{"id":"https://openalex.org/W2556851635","doi":"https://doi.org/10.1021/acs.jcim.6b00591","title":"Extreme Gradient Boosting as a Method for Quantitative Structure\u2013Activity Relationships","display_name":"Extreme Gradient Boosting as a Method for Quantitative Structure\u2013Activity Relationships","publication_year":2016,"publication_date":"2016-11-23","ids":{"openalex":"https://openalex.org/W2556851635","doi":"https://doi.org/10.1021/acs.jcim.6b00591","mag":"2556851635","pmid":"https://pubmed.ncbi.nlm.nih.gov/27958738"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.6b00591","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6b00591","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/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":["Modeling and Informatics Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States"],"raw_orcid":"https://orcid.org/0000-0002-6549-1635","affiliations":[{"raw_affiliation_string":"Modeling and Informatics Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331950","display_name":"Wei Min Wang","orcid":"https://orcid.org/0000-0002-5422-171X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Min Wang","raw_affiliation_strings":["Data\rScience Department, MSD International GmbH (Singapore Branch), 1\rFusionopolis Place, #06-10/07-18, Galaxis, Singapore 138522"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data\rScience Department, MSD International GmbH (Singapore Branch), 1\rFusionopolis Place, #06-10/07-18, Galaxis, Singapore 138522","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018772991","display_name":"Andy Liaw","orcid":null},"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":"Andy Liaw","raw_affiliation_strings":["Biometrics Research Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103477103","display_name":"Junshui Ma","orcid":"https://orcid.org/0009-0008-0324-8155"},"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":"Junshui Ma","raw_affiliation_strings":["Biometrics Research Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometrics Research Department, Merck & Co. Inc., 126 E. Lincoln Ave., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108210243","display_name":"Eric Gifford","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric M. Gifford","raw_affiliation_strings":["Bioinformatics\rDepartment, MSD International GmbH (Singapore Branch), 1 Fusionopolis\rPlace, #06-10/07-18, Galaxis, Singapore 138522"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics\rDepartment, MSD International GmbH (Singapore Branch), 1 Fusionopolis\rPlace, #06-10/07-18, Galaxis, Singapore 138522","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6278,"has_fulltext":false,"cited_by_count":530,"citation_normalized_percentile":{"value":0.99530061,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"56","issue":"12","first_page":"2353","last_page":"2360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9746000170707703,"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/random-forest","display_name":"Random forest","score":0.7853058576583862},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7109382152557373},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.6925424933433533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6858465075492859},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6013731956481934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.58446204662323},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5003728866577148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4561566114425659},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.44718092679977417},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4420653283596039},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43494734168052673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36540406942367554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1869177520275116}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7853058576583862},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7109382152557373},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.6925424933433533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858465075492859},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6013731956481934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.58446204662323},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5003728866577148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4561566114425659},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.44718092679977417},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4420653283596039},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43494734168052673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36540406942367554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1869177520275116},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","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":"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":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.6b00591","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.6b00591","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:27958738","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27958738","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1977405994","https://openalex.org/W1978163942","https://openalex.org/W1988195734","https://openalex.org/W1999798000","https://openalex.org/W2019678805","https://openalex.org/W2021748110","https://openalex.org/W2026910177","https://openalex.org/W2043990744","https://openalex.org/W2070493638","https://openalex.org/W2090641453","https://openalex.org/W2106525823","https://openalex.org/W2213443318","https://openalex.org/W2295598076","https://openalex.org/W2296055924","https://openalex.org/W2911964244","https://openalex.org/W3102476541","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W2967733078","https://openalex.org/W3137904399","https://openalex.org/W4310492845","https://openalex.org/W4386690025","https://openalex.org/W2885778889","https://openalex.org/W2766514146","https://openalex.org/W4289703016","https://openalex.org/W2885516856","https://openalex.org/W2073883415","https://openalex.org/W4310224730"],"abstract_inverted_index":{"In":[0,47],"the":[1,36,89,153,159],"pharmaceutical":[2],"industry":[3],"it":[4],"is":[5,112],"common":[6],"to":[7,56],"generate":[8,35],"many":[9,72],"QSAR":[10,29],"models":[11],"from":[12],"training":[13],"sets":[14],"containing":[15],"a":[16,22,78,128,144,150],"large":[17,23],"number":[18,24],"of":[19,25,80,94,103,110,118,152,156,158],"molecules":[20],"and":[21,59,97,130],"descriptors.":[26],"The":[27,107],"best":[28],"methods":[30],"are":[31,42,134],"those":[32,93,102],"that":[33,41],"can":[34,76,140],"most":[37],"accurate":[38],"predictions":[39],"but":[40],"not":[43],"overly":[44],"expensive":[45],"computationally.":[46],"this":[48],"paper":[49],"we":[50,75],"compare":[51],"eXtreme":[52],"Gradient":[53],"Boosting":[54],"(XGBoost)":[55],"random":[57,95,119],"forest":[58,96,120],"single-task":[60],"deep":[61,104,131],"neural":[62,105,132],"nets":[63,133],"on":[64,88,127,137,143],"30":[65],"in-house":[66],"data":[67],"sets.":[68],"While":[69],"XGBoost":[70,85,111,139],"has":[71],"adjustable":[73],"parameters,":[74],"define":[77],"set":[79],"standard":[81],"parameters":[82],"at":[83],"which":[84],"makes":[86],"predictions,":[87],"average,":[90],"better":[91],"than":[92,149],"almost":[98],"as":[99,101],"good":[100],"nets.":[106],"biggest":[108],"strength":[109],"its":[113],"speed.":[114],"Whereas":[115],"efficient":[116],"use":[117],"requires":[121],"generating":[122],"each":[123],"tree":[124],"in":[125,147],"parallel":[126],"cluster,":[129],"usually":[135],"run":[136,142],"GPUs,":[138],"be":[141],"single":[145],"CPU":[146],"less":[148],"third":[151],"wall-clock":[154],"time":[155],"either":[157],"other":[160],"methods.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":27},{"year":2025,"cited_by_count":92},{"year":2024,"cited_by_count":92},{"year":2023,"cited_by_count":76},{"year":2022,"cited_by_count":75},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":53},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":7}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}