{"id":"https://openalex.org/W2154302115","doi":"https://doi.org/10.1109/bibmw.2010.5703862","title":"In search of true reads: A classification approach to next generation sequencing data selection","display_name":"In search of true reads: A classification approach to next generation sequencing data selection","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2154302115","doi":"https://doi.org/10.1109/bibmw.2010.5703862","mag":"2154302115"},"language":"en","primary_location":{"id":"doi:10.1109/bibmw.2010.5703862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2010.5703862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)","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/A5009819704","display_name":"Edward Wijaya","orcid":"https://orcid.org/0000-0002-1234-0761"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Edward Wijaya","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan","Department of Computational Biology, Graduate School of Frontier Science, University of Tokyo, Kashiwa, Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Computational Biology, Graduate School of Frontier Science, University of Tokyo, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061485115","display_name":"Jean-Fran\u00e7ois Pessiot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Francois Pessiot","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055829507","display_name":"Martin C. Frith","orcid":"https://orcid.org/0000-0003-0998-2859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin C. Frith","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027636639","display_name":"Wataru Fujibuchi","orcid":"https://orcid.org/0000-0003-2243-9981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wataru Fujibuchi","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082068847","display_name":"Kiyoshi Asai","orcid":"https://orcid.org/0000-0003-0909-4982"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoshi Asai","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan","Department of Computational Biology, Graduate School of Frontier Science, University of Tokyo, Kashiwa, Chiba, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Department of Computational Biology, Graduate School of Frontier Science, University of Tokyo, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I74801974","https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088005667","display_name":"Paul Horton","orcid":"https://orcid.org/0000-0002-0916-7339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Horton","raw_affiliation_strings":["Computational Biology Research Center, AIST, Koto, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Computational Biology Research Center, AIST, Koto, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009819704"],"corresponding_institution_ids":["https://openalex.org/I161296585","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13604317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9994000196456909,"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7421181201934814},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6243082880973816},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5543038845062256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5518490076065063},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5361829400062561},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5016114711761475},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44893017411231995},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4455651044845581},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4395349621772766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40804409980773926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34679490327835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7421181201934814},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6243082880973816},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5543038845062256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5518490076065063},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5361829400062561},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5016114711761475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44893017411231995},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4455651044845581},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4395349621772766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40804409980773926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34679490327835083},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibmw.2010.5703862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2010.5703862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W740415","https://openalex.org/W82055556","https://openalex.org/W1768187423","https://openalex.org/W1991007428","https://openalex.org/W2019866636","https://openalex.org/W2049633694","https://openalex.org/W2085060961","https://openalex.org/W2101800045","https://openalex.org/W2117945751","https://openalex.org/W2119745866","https://openalex.org/W2119923823","https://openalex.org/W2131088968","https://openalex.org/W2131776122","https://openalex.org/W2143697424","https://openalex.org/W2150815784","https://openalex.org/W2152246890","https://openalex.org/W2156909104","https://openalex.org/W2161260747","https://openalex.org/W2314485382","https://openalex.org/W2505936072","https://openalex.org/W2523692606","https://openalex.org/W3129711340","https://openalex.org/W6603319556","https://openalex.org/W6637934610"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W2012353789","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W1980100242"],"abstract_inverted_index":{"Next":[0],"generation":[1,112],"sequencing":[2],"(NGS)":[3],"technology":[4],"has":[5],"increasingly":[6],"become":[7],"the":[8,19,63,115],"backbone":[9],"of":[10,53,62],"transcriptomics":[11],"analysis,":[12],"but":[13],"sequencer":[14],"error":[15,57],"causes":[16],"biases":[17],"in":[18,85],"read":[20],"counts.":[21],"In":[22],"this":[23,38,90],"paper":[24],"we":[25,72,92],"establish":[26],"a":[27,41,66,94,102],"framework":[28,91],"for":[29,96,107],"predicting":[30],"true":[31,55,87],"sequences":[32,100],"from":[33,122],"NGS":[34],"data.":[35],"We":[36,44],"formulate":[37],"task":[39],"as":[40,49],"classification":[42,83],"problem.":[43],"define":[45],"several":[46],"features,":[47],"such":[48],"log":[50],"likelihood":[51],"ratio":[52],"estimated":[54],"counts,":[56],"probability":[58],"and":[59,105,114],"observed":[60],"count":[61],"reads.":[64],"Using":[65,89],"Support":[67],"Vector":[68],"Machine":[69],"(SVM)":[70],"classifier,":[71],"show":[73],"that":[74],"on":[75],"simulated":[76,116],"reads":[77],"these":[78],"features":[79],"can":[80,119],"achieve":[81],"96.35%":[82],"accuracy":[84],"discriminating":[86],"sequences.":[88],"provide":[93],"way":[95],"users":[97],"to":[98],"select":[99],"with":[101],"desired":[103],"precision":[104],"recall":[106],"their":[108],"analysis.":[109],"The":[110],"feature":[111],"software":[113],"data":[117],"set":[118],"be":[120],"obtained":[121],"(http://seq.cbrc.jp/NGSFeatGen).":[123]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}