{"id":"https://openalex.org/W3012585755","doi":"https://doi.org/10.1021/acs.jcim.9b01067","title":"Experimental Error, Kurtosis, Activity Cliffs, and Methodology: What Limits the Predictivity of Quantitative Structure\u2013Activity Relationship Models?","display_name":"Experimental Error, Kurtosis, Activity Cliffs, and Methodology: What Limits the Predictivity of Quantitative Structure\u2013Activity Relationship Models?","publication_year":2020,"publication_date":"2020-03-24","ids":{"openalex":"https://openalex.org/W3012585755","doi":"https://doi.org/10.1021/acs.jcim.9b01067","mag":"3012585755","pmid":"https://pubmed.ncbi.nlm.nih.gov/32207612"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.9b01067","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b01067","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":true,"raw_author_name":"Robert P. Sheridan","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., Kenilworth, New Jersey 07033, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., Kenilworth, New Jersey 07033, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026525812","display_name":"Prabha Karnachi","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":"Prabha Karnachi","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., Kenilworth, New Jersey 07033, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., Kenilworth, New Jersey 07033, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078362457","display_name":"Matthew Tudor","orcid":"https://orcid.org/0000-0001-8766-195X"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Tudor","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., West Point, Pennsylvania 19486, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., West Point, Pennsylvania 19486, United States","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079572594","display_name":"Yuting Xu","orcid":"https://orcid.org/0000-0003-2091-3854"},"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":"Yuting Xu","raw_affiliation_strings":["Biometrics Research, Merck & Company Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck & Company Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"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, Merck & Company Inc., Rahway, New Jersey 07065, United States"],"affiliations":[{"raw_affiliation_string":"Biometrics Research, Merck & Company Inc., Rahway, New Jersey 07065, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069224628","display_name":"Falgun Shah","orcid":"https://orcid.org/0000-0001-9280-5487"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Falgun Shah","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., West Point, Pennsylvania 19486, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., West Point, Pennsylvania 19486, United States","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083026456","display_name":"Alan C. Cheng","orcid":"https://orcid.org/0000-0003-3645-172X"},"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":"Alan C. Cheng","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., South San Francisco, California 94080, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., South San Francisco, California 94080, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027719975","display_name":"Elizabeth Joshi","orcid":"https://orcid.org/0000-0003-3267-0634"},"institutions":[{"id":"https://openalex.org/I192545095","display_name":"United States Military Academy","ror":"https://ror.org/01jepya76","country_code":"US","type":"education","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I192545095","https://openalex.org/I4210088792"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Joshi","raw_affiliation_strings":["Pharmacokinetics, Pharmacodynamics & Drug Metabolism, Merck & Company Inc., West Point, Pennsylvania 19486, United States"],"affiliations":[{"raw_affiliation_string":"Pharmacokinetics, Pharmacodynamics & Drug Metabolism, Merck & Company Inc., West Point, Pennsylvania 19486, United States","institution_ids":["https://openalex.org/I192545095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110421667","display_name":"Meir Glick","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":"Meir Glick","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., Boston, Massachusetts 02115, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., Boston, Massachusetts 02115, United States","institution_ids":["https://openalex.org/I1285764155"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101692824","display_name":"Juan C. Alvarez","orcid":"https://orcid.org/0000-0003-2031-2135"},"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":"Juan Alvarez","raw_affiliation_strings":["Computational and Structural Chemistry, Merck & Company Inc., Boston, Massachusetts 02115, United States"],"affiliations":[{"raw_affiliation_string":"Computational and Structural Chemistry, Merck & Company Inc., Boston, Massachusetts 02115, United States","institution_ids":["https://openalex.org/I1285764155"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5082475080"],"corresponding_institution_ids":["https://openalex.org/I1285764155"],"apc_list":null,"apc_paid":null,"fwci":5.1963,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96273043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"60","issue":"4","first_page":"1969","last_page":"1982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.995199978351593,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9573000073432922,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8394975662231445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6131532788276672},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5960352420806885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5770976543426514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5585129857063293},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5135155320167542},{"id":"https://openalex.org/keywords/cliff","display_name":"Cliff","score":0.4513874351978302},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41139236092567444},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07236850261688232}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8394975662231445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6131532788276672},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5960352420806885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5770976543426514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5585129857063293},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5135155320167542},{"id":"https://openalex.org/C164139821","wikidata":"https://www.wikidata.org/wiki/Q107679","display_name":"Cliff","level":2,"score":0.4513874351978302},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41139236092567444},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07236850261688232},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000073886","descriptor_name":"Scientific Experimental Error","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000073886","descriptor_name":"Scientific Experimental Error","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000073886","descriptor_name":"Scientific Experimental Error","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013329","descriptor_name":"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":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":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.9b01067","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.9b01067","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:32207612","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32207612","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W128607844","https://openalex.org/W1988037271","https://openalex.org/W1988195734","https://openalex.org/W1999798000","https://openalex.org/W2007344527","https://openalex.org/W2016979469","https://openalex.org/W2019678805","https://openalex.org/W2021083597","https://openalex.org/W2021748110","https://openalex.org/W2026910177","https://openalex.org/W2039609876","https://openalex.org/W2085890279","https://openalex.org/W2096541451","https://openalex.org/W2118585731","https://openalex.org/W2140959043","https://openalex.org/W2213443318","https://openalex.org/W2278332638","https://openalex.org/W2295598076","https://openalex.org/W2327438214","https://openalex.org/W2329862012","https://openalex.org/W2330317998","https://openalex.org/W2410846838","https://openalex.org/W2473238561","https://openalex.org/W2556851635","https://openalex.org/W2735246657","https://openalex.org/W2889157215","https://openalex.org/W2892349988","https://openalex.org/W2911964244","https://openalex.org/W2916327454","https://openalex.org/W2947071759","https://openalex.org/W2999614829","https://openalex.org/W3102476541","https://openalex.org/W4233751794","https://openalex.org/W4234276140","https://openalex.org/W4241690031"],"related_works":["https://openalex.org/W4296179769","https://openalex.org/W4233990179","https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W2513124405","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1571156853"],"abstract_inverted_index":{"Given":[0],"a":[1,72,107,157],"particular":[2],"descriptor/method":[3],"combination,":[4],"some":[5,164],"quantitative":[6],"structure-activity":[7],"relationship":[8],"(QSAR)":[9],"datasets":[10,83,95,104],"are":[11,19,43,167,201],"very":[12],"predictive":[13,71,88],"by":[14],"random-split":[15,191],"cross-validation":[16],"while":[17],"others":[18],"not.":[20],"Recent":[21],"literature":[22],"in":[23,33,68,150,208,213],"modelability":[24,136],"suggests":[25],"that":[26,84,105,115,156,195],"the":[27,34,37,41,54,62,92,97,123,129,135,151,172,181],"limiting":[28,214],"issue":[29],"for":[30],"predictivity":[31,120,189,192],"is":[32,74,101],"data,":[35,53],"not":[36],"QSAR":[38,161],"methodology,":[39],"and":[40,64,103,163,193],"limits":[42],"due":[44,146],"to":[45,76,147],"activity":[46,65,116,144,177,209,211],"cliffs.":[47],"Here,":[48],"we":[49,126,186],"investigate,":[50],"on":[51,91,176],"in-house":[52,81],"relative":[55],"usefulness":[56],"of":[57,61,99,110,131,159,174,198],"experimental":[58],"error,":[59],"distribution":[60,98],"activities,":[63],"cliff":[66,117],"metrics":[67,118,125,140],"determining":[69],"how":[70],"dataset":[73],"likely":[75],"be.":[77],"We":[78,113,153],"include":[79,106],"unmodified":[80],"datasets,":[82],"should":[85],"be":[86],"perfectly":[87],"based":[89],"only":[90],"chemical":[93,199],"structure,":[94],"where":[96],"activities":[100,173],"manipulated,":[102],"known":[108],"amount":[109],"added":[111],"noise.":[112],"find":[114],"determine":[119],"better":[121],"than":[122],"other":[124],"investigated,":[127],"whatever":[128],"type":[130],"dataset,":[132],"consistent":[133,179],"with":[134,180,190],"literature.":[137],"However,":[138],"such":[139],"cannot":[141],"distinguish":[142],"real":[143],"cliffs":[145,212],"large":[148],"uncertainties":[149],"activities.":[152],"also":[154],"show":[155,194],"number":[158],"modern":[160],"methods,":[162],"alternative":[165],"descriptors,":[166],"equally":[168],"bad":[169],"at":[170,202],"predicting":[171],"compounds":[175],"cliffs,":[178],"assumptions":[182],"behind":[183],"\"modelability.\"":[184],"Finally,":[185],"relate":[187],"time-split":[188],"different":[196],"coverages":[197],"space":[200],"least":[203],"as":[204,206],"important":[205],"uncertainty":[207],"and/or":[210],"predictivity.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
