{"id":"https://openalex.org/W1965427641","doi":"https://doi.org/10.1021/ci400527b","title":"Binary Classification of a Large Collection of Environmental Chemicals from Estrogen Receptor Assays by Quantitative Structure\u2013Activity Relationship and Machine Learning Methods","display_name":"Binary Classification of a Large Collection of Environmental Chemicals from Estrogen Receptor Assays by Quantitative Structure\u2013Activity Relationship and Machine Learning Methods","publication_year":2013,"publication_date":"2013-11-26","ids":{"openalex":"https://openalex.org/W1965427641","doi":"https://doi.org/10.1021/ci400527b","mag":"1965427641","pmid":"https://pubmed.ncbi.nlm.nih.gov/24279462"},"language":"en","primary_location":{"id":"doi:10.1021/ci400527b","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci400527b","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/A5067338429","display_name":"Qingda Zang","orcid":"https://orcid.org/0000-0003-1543-8307"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qingda Zang","raw_affiliation_strings":["ORISE Postdoctoral Fellow and \u2021National Center for Computational Toxicology, U.S. Environmental Protection Agency , Research Triangle Park, North Carolina 27711, United States"],"affiliations":[{"raw_affiliation_string":"ORISE Postdoctoral Fellow and \u2021National Center for Computational Toxicology, U.S. Environmental Protection Agency , Research Triangle Park, North Carolina 27711, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064332538","display_name":"Daniel M. Rotroff","orcid":"https://orcid.org/0000-0003-0553-3220"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel M. Rotroff","raw_affiliation_strings":["Bioinformatics\rResearch Center, Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, United States","Bioinformatics#R#Research Center, Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, United States"],"affiliations":[{"raw_affiliation_string":"Bioinformatics\rResearch Center, Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, United States","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Bioinformatics#R#Research Center, Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695, United States","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026992703","display_name":"Richard Judson","orcid":"https://orcid.org/0000-0002-2348-9633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard S. Judson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067338429"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.701,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.98159651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"53","issue":"12","first_page":"3244","last_page":"3261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11460","display_name":"Analytical Methods in Pharmaceuticals","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7160873413085938},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.6895357370376587},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6633512377738953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6603043675422668},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6500495672225952},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.6206512451171875},{"id":"https://openalex.org/keywords/in-silico","display_name":"In silico","score":0.5826514959335327},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5476180911064148},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5240733027458191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4975138008594513},{"id":"https://openalex.org/keywords/applicability-domain","display_name":"Applicability domain","score":0.4869881570339203},{"id":"https://openalex.org/keywords/molecular-descriptor","display_name":"Molecular descriptor","score":0.439762145280838},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18527182936668396}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7160873413085938},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.6895357370376587},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6633512377738953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6603043675422668},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6500495672225952},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.6206512451171875},{"id":"https://openalex.org/C2775905019","wikidata":"https://www.wikidata.org/wiki/Q192572","display_name":"In silico","level":3,"score":0.5826514959335327},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5476180911064148},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5240733027458191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4975138008594513},{"id":"https://openalex.org/C107908354","wikidata":"https://www.wikidata.org/wiki/Q4781456","display_name":"Applicability domain","level":3,"score":0.4869881570339203},{"id":"https://openalex.org/C164923092","wikidata":"https://www.wikidata.org/wiki/Q3705921","display_name":"Molecular descriptor","level":3,"score":0.439762145280838},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18527182936668396},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004784","descriptor_name":"Environmental Monitoring","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004784","descriptor_name":"Environmental Monitoring","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004784","descriptor_name":"Environmental Monitoring","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":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000037","qualifier_name":"antagonists & inhibitors","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D011960","descriptor_name":"Receptors, Estrogen","qualifier_ui":"Q000819","qualifier_name":"agonists","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D014874","descriptor_name":"Water Pollutants, Chemical","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016002","descriptor_name":"Discriminant Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018570","descriptor_name":"Risk Assessment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018570","descriptor_name":"Risk Assessment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018570","descriptor_name":"Risk Assessment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D052244","descriptor_name":"Endocrine Disruptors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci400527b","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci400527b","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:24279462","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24279462","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/10","score":0.44999998807907104,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309037","display_name":"Office of Research and Development","ror":"https://ror.org/05rsv9s98"},{"id":"https://openalex.org/F4320332382","display_name":"Oak Ridge Institute for Science and Education","ror":"https://ror.org/0526p1y61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1418475881","https://openalex.org/W1535188141","https://openalex.org/W1970197319","https://openalex.org/W1980230522","https://openalex.org/W1990814794","https://openalex.org/W1990923714","https://openalex.org/W1992470121","https://openalex.org/W1992826795","https://openalex.org/W1996561782","https://openalex.org/W1999318832","https://openalex.org/W2003998164","https://openalex.org/W2004429971","https://openalex.org/W2005205901","https://openalex.org/W2007145643","https://openalex.org/W2007436490","https://openalex.org/W2012035409","https://openalex.org/W2012444866","https://openalex.org/W2016770597","https://openalex.org/W2021558456","https://openalex.org/W2027109773","https://openalex.org/W2031982698","https://openalex.org/W2032094685","https://openalex.org/W2035052391","https://openalex.org/W2035288789","https://openalex.org/W2036713904","https://openalex.org/W2038857259","https://openalex.org/W2039618891","https://openalex.org/W2041383203","https://openalex.org/W2041392558","https://openalex.org/W2046108080","https://openalex.org/W2051175597","https://openalex.org/W2052260244","https://openalex.org/W2059405137","https://openalex.org/W2061611346","https://openalex.org/W2063500063","https://openalex.org/W2065256937","https://openalex.org/W2067943075","https://openalex.org/W2068895833","https://openalex.org/W2071824173","https://openalex.org/W2076625865","https://openalex.org/W2080525767","https://openalex.org/W2083933079","https://openalex.org/W2095441995","https://openalex.org/W2104020189","https://openalex.org/W2112208320","https://openalex.org/W2122025333","https://openalex.org/W2125697820","https://openalex.org/W2128245586","https://openalex.org/W2144070700","https://openalex.org/W2145126338","https://openalex.org/W2147334256","https://openalex.org/W2148804536","https://openalex.org/W2150962198","https://openalex.org/W2151747929","https://openalex.org/W2159887157","https://openalex.org/W2163772944","https://openalex.org/W2169678694","https://openalex.org/W2329907539","https://openalex.org/W2334218692","https://openalex.org/W3157129055"],"related_works":["https://openalex.org/W2746158299","https://openalex.org/W1969085205","https://openalex.org/W1977382278","https://openalex.org/W2325795844","https://openalex.org/W2753230657","https://openalex.org/W2793396277","https://openalex.org/W2026843845","https://openalex.org/W2059405137","https://openalex.org/W3185489153","https://openalex.org/W2150562758"],"abstract_inverted_index":{"There":[0],"are":[1,342],"thousands":[2],"of":[3,28,102,110,136,157,187,193,207,237,275,296,304,324,350],"environmental":[4,353],"chemicals":[5,22,112,128,208,351],"subject":[6],"to":[7,51,69,117,144,152,167,179,202,209,252,259,333],"regulatory":[8],"decisions":[9],"for":[10,35,345,352],"endocrine":[11],"disrupting":[12],"potential.":[13],"The":[14,43,263],"ToxCast":[15,79,114],"and":[16,40,65,119,159,171,175,191,219,223,234,290,298,311,328],"Tox21":[17,131],"programs":[18],"have":[19],"tested":[20],"\u223c8200":[21],"in":[23,29,53,105,134,139,270],"a":[24,66,93,100,164,273,279,301,322],"broad":[25],"screening":[26,32,349],"panel":[27],"vitro":[30,106,140],"high-throughput":[31],"(HTS)":[33],"assays":[34],"estrogen":[36],"receptor":[37],"(ER)":[38],"agonist":[39],"antagonist":[41],"activity.":[42,262],"present":[44],"work":[45],"uses":[46],"this":[47,177],"large":[48,280],"data":[49,73,327],"set":[50,281,310],"develop":[52],"silico":[54],"quantitative":[55],"structure-activity":[56],"relationship":[57],"(QSAR)":[58],"models":[59,124,199,335],"using":[60,213,268],"machine":[61],"learning":[62],"(ML)":[63],"methods":[64,330],"novel":[67],"approach":[68],"manage":[70],"the":[71,78,121,130,137,147,154,188,194,204,254,260,283,288,294,307,314,347],"imbalanced":[72,155],"distribution.":[74],"Training":[75],"compounds":[76,292],"from":[77,99,113,129,232,278],"project":[80],"were":[81,115,142,200],"categorized":[82],"as":[83,240],"active":[84,158,289],"or":[85,88],"inactive":[86,160,291],"(binding":[87],"nonbinding)":[89],"classes":[90],"based":[91],"on":[92,306,313],"composite":[94],"ER":[95,104,211,261],"Interaction":[96],"Score":[97],"derived":[98],"collection":[101],"13":[103,138],"assays.":[107],"A":[108,243],"total":[109,302],"1537":[111],"used":[116,143],"derive":[118],"optimize":[120],"binary":[122],"classification":[123,198,218],"while":[125],"5073":[126],"additional":[127],"project,":[132],"evaluated":[133],"2":[135],"assays,":[141],"externally":[145],"validate":[146],"model":[148,265],"performance.":[149],"In":[150],"order":[151],"handle":[153],"distribution":[156],"chemicals,":[161],"we":[162],"developed":[163],"cluster-selection":[165],"strategy":[166,178],"minimize":[168],"information":[169],"loss":[170],"increase":[172],"predictive":[173,339],"performance":[174],"compared":[176],"three":[180],"currently":[181],"popular":[182],"techniques:":[183],"cost-sensitive":[184],"learning,":[185],"oversampling":[186],"minority":[189],"class,":[190],"undersampling":[192],"majority":[195],"class.":[196],"QSAR":[197],"built":[201],"relate":[203],"molecular":[205,230],"structures":[206],"their":[210],"activities":[212],"linear":[214],"discriminant":[215],"analysis":[216],"(LDA),":[217],"regression":[220],"trees":[221],"(CART),":[222],"support":[224],"vector":[225],"machines":[226],"(SVM)":[227],"with":[228,272,300],"51":[229],"descriptors":[231,276],"QikProp":[233],"4328":[235],"bits":[236],"structural":[238,255],"fingerprints":[239],"explanatory":[241],"variables.":[242],"random":[244],"forest":[245],"(RF)":[246],"feature":[247],"selection":[248],"method":[249],"was":[250,266],"employed":[251],"extract":[253],"features":[256],"most":[257],"relevant":[258],"best":[264],"obtained":[267],"SVM":[269],"combination":[271,323],"subset":[274],"identified":[277],"via":[282],"RF":[284],"algorithm,":[285],"which":[286,341],"recognized":[287],"at":[293],"accuracies":[295],"76.1%":[297],"82.8%":[299],"accuracy":[303],"81.6%":[305],"internal":[308],"test":[309,316],"70.8%":[312],"external":[315],"set.":[317],"These":[318],"results":[319],"demonstrate":[320],"that":[321,336],"high-quality":[325],"experimental":[326],"ML":[329],"can":[331],"lead":[332],"robust":[334],"achieve":[337],"excellent":[338],"accuracy,":[340],"potentially":[343],"useful":[344],"facilitating":[346],"virtual":[348],"risk":[354],"assessment.":[355]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":3}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}