{"id":"https://openalex.org/W1988195734","doi":"https://doi.org/10.1021/ci034160g","title":"Random Forest:\u2009 A Classification and Regression Tool for Compound Classification and QSAR Modeling","display_name":"Random Forest:\u2009 A Classification and Regression Tool for Compound Classification and QSAR Modeling","publication_year":2003,"publication_date":"2003-11-01","ids":{"openalex":"https://openalex.org/W1988195734","doi":"https://doi.org/10.1021/ci034160g","mag":"1988195734","pmid":"https://pubmed.ncbi.nlm.nih.gov/14632445"},"language":"en","primary_location":{"id":"doi:10.1021/ci034160g","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034160g","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","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/A5081059721","display_name":"Vladimir Svetnik","orcid":"https://orcid.org/0000-0003-1561-2387"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vladimir Svetnik","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018772991","display_name":"Andy Liaw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andy Liaw","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006596843","display_name":"Christopher Tong","orcid":"https://orcid.org/0000-0003-0770-3270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Tong","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042020810","display_name":"Joseph Culberson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Christopher Culberson","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082475080","display_name":"Robert P. Sheridan","orcid":"https://orcid.org/0000-0002-6549-1635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert P. Sheridan","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072091499","display_name":"Bradley P. Feuston","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bradley P. Feuston","raw_affiliation_strings":["Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065, Molecular Systems, Merck Research Laboratories, P.O. Box 4, West Point, Pennsylvania 19486, and Molecular Systems, Merck Research Laboratories, P.O. Box 2000, Rahway, New Jersey 07065","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5081059721"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.1684,"has_fulltext":false,"cited_by_count":3598,"citation_normalized_percentile":{"value":0.99581975,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"43","issue":"6","first_page":"1947","last_page":"1958"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9847000241279602,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9803000092506409,"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/random-forest","display_name":"Random forest","score":0.9463829398155212},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.7397216558456421},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7170151472091675},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5345869064331055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5237317681312561},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5173711180686951},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4980897903442383},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.49538886547088623},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47176697850227356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4667319059371948},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46456778049468994},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.43166959285736084},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.42012345790863037},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4153480529785156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3988840579986572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33281487226486206},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.30592411756515503},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.07510867714881897}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.9463829398155212},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.7397216558456421},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7170151472091675},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5345869064331055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5237317681312561},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5173711180686951},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4980897903442383},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.49538886547088623},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47176697850227356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4667319059371948},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46456778049468994},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.43166959285736084},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.42012345790863037},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4153480529785156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3988840579986572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33281487226486206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30592411756515503},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.07510867714881897},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1021/ci034160g","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci034160g","pdf_url":null,"source":{"id":"https://openalex.org/S171559003","display_name":"Journal of Chemical Information and Computer Sciences","issn_l":"0095-2338","issn":["0095-2338","1520-5142"],"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 Computer Sciences","raw_type":"journal-article"},{"id":"pmid:14632445","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14632445","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 computer sciences","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1491002046","https://openalex.org/W1594031697","https://openalex.org/W1594730842","https://openalex.org/W1678356000","https://openalex.org/W1840338487","https://openalex.org/W1966632536","https://openalex.org/W1987202142","https://openalex.org/W1988790447","https://openalex.org/W1994126845","https://openalex.org/W2003254548","https://openalex.org/W2005685204","https://openalex.org/W2015928143","https://openalex.org/W2021070595","https://openalex.org/W2021748110","https://openalex.org/W2051802332","https://openalex.org/W2064676317","https://openalex.org/W2067885219","https://openalex.org/W2096729078","https://openalex.org/W2103238395","https://openalex.org/W2117812871","https://openalex.org/W2139353173","https://openalex.org/W2164583936"],"related_works":["https://openalex.org/W1573015311","https://openalex.org/W1570419641","https://openalex.org/W4386509167","https://openalex.org/W2889938001","https://openalex.org/W4293771607","https://openalex.org/W3165034028","https://openalex.org/W2296499206","https://openalex.org/W2551736466","https://openalex.org/W2382340815","https://openalex.org/W3136871737"],"abstract_inverted_index":{"A":[0],"new":[1],"classification":[2,38],"and":[3,10,51,123,147],"regression":[4,40],"tool,":[5],"Random":[6,31,85,111,155],"Forest,":[7],"is":[8,33,59,87,96,130,139],"introduced":[9],"investigated":[11],"for":[12,76,159],"predicting":[13],"a":[14,23,88,116,124],"compound's":[15,28],"quantitative":[16,24],"or":[17,39,65],"categorical":[18],"biological":[19],"activity":[20],"based":[21],"on":[22],"description":[25],"of":[26,36,47,69,92,110,118,121,126,136,142,150],"the":[27,48,67,70,98,133,140],"molecular":[29],"structure.":[30],"Forest":[32,86,156],"an":[34],"ensemble":[35],"unpruned":[37],"trees":[41],"created":[42],"by":[43,61,132],"using":[44],"bootstrap":[45],"samples":[46],"training":[49],"data":[50,79],"random":[52],"feature":[53],"selection":[54],"in":[55,161],"tree":[56],"induction.":[57],"Prediction":[58],"made":[60],"aggregating":[62],"(majority":[63],"vote":[64],"averaging)":[66],"predictions":[68],"ensemble.":[71],"We":[72,104],"built":[73],"predictive":[74],"models":[75],"six":[77],"cheminformatics":[78],"sets.":[80],"Our":[81],"analysis":[82],"demonstrates":[83],"that":[84,95,129,153],"powerful":[89],"tool":[90],"capable":[91],"delivering":[93],"performance":[94,114],"among":[97],"most":[99],"accurate":[100],"methods":[101],"to":[102],"date.":[103],"also":[105],"present":[106],"three":[107],"additional":[108],"features":[109,152],"Forest:":[112],"built-in":[113],"assessment,":[115],"measure":[117,125],"relative":[119,134],"importance":[120,135],"descriptors,":[122],"compound":[127],"similarity":[128],"weighted":[131],"descriptors.":[137],"It":[138],"combination":[141],"relatively":[143],"high":[144],"prediction":[145],"accuracy":[146],"its":[148],"collection":[149],"desired":[151],"makes":[154],"uniquely":[157],"suited":[158],"modeling":[160],"cheminformatics.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":133},{"year":2025,"cited_by_count":323},{"year":2024,"cited_by_count":345},{"year":2023,"cited_by_count":376},{"year":2022,"cited_by_count":467},{"year":2021,"cited_by_count":408},{"year":2020,"cited_by_count":288},{"year":2019,"cited_by_count":249},{"year":2018,"cited_by_count":186},{"year":2017,"cited_by_count":146},{"year":2016,"cited_by_count":101},{"year":2015,"cited_by_count":99},{"year":2014,"cited_by_count":99},{"year":2013,"cited_by_count":68},{"year":2012,"cited_by_count":62}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}