{"id":"https://openalex.org/W2296055924","doi":"https://doi.org/10.1021/acs.jcim.5b00101","title":"Comparing the Influence of Simulated Experimental Errors on 12 Machine Learning Algorithms in Bioactivity Modeling Using 12 Diverse Data Sets","display_name":"Comparing the Influence of Simulated Experimental Errors on 12 Machine Learning Algorithms in Bioactivity Modeling Using 12 Diverse Data Sets","publication_year":2015,"publication_date":"2015-06-03","ids":{"openalex":"https://openalex.org/W2296055924","doi":"https://doi.org/10.1021/acs.jcim.5b00101","mag":"2296055924","pmid":"https://pubmed.ncbi.nlm.nih.gov/26038978"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5b00101","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5b00101","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","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/A5091416834","display_name":"Isidro Cort\u00e9s\u2010Ciriano","orcid":"https://orcid.org/0000-0002-2036-494X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"funder","lineage":["https://openalex.org/I157536573"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Isidro Cortes-Ciriano","raw_affiliation_strings":["D\u00e9partement\rde Biologie Structurale et Chimie, Institut Pasteur, Unit\u00e9 de Bioinformatique Structurale, CNRS UMR 3825, 25, rue du Dr Roux, 75015 Paris, Ile de France, France"],"affiliations":[{"raw_affiliation_string":"D\u00e9partement\rde Biologie Structurale et Chimie, Institut Pasteur, Unit\u00e9 de Bioinformatique Structurale, CNRS UMR 3825, 25, rue du Dr Roux, 75015 Paris, Ile de France, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026643759","display_name":"Andreas Bender","orcid":"https://orcid.org/0000-0002-6683-7546"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andreas Bender","raw_affiliation_strings":["Centre\rfor Molecular Science Informatics, Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Centre\rfor Molecular Science Informatics, Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048175686","display_name":"Th\u00e9r\u00e8se E. Malliavin","orcid":"https://orcid.org/0000-0002-3276-3366"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I157536573","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12","country_code":"FR","type":"funder","lineage":["https://openalex.org/I157536573"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Th\u00e9r\u00e8se E. Malliavin","raw_affiliation_strings":["D\u00e9partement\rde Biologie Structurale et Chimie, Institut Pasteur, Unit\u00e9 de Bioinformatique Structurale, CNRS UMR 3825, 25, rue du Dr Roux, 75015 Paris, Ile de France, France"],"affiliations":[{"raw_affiliation_string":"D\u00e9partement\rde Biologie Structurale et Chimie, Institut Pasteur, Unit\u00e9 de Bioinformatique Structurale, CNRS UMR 3825, 25, rue du Dr Roux, 75015 Paris, Ile de France, France","institution_ids":["https://openalex.org/I157536573","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091416834"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I157536573"],"apc_list":null,"apc_paid":null,"fwci":3.6383,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93620657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"55","issue":"7","first_page":"1413","last_page":"1425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9930999875068665,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9930999875068665,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9879000186920166,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6167250871658325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6076037883758545},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49656087160110474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4735397696495056},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.47085684537887573},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4518267512321472},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.4510561227798462},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4495851993560791},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42937329411506653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4256565272808075},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41513383388519287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40874823927879333}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6167250871658325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6076037883758545},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49656087160110474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4735397696495056},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.47085684537887573},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4518267512321472},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.4510561227798462},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4495851993560791},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42937329411506653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4256565272808075},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41513383388519287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40874823927879333},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic 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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5b00101","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5b00101","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:26038978","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26038978","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G8703363528","display_name":null,"funder_award_id":"336159","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320322141","display_name":"Institut Pasteur","ror":"https://ror.org/0495fxg12"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W429766147","https://openalex.org/W1480376833","https://openalex.org/W1513618424","https://openalex.org/W1542652324","https://openalex.org/W1567012231","https://openalex.org/W1594031697","https://openalex.org/W1605688901","https://openalex.org/W1607198972","https://openalex.org/W1678356000","https://openalex.org/W1831050183","https://openalex.org/W1898375943","https://openalex.org/W1906257803","https://openalex.org/W1912123407","https://openalex.org/W1987275960","https://openalex.org/W1988037271","https://openalex.org/W1988909822","https://openalex.org/W1988950592","https://openalex.org/W1994550352","https://openalex.org/W1995897489","https://openalex.org/W2034841618","https://openalex.org/W2043990744","https://openalex.org/W2048611698","https://openalex.org/W2049074494","https://openalex.org/W2051503575","https://openalex.org/W2067885219","https://openalex.org/W2071234745","https://openalex.org/W2073503722","https://openalex.org/W2076592938","https://openalex.org/W2083298336","https://openalex.org/W2087661061","https://openalex.org/W2088794999","https://openalex.org/W2088970363","https://openalex.org/W2095032418","https://openalex.org/W2096541451","https://openalex.org/W2096560421","https://openalex.org/W2097363837","https://openalex.org/W2097936772","https://openalex.org/W2105958932","https://openalex.org/W2107189314","https://openalex.org/W2119821739","https://openalex.org/W2121302072","https://openalex.org/W2125055259","https://openalex.org/W2128728535","https://openalex.org/W2129434099","https://openalex.org/W2138695073","https://openalex.org/W2144377773","https://openalex.org/W2147169507","https://openalex.org/W2157963336","https://openalex.org/W2168990503","https://openalex.org/W2314633289","https://openalex.org/W2317066137","https://openalex.org/W2323444743","https://openalex.org/W2329862012","https://openalex.org/W2479531384","https://openalex.org/W2490901831","https://openalex.org/W2911964244","https://openalex.org/W3106889297","https://openalex.org/W4205431832","https://openalex.org/W4211049957","https://openalex.org/W4285719527","https://openalex.org/W4312960235","https://openalex.org/W6607348573","https://openalex.org/W6631550275"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4200112873","https://openalex.org/W2955796858","https://openalex.org/W4224941037","https://openalex.org/W2073883415","https://openalex.org/W2004826645","https://openalex.org/W3135818052","https://openalex.org/W4363647452"],"abstract_inverted_index":{"To":[0,20],"date,":[1],"no":[2],"systematic":[3],"study":[4],"has":[5,203],"assessed":[6],"the":[7,14,27,43,87,97,108,115,118,139,199,208,250,292,297],"effect":[8],"of":[9,17,30,101,107,110,141,211,244,252],"random":[10],"experimental":[11],"errors":[12],"on":[13,34,86,207],"predictive":[15],"power":[16],"QSAR":[18],"models.":[19],"address":[21],"this":[22,220],"shortage,":[23],"we":[24,196],"have":[25],"benchmarked":[26],"noise":[28,99,112,122,171,191,209,236,262,266,293],"sensitivity":[29,100,210,263],"12":[31,35],"learning":[32],"algorithms":[33,103,232],"data":[36,148],"sets":[37],"(15,840":[38],"models":[39],"in":[40,145,268,296],"total),":[41],"namely":[42],"following:":[44],"Support":[45],"Vector":[46,64],"Machines":[47,65,73],"(SVM)":[48],"with":[49,58,130,162,249],"radial":[50,59],"and":[51,60,81,186,241,257,285],"polynomial":[52,61],"(Poly)":[53],"kernels,":[54,62],"Gaussian":[55,128],"Process":[56],"(GP)":[57],"Relevant":[63],"(radial":[66],"kernel),":[67],"Random":[68],"Forest":[69],"(RF),":[70],"Gradient":[71],"Boosting":[72],"(GBM),":[74],"Bagged":[75],"Regression":[76],"Trees,":[77],"Partial":[78],"Least":[79],"Squares,":[80],"k-Nearest":[82],"Neighbors.":[83],"Model":[84],"performance":[85,175,246],"test":[88],"set":[89,224],"was":[90,123,160,176],"used":[91],"as":[92,104,238],"a":[93,105,146,156,163,204,234,239,275],"proxy":[94],"to":[95,114,138,178,278,288,291],"monitor":[96],"relative":[98],"these":[102,272],"function":[106],"level":[109,251,294],"simulated":[111,124],"added":[113],"bioactivities":[116],"from":[117,127,136],"training":[119],"set.":[120,149],"The":[121,229],"by":[125,154],"sampling":[126],"distributions":[129],"increasingly":[131],"larger":[132],"variances,":[133],"which":[134,159,283],"ranged":[135],"zero":[137],"range":[140],"pIC50":[142],"values":[143,216,287],"comprised":[144],"given":[147],"General":[150],"trends":[151],"were":[152],"identified":[153],"designing":[155],"full-factorial":[157],"experiment,":[158],"analyzed":[161],"normal":[164],"linear":[165,242],"model.":[166],"Overall,":[167,271],"GBM":[168],"displayed":[169],"low":[170,190,215],"tolerance,":[172,237],"although":[173],"its":[174],"comparable":[177,235],"RF,":[179],"SVM":[180,182,255],"Radial,":[181],"Poly,":[183,185],"GP":[184,187,258],"Radial":[188],"at":[189,264],"levels.":[192],"Of":[193],"practical":[194,276],"relevance,":[195],"show":[197],"that":[198,214],"bag":[200],"fraction":[201],"parameter":[202,221,286],"marked":[205],"influence":[206],"GBM,":[212],"suggesting":[213],"(e.g.,":[217],"0.1-0.2)":[218],"for":[219],"should":[222],"be":[223],"when":[225],"modeling":[226],"noisy":[227],"data.":[228,298],"remaining":[230],"11":[231],"display":[233,260],"smooth":[240],"degradation":[243],"model":[245],"is":[247],"observed":[248],"noise.":[253],"However,":[254],"Poly":[256,259],"significant":[261],"high":[265],"levels":[267],"some":[269],"cases.":[270],"results":[273],"provide":[274],"guide":[277],"make":[279],"informed":[280],"decisions":[281],"about":[282],"algorithm":[284],"use":[289],"according":[290],"present":[295]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}