{"id":"https://openalex.org/W2101181063","doi":"https://doi.org/10.1093/bioinformatics/bti1020","title":"Robust classification modeling on microarray data using misclassification penalized posterior","display_name":"Robust classification modeling on microarray data using misclassification penalized posterior","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W2101181063","doi":"https://doi.org/10.1093/bioinformatics/bti1020","mag":"2101181063","pmid":"https://pubmed.ncbi.nlm.nih.gov/15961487"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti1020","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1020","pdf_url":null,"source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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","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/A5036673955","display_name":"Mat Soukup","orcid":null},"institutions":[{"id":"https://openalex.org/I1320320070","display_name":"United States Food and Drug Administration","ror":"https://ror.org/034xvzb47","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1320320070"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Soukup","raw_affiliation_strings":["Division of Biometrics III, Food and Drug Administration 9201 Corporate Blvd, Rm. N-250, Rockville, MD 20850, USA","Division of Biometrics III, Food and Drug Administration  9201 Corporate Blvd, Rm. N-250, Rockville, MD 20850, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biometrics III, Food and Drug Administration 9201 Corporate Blvd, Rm. N-250, Rockville, MD 20850, USA","institution_ids":["https://openalex.org/I1320320070"]},{"raw_affiliation_string":"Division of Biometrics III, Food and Drug Administration  9201 Corporate Blvd, Rm. N-250, Rockville, MD 20850, USA","institution_ids":["https://openalex.org/I1320320070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030498031","display_name":"HyungJun Cho","orcid":"https://orcid.org/0000-0003-0844-9948"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Cho","raw_affiliation_strings":["Division of Biostatistics and Epidemiology, University of Virginia PO Box 800717, Charlottesville, VA 22908, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biostatistics and Epidemiology, University of Virginia PO Box 800717, Charlottesville, VA 22908, USA#TAB#","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070753145","display_name":"Jae Kang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. K. Lee","raw_affiliation_strings":["Division of Biostatistics and Epidemiology, University of Virginia PO Box 800717, Charlottesville, VA 22908, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Biostatistics and Epidemiology, University of Virginia PO Box 800717, Charlottesville, VA 22908, USA#TAB#","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036673955"],"corresponding_institution_ids":["https://openalex.org/I1320320070"],"apc_list":null,"apc_paid":null,"fwci":1.1377,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.76359216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"21","issue":"Suppl 1","first_page":"i423","last_page":"i430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9387000203132629,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9387000203132629,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.009700000286102295,"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/T10862","display_name":"AI in cancer detection","score":0.008100000210106373,"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/bioconductor","display_name":"Bioconductor","score":0.8967575430870056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.639319658279419},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5847017168998718},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.522894561290741},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4876824617385864},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44402652978897095},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4430692195892334},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.437570720911026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4289427101612091},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42859792709350586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39763641357421875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.345216304063797}],"concepts":[{"id":"https://openalex.org/C2779694297","wikidata":"https://www.wikidata.org/wiki/Q2888953","display_name":"Bioconductor","level":3,"score":0.8967575430870056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.639319658279419},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5847017168998718},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.522894561290741},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4876824617385864},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44402652978897095},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4430692195892334},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.437570720911026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4289427101612091},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42859792709350586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39763641357421875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.345216304063797},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"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":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D052138","descriptor_name":"Genes, Neoplasm","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D052138","descriptor_name":"Genes, Neoplasm","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D052138","descriptor_name":"Genes, Neoplasm","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/bti1020","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti1020","pdf_url":null,"source":{"id":"https://openalex.org/S4210188263","display_name":"Computer applications in the biosciences","issn_l":"0266-7061","issn":["0266-7061","1460-2059"],"is_oa":false,"is_in_doaj":false,"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:15961487","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15961487","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/F4320306095","display_name":"American Cancer Society","ror":"https://ror.org/02e463172"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W99903558","https://openalex.org/W1601740268","https://openalex.org/W1604938182","https://openalex.org/W1607899705","https://openalex.org/W1966701961","https://openalex.org/W2048631447","https://openalex.org/W2087684630","https://openalex.org/W2107956883","https://openalex.org/W2108728387","https://openalex.org/W2109363337","https://openalex.org/W2112440119","https://openalex.org/W2122599407","https://openalex.org/W2127544153","https://openalex.org/W2131666115","https://openalex.org/W2133199783","https://openalex.org/W2155653793","https://openalex.org/W2168561598","https://openalex.org/W2797114046"],"related_works":["https://openalex.org/W2135678793","https://openalex.org/W2011682793","https://openalex.org/W2109288169","https://openalex.org/W2157684052","https://openalex.org/W2978247079","https://openalex.org/W2140163842","https://openalex.org/W2148708580","https://openalex.org/W3037604406","https://openalex.org/W2166887457","https://openalex.org/W4381571012"],"abstract_inverted_index":{"MOTIVATION:":[0],"Genome-wide":[1],"microarray":[2,207],"data":[3,34],"are":[4,175],"often":[5,221],"used":[6],"in":[7,217,227],"challenging":[8],"classification":[9,55,69,91,99,133,170,186],"problems":[10],"of":[11,15,21,50,63,81,120,130,139,161],"clinically":[12],"relevant":[13],"subtypes":[14],"human":[16],"diseases.":[17],"However,":[18],"the":[19,41,54,118,124,128,131,137,193,218,239],"identification":[20],"a":[22,75,113,121,147,164,179],"parsimonious":[23,195],"robust":[24,169,196],"prediction":[25,64,122,156,197],"model":[26,43,56,65,171,229],"that":[27,220],"performs":[28],"consistently":[29],"well":[30],"on":[31,104,163,178,205],"future":[32],"independent":[33,181],"has":[35],"not":[36,73],"been":[37,94,108],"successful":[38],"due":[39],"to":[40,96,152,191,214],"biased":[42],"selection":[44],"from":[45],"an":[46],"extremely":[47],"large":[48],"number":[49,138],"candidate":[51],"models":[52,157,198,210,216],"during":[53],"search":[57],"and":[58,172],"construction.":[59,230],"Furthermore,":[60],"common":[61],"criteria":[62],"performance,":[66],"such":[67,82,98],"as":[68],"error":[70],"rates,":[71],"do":[72],"provide":[74],"sensitive":[76],"measure":[77,115],"for":[78,116],"evaluating":[79],"performance":[80,119,213],"astronomic":[83],"competing":[84],"models.":[85],"Also,":[86],"even":[87],"though":[88],"several":[89],"different":[90,159],"approaches":[92],"have":[93,107,222],"utilized":[95],"tackle":[97],"problems,":[100],"no":[101],"direct":[102],"comparison":[103],"these":[105],"methods":[106],"made.":[109],"RESULTS:":[110],"We":[111],"introduce":[112],"novel":[114],"assessing":[117],"model,":[123],"misclassification-penalized":[125],"posterior":[126,132],"(MiPP),":[127],"sum":[129],"probabilities":[134],"penalized":[135],"by":[136],"incorrectly":[140],"classified":[141],"samples.":[142],"Using":[143],"MiPP,":[144],"we":[145],"implement":[146],"forward":[148],"step-wise":[149],"cross-validated":[150],"procedure":[151],"find":[153],"our":[154],"optimal":[155],"with":[158,200],"numbers":[160],"features":[162,204,226],"training":[165],"set.":[166],"Our":[167,232],"final":[168],"its":[173],"dimension":[174],"determined":[176],"based":[177],"completely":[180],"test":[182],"dataset.":[183],"This":[184],"MiPP-based":[185],"modeling":[187],"approach":[188],"enables":[189],"us":[190],"identify":[192],"most":[194],"only":[199],"two":[201],"or":[202],"three":[203],"well-known":[206],"datasets.":[208],"These":[209],"show":[211],"superior":[212],"other":[215],"literature":[219],"more":[223],"than":[224],"40-100":[225],"their":[228],"AVAILABILITY:":[231],"MiPP":[233],"software":[234],"program":[235],"is":[236],"available":[237],"at":[238],"Bioconductor":[240],"website":[241],"(http://www.bioconductor.org).":[242]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}