{"id":"https://openalex.org/W2021444228","doi":"https://doi.org/10.1021/ci200615h","title":"Comparison of Random Forest and Pipeline Pilot Na\u00efve Bayes in Prospective QSAR Predictions","display_name":"Comparison of Random Forest and Pipeline Pilot Na\u00efve Bayes in Prospective QSAR Predictions","publication_year":2012,"publication_date":"2012-02-23","ids":{"openalex":"https://openalex.org/W2021444228","doi":"https://doi.org/10.1021/ci200615h","mag":"2021444228","pmid":"https://pubmed.ncbi.nlm.nih.gov/22360769"},"language":"en","primary_location":{"id":"doi:10.1021/ci200615h","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200615h","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/A5100427431","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0003-3503-2291"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bin Chen","raw_affiliation_strings":["School of Informatics\rand Computing, Indiana University at Bloomington, Bloomington, Indiana 47405, United States"],"affiliations":[{"raw_affiliation_string":"School of Informatics\rand Computing, Indiana University at Bloomington, Bloomington, Indiana 47405, United States","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082475080","display_name":"Robert P. Sheridan","orcid":"https://orcid.org/0000-0002-6549-1635"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert P. Sheridan","raw_affiliation_strings":["Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069016592","display_name":"Viktor Horn\u0306\u00e1k","orcid":"https://orcid.org/0000-0002-2344-9586"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Hornak","raw_affiliation_strings":["Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085300960","display_name":"Johannes Voigt","orcid":"https://orcid.org/0009-0000-3912-8595"},"institutions":[{"id":"https://openalex.org/I1285764155","display_name":"Merck & Co., Inc., Rahway, NJ, USA (United States)","ror":"https://ror.org/02891sr49","country_code":"US","type":"company","lineage":["https://openalex.org/I1285764155"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes H. Voigt","raw_affiliation_strings":["Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Chemistry Modeling and Informatics\rDepartment, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Chemistry Modeling and Informatics#R#Department, Merck Research Laboratories, Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100427431"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":6.3644063,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.97137721,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"52","issue":"3","first_page":"792","last_page":"803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.998199999332428,"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":0.998199999332428,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9973999857902527,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9923999905586243,"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":0.8356903791427612},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8321869373321533},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7370409965515137},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.6682682633399963},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5958070158958435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5779313445091248},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5723108053207397},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5175415873527527},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5029794573783875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5006833076477051},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.19404691457748413},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12659049034118652},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.09497702121734619}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8356903791427612},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8321869373321533},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7370409965515137},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.6682682633399963},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5958070158958435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5779313445091248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5723108053207397},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5175415873527527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5029794573783875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006833076477051},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.19404691457748413},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12659049034118652},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.09497702121734619},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003663","descriptor_name":"Decision Trees","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004791","descriptor_name":"Enzyme Inhibitors","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D013997","descriptor_name":"Time Factors","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci200615h","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200615h","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:22360769","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22360769","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":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W349770100","https://openalex.org/W1971256926","https://openalex.org/W1972821149","https://openalex.org/W1977405994","https://openalex.org/W1978163942","https://openalex.org/W1978253274","https://openalex.org/W1988037271","https://openalex.org/W1988195734","https://openalex.org/W1988909822","https://openalex.org/W1991537916","https://openalex.org/W1995495408","https://openalex.org/W2005772498","https://openalex.org/W2016979469","https://openalex.org/W2017547569","https://openalex.org/W2021574925","https://openalex.org/W2021748110","https://openalex.org/W2026910177","https://openalex.org/W2040429619","https://openalex.org/W2041253429","https://openalex.org/W2041516679","https://openalex.org/W2046653925","https://openalex.org/W2068017165","https://openalex.org/W2071508893","https://openalex.org/W2073503722","https://openalex.org/W2079639517","https://openalex.org/W2085890279","https://openalex.org/W2091295168","https://openalex.org/W2099536767","https://openalex.org/W2112912103","https://openalex.org/W2123590349","https://openalex.org/W2125852843","https://openalex.org/W2142602210","https://openalex.org/W2143456020","https://openalex.org/W2147084679","https://openalex.org/W2148603752","https://openalex.org/W2149150765","https://openalex.org/W2165618135","https://openalex.org/W2911964244","https://openalex.org/W2999197824"],"related_works":["https://openalex.org/W4367336074","https://openalex.org/W3154045278","https://openalex.org/W4379620016","https://openalex.org/W4393666307","https://openalex.org/W3210764983","https://openalex.org/W4393443811","https://openalex.org/W4367335949","https://openalex.org/W3089416646","https://openalex.org/W4380048833","https://openalex.org/W4393601998"],"abstract_inverted_index":{"Random":[0],"forest":[1,65,128],"is":[2,20,25,36,114,123],"currently":[3],"considered":[4],"one":[5],"of":[6,14,16,54,57,104,118,143],"the":[7,37,42,55],"best":[8],"QSAR":[9,39,75],"methods":[10],"available":[11],"in":[12,41,136],"terms":[13],"accuracy":[15],"prediction.":[17,121],"However,":[18,126],"it":[19],"computationally":[21,124],"intensive.":[22],"Na\u00efve":[23,33,60],"Bayes":[24,34,61],"a":[26,52,101,115],"simple,":[27],"robust":[28],"classification":[29,91],"method.":[30],"The":[31],"Laplacian-modified":[32],"implementation":[35],"preferred":[38],"method":[40,103],"widely":[43],"used":[44,100],"commercial":[45],"chemoinformatics":[46],"platform":[47],"Pipeline":[48,58,161],"Pilot.":[49],"We":[50,99],"made":[51],"comparison":[53],"ability":[56],"Pilot":[59],"(PLPNB)":[62],"and":[63,81,107,135,154,163],"random":[64,127],"to":[66,160],"make":[67],"accurate":[68],"predictions":[69,129],"on":[70,145],"18":[71],"large,":[72],"diverse":[73],"in-house":[74],"data":[76,85,147],"sets.":[77,148],"These":[78,84],"include":[79],"on-target":[80],"ADME-related":[82],"activities.":[83,98],"sets":[86],"were":[87],"set":[88],"up":[89],"as":[90,110,133],"problems":[92],"with":[93,152,166],"either":[94],"binary":[95],"or":[96],"multicategory":[97],"time-split":[102],"dividing":[105],"training":[106],"test":[108],"sets,":[109],"we":[111,169],"feel":[112],"this":[113],"realistic":[116],"way":[117],"simulating":[119],"prospective":[120],"PLPNB":[122,144,149],"efficient.":[125],"are":[130,158],"at":[131],"least":[132],"good":[134],"many":[137],"cases":[138],"significantly":[139],"better":[140,151],"than":[141],"those":[142],"our":[146],"performs":[150],"ECFP4":[153],"ECFP6":[155],"descriptors,":[156],"which":[157],"native":[159],"Pilot,":[162],"more":[164],"poorly":[165],"other":[167],"descriptors":[168],"tried.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}