{"id":"https://openalex.org/W2071516191","doi":"https://doi.org/10.1145/1014052.1016923","title":"Learning a complex metabolomic dataset using random forests and support vector machines","display_name":"Learning a complex metabolomic dataset using random forests and support vector machines","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2071516191","doi":"https://doi.org/10.1145/1014052.1016923","mag":"2071516191"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1016923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5112216962","display_name":"Young K. Truong","orcid":"https://orcid.org/0009-0003-8679-2917"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Young Truong","raw_affiliation_strings":["University of North Carolina, Chapel Hill, NC","University of North Carolina, Chapel, Hill, NC#TAB#"],"affiliations":[{"raw_affiliation_string":"University of North Carolina, Chapel Hill, NC","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"University of North Carolina, Chapel, Hill, NC#TAB#","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083787204","display_name":"Xiaodong Lin","orcid":"https://orcid.org/0000-0001-8916-6645"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Lin","raw_affiliation_strings":["Duke University, Research Triangle Park, NC","Duke University, Research Triangle Park, NC#TAB#"],"affiliations":[{"raw_affiliation_string":"Duke University, Research Triangle Park, NC","institution_ids":["https://openalex.org/I1309191912"]},{"raw_affiliation_string":"Duke University, Research Triangle Park, NC#TAB#","institution_ids":["https://openalex.org/I1309191912","https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001180013","display_name":"Chris Beecher","orcid":"https://orcid.org/0000-0003-4934-7278"},"institutions":[{"id":"https://openalex.org/I4210090916","display_name":"Triangle","ror":"https://ror.org/00fhbr831","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210090916"]},{"id":"https://openalex.org/I4210123764","display_name":"Metabolon (United States)","ror":"https://ror.org/033qhvk72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123764"]},{"id":"https://openalex.org/I1309191912","display_name":"Research Triangle Park Foundation","ror":"https://ror.org/03eqttr49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1309191912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Beecher","raw_affiliation_strings":["Metabolon, Research Triangle Park, NC","Metabolon, Research Triangle Park, NC#TAB#"],"affiliations":[{"raw_affiliation_string":"Metabolon, Research Triangle Park, NC","institution_ids":["https://openalex.org/I4210123764","https://openalex.org/I4210090916"]},{"raw_affiliation_string":"Metabolon, Research Triangle Park, NC#TAB#","institution_ids":["https://openalex.org/I1309191912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112216962"],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.1169,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.47433719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"835","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9998999834060669,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9998999834060669,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9804999828338623,"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/support-vector-machine","display_name":"Support vector machine","score":0.829677939414978},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8274286985397339},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6978434324264526},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6613972187042236},{"id":"https://openalex.org/keywords/metabolomics","display_name":"Metabolomics","score":0.6202020645141602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5285826325416565},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5265569686889648},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.48246484994888306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42605432868003845},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4173422157764435},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41679292917251587},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4022829532623291},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3842760920524597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38218265771865845},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33765578269958496},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.28764626383781433}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.829677939414978},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8274286985397339},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6978434324264526},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6613972187042236},{"id":"https://openalex.org/C21565614","wikidata":"https://www.wikidata.org/wiki/Q12149006","display_name":"Metabolomics","level":2,"score":0.6202020645141602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285826325416565},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5265569686889648},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.48246484994888306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42605432868003845},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4173422157764435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41679292917251587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4022829532623291},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3842760920524597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38218265771865845},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33765578269958496},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.28764626383781433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1014052.1016923","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016923","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W33057087","https://openalex.org/W1512708805","https://openalex.org/W1594031697","https://openalex.org/W2054044693","https://openalex.org/W2063309970","https://openalex.org/W2153631847","https://openalex.org/W2911964244","https://openalex.org/W3023786531","https://openalex.org/W3085162807","https://openalex.org/W6633616865","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W42525420","https://openalex.org/W4283773154","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Metabolomics":[0],"is":[1,76,103,121,176],"the":[2,11,62,82,99,106,115,140,161,192,195],"\"omics\"":[3],"science":[4],"of":[5,14,94,101,108,173,180,194],"biochemistry.":[6],"The":[7,49,74,171],"associated":[8],"data":[9,113,118],"include":[10],"quantitative":[12],"measurements":[13],"all":[15],"small":[16],"molecule":[17],"metabolites":[18],"in":[19,52,166],"a":[20,26,92,131],"biological":[21],"sample.":[22],"These":[23],"datasets":[24],"provide":[25],"window":[27],"into":[28,178],"dynamic":[29],"biochemical":[30],"networks":[31],"and":[32,39,59,61,114,148,157,168,183],"conjointly":[33],"with":[34,164],"other":[35],"\"omic\"":[36],"data,":[37,98],"genes":[38],"proteins,":[40],"have":[41],"great":[42],"potential":[43],"to":[44,77,130,191],"unravel":[45],"complex":[46],"human":[47],"diseases.":[48],"dataset":[50],"used":[51],"this":[53,174],"study":[54,175],"has":[55],"63":[56],"individuals,":[57],"normal":[58],"diseased,":[60],"diseased":[63],"are":[64,71,91,111,119,136],"drug":[65],"treated":[66],"or":[67],"not,":[68],"so":[69],"there":[70,110,135],"three":[72],"classes.":[73],"goal":[75],"classify":[78],"these":[79],"individuals":[80],"using":[81],"observed":[83],"metabolite":[84],"levels":[85],"for":[86,152],"317":[87],"measured":[88],"metabolites.":[89,141],"There":[90],"number":[93,100,107],"statistical":[95],"challenges:":[96],"non-normal":[97],"samples":[102],"less":[104],"than":[105],"metabolites;":[109],"missing":[112,120],"fact":[116],"that":[117],"informative":[122],"(assay":[123],"values":[124],"below":[125],"detection":[126],"limits":[127],"can":[128],"point":[129],"specific":[132],"class);":[133],"also,":[134],"high":[137],"correlations":[138],"among":[139],"We":[142,159,186],"investigate":[143],"support":[144],"vector":[145],"machines":[146],"(SVM),":[147],"random":[149],"forest":[150],"(RF),":[151],"outlier":[153],"detection,":[154],"variable":[155,181],"selection":[156,182],"classification.":[158],"use":[160],"variables":[162],"selected":[163,189],"RF":[165],"SVM":[167],"visa":[169],"versa.":[170],"benefit":[172],"insight":[177],"interplay":[179],"classification":[184],"methods.":[185],"link":[187],"our":[188],"predictors":[190],"biochemistry":[193],"disease.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}