{"id":"https://openalex.org/W4406047371","doi":"https://doi.org/10.1109/tcbbio.2024.3494599","title":"Multivariate Optimization of k for k-Nearest-Neighbor Feature Selection With Dichotomous Outcomes: Complex Associations, Class Imbalance, and Application to RNA-Seq in Major Depressive Disorder","display_name":"Multivariate Optimization of k for k-Nearest-Neighbor Feature Selection With Dichotomous Outcomes: Complex Associations, Class Imbalance, and Application to RNA-Seq in Major Depressive Disorder","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406047371","doi":"https://doi.org/10.1109/tcbbio.2024.3494599","pmid":"https://pubmed.ncbi.nlm.nih.gov/40811240"},"language":"en","primary_location":{"id":"doi:10.1109/tcbbio.2024.3494599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2024.3494599","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12356037/pdf/nihms-2054939.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078611594","display_name":"Bryan A. Dawkins","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086149","display_name":"Standard Bio (Norway)","ror":"https://ror.org/00njcfy31","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210086149"]},{"id":"https://openalex.org/I4210107489","display_name":"American Standard (United States)","ror":"https://ror.org/013b0rk29","country_code":"US","type":"company","lineage":["https://openalex.org/I4210107489"]}],"countries":["NO","US"],"is_corresponding":true,"raw_author_name":"Bryan A. Dawkins","raw_affiliation_strings":["Bioinformatics Department, Standard BioTools, South San Francisco, CA, USA","Bioinformatics Department, Standard BioTools, 2 Tower Place, Suite 2000, South San Francisco, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0087-312X","affiliations":[{"raw_affiliation_string":"Bioinformatics Department, Standard BioTools, South San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210086149"]},{"raw_affiliation_string":"Bioinformatics Department, Standard BioTools, 2 Tower Place, Suite 2000, South San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210107489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049579672","display_name":"Brett A. McKinney","orcid":"https://orcid.org/0000-0002-9494-8833"},"institutions":[{"id":"https://openalex.org/I87208437","display_name":"University of Tulsa","ror":"https://ror.org/04wn28048","country_code":"US","type":"education","lineage":["https://openalex.org/I87208437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brett A. McKinney","raw_affiliation_strings":["Department of Mathematics and the Tandy School of Computer Science, University of Tulsa, Tulsa, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and the Tandy School of Computer Science, University of Tulsa, Tulsa, OK, USA","institution_ids":["https://openalex.org/I87208437"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078611594"],"corresponding_institution_ids":["https://openalex.org/I4210086149","https://openalex.org/I4210107489"],"apc_list":null,"apc_paid":null,"fwci":4.6546,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92514729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"22","issue":"1","first_page":"39","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9825000166893005,"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/feature-selection","display_name":"Feature selection","score":0.7431071996688843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6136284470558167},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.6070383787155151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6010576486587524},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5476239919662476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5207316875457764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5182085633277893},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4239428639411926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3773213028907776},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3181207478046417}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7431071996688843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136284470558167},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.6070383787155151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6010576486587524},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5476239919662476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5207316875457764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5182085633277893},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4239428639411926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3773213028907776},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3181207478046417},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tcbbio.2024.3494599","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbbio.2024.3494599","pdf_url":null,"source":{"id":"https://openalex.org/S5407042751","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"2998-4165","issn":["2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40811240","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40811240","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 transactions on computational biology and bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12356037","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12356037/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12356037/pdf/nihms-2054939.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Comput Biol Bioinform","raw_type":"Text"},{"id":"pmh:oai:europepmc.org:11563448","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12356037","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12356037","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12356037/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12356037/pdf/nihms-2054939.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Comput Biol Bioinform","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.5,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406047371.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1808644423","https://openalex.org/W1969198439","https://openalex.org/W2012034410","https://openalex.org/W2062801722","https://openalex.org/W2109553965","https://openalex.org/W2119590375","https://openalex.org/W2137499573","https://openalex.org/W2148143831","https://openalex.org/W2334471942","https://openalex.org/W2509717357","https://openalex.org/W2522267037","https://openalex.org/W2584710572","https://openalex.org/W2610276113","https://openalex.org/W2795896985","https://openalex.org/W2919821184","https://openalex.org/W2953267417","https://openalex.org/W2999299543","https://openalex.org/W3004127313","https://openalex.org/W3021835408","https://openalex.org/W3049050614","https://openalex.org/W3128859846","https://openalex.org/W4220726338","https://openalex.org/W4401502046","https://openalex.org/W6607693206","https://openalex.org/W6871354055"],"related_works":["https://openalex.org/W4388745254","https://openalex.org/W2980082554","https://openalex.org/W1517228774","https://openalex.org/W2767419625","https://openalex.org/W2389704471","https://openalex.org/W4386564352","https://openalex.org/W2952668426","https://openalex.org/W2048488252","https://openalex.org/W2940614149","https://openalex.org/W2787485953"],"abstract_inverted_index":{"Optimization":[0],"of":[1,9,15,38,69,98,120,155],"nearest-neighbor":[2,121],"feature":[3,19,115,122,143],"selection":[4],"depends":[5],"on":[6,72],"the":[7,13,18,54],"number":[8],"samples":[10],"and":[11,22,88,125,135,166],"features,":[12],"type":[14],"statistical":[16],"effect,":[17],"scoring":[20,123],"algorithm,":[21],"class":[23,43,56,103],"imbalance.":[24,44,104],"We":[25,59,145],"recently":[26],"reported":[27],"a":[28,62,89,118,153],"fixed-k":[29,52,64,90,191],"for":[30,42,142,169],"Nearest-neighbor":[31],"Projected-Distance":[32],"Regression":[33],"(NPDR)":[34],"that":[35,110,175,188],"addresses":[36],"each":[37],"these":[39],"parameters,":[40],"except":[41],"To":[45],"remedy":[46],"this,":[47],"we":[48,77,108,126],"parameterize":[49],"our":[50,111,189],"NPDR":[51,161,176],"by":[53],"minority":[55],"size":[57],"(minority-class-k).":[58],"also":[60],"introduce":[61],"class-adaptive":[63],"(hit-miss-k)":[65],"to":[66,102,132,148,185],"improve":[67,114],"performance":[68,129],"Relief-based":[70],"algorithms":[71],"imbalanced":[73],"data.":[74],"In":[75],"addition,":[76],"present":[78],"two":[79],"optimization":[80],"methods,":[81],"including":[82],"constrained":[83],"variable-wise":[84],"optimized":[85],"k":[86],"(VWOK)":[87],"derived":[91],"with":[92,162,177,182],"principal":[93],"components":[94],"analysis":[95,173],"(kPCA),":[96],"both":[97],"which":[99],"are":[100],"adaptive":[101],"Using":[105],"simulated":[106],"data,":[107],"show":[109],"methods":[112],"significantly":[113],"detection":[116],"across":[117],"variety":[119],"metrics,":[124],"demonstrate":[127],"superior":[128],"in":[130],"comparison":[131],"random":[133,164],"forest":[134],"ridge":[136],"regression":[137,168],"using":[138,160],"consensus-nested":[139],"cross-validation":[140],"(cnCV)":[141],"selection.":[144],"applied":[146],"cnCV":[147],"RNASeq":[149],"expression":[150],"data":[151],"from":[152],"study":[154],"Major":[156],"Depressive":[157],"Disorder":[158],"(MDD)":[159],"minority-class-k,":[163],"forest,":[165],"cnCV-ridge":[167],"gene":[170],"importance.":[171],"Pathway":[172],"showed":[174],"minority-class-k":[178],"alone":[179],"detected":[180],"genes":[181],"clear":[183],"relevance":[184],"MDD,":[186],"suggesting":[187],"new":[190],"formula":[192],"is":[193],"an":[194],"effective":[195],"rule-of-thumb.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}