doi.org/10.1109/tcbb.2016.2598752","title":"Machine Learned Replacement of N-Labels for Basecalled Sequences in DNA Barcoding","display_name":"Machine Learned Replacement of N-Labels for Basecalled Sequences in DNA Barcoding","publication_year":2016,"publication_date":"2016-08-11","ids":{"openalex":"https://openalex.org/W2517033688","doi":"https://doi.org/10.1109/tcbb.2016.2598752","mag":"2517033688","pmid":"https://pubmed.ncbi.nlm.nih.gov/28092571"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2016.2598752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2016.2598752","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","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/A5074231652","display_name":"Y. T. Eddie","orcid":"https://orcid.org/0000-0003-2434-5356"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eddie Y. T. Ma","raw_affiliation_strings":["School of Computer Science, University of Guelph, Guelph, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-2434-5356","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Guelph, Guelph, ON, Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046508393","display_name":"Sujeevan Ratnasingham","orcid":"https://orcid.org/0000-0002-3694-0171"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sujeevan Ratnasingham","raw_affiliation_strings":["Biodiversity Institute of Ontario, University of Guelph, Guelph, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biodiversity Institute of Ontario, University of Guelph, Guelph, ON, Canada","institution_ids":["https://openalex.org/I79817857"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053492737","display_name":"Stefan C. Kremer","orcid":"https://orcid.org/0000-0002-3667-4379"},"institutions":[{"id":"https://openalex.org/I79817857","display_name":"University of Guelph","ror":"https://ror.org/01r7awg59","country_code":"CA","type":"education","lineage":["https://openalex.org/I79817857"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stefan C. Kremer","raw_affiliation_strings":["School of Computer Science, University of Guelph, Guelph, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Guelph, Guelph, ON, Canada","institution_ids":["https://openalex.org/I79817857"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79817857"],"apc_list":null,"apc_paid":null,"fwci":0.3206,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66825662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"15","issue":"1","first_page":"191","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9945999979972839,"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/T11970","display_name":"Molecular Biology Techniques and Applications","score":0.9879999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/barcode","display_name":"Barcode","score":0.9411451816558838},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7440556287765503},{"id":"https://openalex.org/keywords/dna-barcoding","display_name":"DNA barcoding","score":0.6331969499588013},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5645796060562134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5533329844474792},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5294805765151978},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.4475897550582886},{"id":"https://openalex.org/keywords/sanger-sequencing","display_name":"Sanger sequencing","score":0.4444693922996521},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.420898973941803},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4161653220653534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41293469071388245},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3874746263027191},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.33542272448539734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3223205804824829},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.2951595187187195},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2938004732131958},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28547465801239014},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13433223962783813},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.0898447334766388},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08671790361404419}],"concepts":[{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.9411451816558838},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7440556287765503},{"id":"https://openalex.org/C141732470","wikidata":"https://www.wikidata.org/wiki/Q1154642","display_name":"DNA barcoding","level":2,"score":0.6331969499588013},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5645796060562134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533329844474792},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5294805765151978},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.4475897550582886},{"id":"https://openalex.org/C76818968","wikidata":"https://www.wikidata.org/wiki/Q181940","display_name":"Sanger sequencing","level":4,"score":0.4444693922996521},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.420898973941803},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4161653220653534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41293469071388245},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3874746263027191},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.33542272448539734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3223205804824829},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.2951595187187195},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2938004732131958},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28547465801239014},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13433223962783813},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0898447334766388},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08671790361404419},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058893","descriptor_name":"DNA Barcoding, Taxonomic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058893","descriptor_name":"DNA Barcoding, Taxonomic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058893","descriptor_name":"DNA Barcoding, Taxonomic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2016.2598752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2016.2598752","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:28092571","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28092571","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310787","display_name":"Genome Canada","ror":"https://ror.org/029s29983"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320319905","display_name":"Ontario Genomics Institute","ror":"https://ror.org/00c68jz96"},{"id":"https://openalex.org/F4320319952","display_name":"Canada Foundation for Innovation","ror":"https://ror.org/000az4664"},{"id":"https://openalex.org/F4320321886","display_name":"Ontario Ministry of Research, Innovation and Science","ror":"https://ror.org/03zr1tg88"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W87025988","https://openalex.org/W190861770","https://openalex.org/W196761320","https://openalex.org/W1498436455","https://openalex.org/W1530968569","https://openalex.org/W1564549801","https://openalex.org/W1584535387","https://openalex.org/W1900973458","https://openalex.org/W1930624869","https://openalex.org/W1986700282","https://openalex.org/W1995341919","https://openalex.org/W1996151897","https://openalex.org/W1996816368","https://openalex.org/W2002828244","https://openalex.org/W2007277320","https://openalex.org/W2008389467","https://openalex.org/W2013769445","https://openalex.org/W2020246210","https://openalex.org/W2023207868","https://openalex.org/W2050624542","https://openalex.org/W2058839892","https://openalex.org/W2074231493","https://openalex.org/W2077613581","https://openalex.org/W2099901798","https://openalex.org/W2100495367","https://openalex.org/W2100805904","https://openalex.org/W2101234009","https://openalex.org/W2111578675","https://openalex.org/W2119821739","https://openalex.org/W2119923823","https://openalex.org/W2121016876","https://openalex.org/W2129365081","https://openalex.org/W2135670838","https://openalex.org/W2137983211","https://openalex.org/W2138270253","https://openalex.org/W2138942899","https://openalex.org/W2139212933","https://openalex.org/W2143908786","https://openalex.org/W2150401960","https://openalex.org/W2152157019","https://openalex.org/W2153635508","https://openalex.org/W2155806188","https://openalex.org/W2160702878","https://openalex.org/W2164370980","https://openalex.org/W2171068274","https://openalex.org/W2900868617","https://openalex.org/W3121926921","https://openalex.org/W3121953277","https://openalex.org/W3146803896","https://openalex.org/W3152202442","https://openalex.org/W4236355931","https://openalex.org/W4238404964","https://openalex.org/W4239510810","https://openalex.org/W6608133726","https://openalex.org/W6675354045","https://openalex.org/W6680660727","https://openalex.org/W7015884252"],"related_works":["https://openalex.org/W4291786356","https://openalex.org/W2402613932","https://openalex.org/W2111456242","https://openalex.org/W2360712899","https://openalex.org/W2097619744","https://openalex.org/W2394007119","https://openalex.org/W1972123826","https://openalex.org/W2032317445","https://openalex.org/W2389721777","https://openalex.org/W2911724990"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,20,26,54],"machine":[4],"learning":[5],"method":[6],"that":[7],"increases":[8,133],"the":[9,32,50,62,68,75,78,84,91,102,114,124],"number":[10,125],"of":[11,29,49,77,89,111,117,126,151,163,176],"identified":[12],"bases":[13,128],"in":[14,31,90],"Sanger":[15],"Sequencing.":[16],"The":[17],"system":[18,99,146,154],"post-processes":[19],"KB":[21,80],"basecalled":[22],"chromatogram.":[23],"It":[24],"selects":[25,171],"recoverable":[27],"subset":[28],"N-labels":[30,106,177],"KB-called":[33],"chromatogram":[34],"to":[35,61],"replace":[36],"with":[37,86,142],"basecalls":[38],"(A,C,G,T).":[39],"An":[40],"N-label":[41],"correction":[42],"is":[43],"defined":[44],"given":[45],"an":[46,65,148],"additional":[47,69,92],"read":[48,70],"same":[51],"sequence,":[52],"and":[53,71,137,172,186,190],"human":[55,72],"finished":[56],"sequence.":[57],"Corrections":[58,94],"are":[59,95,107],"added":[60],"dataset":[63],"when":[64,158],"alignment":[66],"determines":[67],"agree":[73],"on":[74,166],"identity":[76],"N-label.":[79],"must":[81],"also":[82],"rate":[83,150,162],"replacement":[85],"quality":[87],"value":[88],"read.":[93],"only":[96,155],"available":[97],"during":[98],"training.":[100],"Developing":[101],"system,":[103],"nearly":[104],"850,000":[105],"obtained":[108],"from":[109,178,184,193],"Barcode":[110],"Life":[112],"Datasystems,":[113],"premier":[115],"database":[116],"genetic":[118],"markers":[119],"called":[120],"DNA":[121],"Barcodes.":[122],"Increasing":[123],"correct":[127],"improves":[129],"reference":[130],"sequence":[131,134],"reliability,":[132],"identification":[135],"accuracy,":[136],"assures":[138],"analysis":[139],"correctness.":[140],"Keeping":[141],"barcoding":[143],"standards,":[144],"our":[145,169],"maintains":[147],"error":[149],"percent.":[152],"Our":[153],"applies":[156],"corrections":[157],"it":[159],"estimates":[160],"low":[161],"error.":[164],"Tested":[165],"this":[167],"data,":[168],"automation":[170],"recovers:":[173],"79":[174],"percent":[175,183,192],"COI":[179],"(animal":[180],"barcode);":[181],"80":[182],"matK":[185],"rbcL":[187],"(plant":[188],"barcodes);":[189],"58":[191],"non-protein-coding":[194],"sequences":[195],"(across":[196],"eukaryotes).":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
