{"id":"https://openalex.org/W4410957854","doi":"https://doi.org/10.1021/acs.jcim.5c00538","title":"Data Scaling and Generalization Insights for Medicinal Chemistry Deep Learning Models","display_name":"Data Scaling and Generalization Insights for Medicinal Chemistry Deep Learning Models","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410957854","doi":"https://doi.org/10.1021/acs.jcim.5c00538","pmid":"https://pubmed.ncbi.nlm.nih.gov/40454949"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00538","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00538","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/A5082543970","display_name":"Jacky Chen","orcid":"https://orcid.org/0000-0003-0809-8340"},"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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacky Chen","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062459841","display_name":"Yunsie Chung","orcid":"https://orcid.org/0000-0002-3097-010X"},"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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunsie Chung","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057238172","display_name":"Jonathan Tynan","orcid":"https://orcid.org/0000-0001-6433-4729"},"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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Tynan","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102962382","display_name":"Chen Cheng","orcid":"https://orcid.org/0000-0003-3395-5375"},"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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Cheng","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":"https://orcid.org/0000-0003-3395-5375","affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804132","display_name":"Yang Song","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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I4210105725","display_name":"Medical Decision Modeling (United States)","ror":"https://ror.org/01h42mb65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105725"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alan C. Cheng","raw_affiliation_strings":["Merck & Co., Inc","Modeling & Informatics"],"raw_orcid":"https://orcid.org/0000-0003-3645-172X","affiliations":[{"raw_affiliation_string":"Merck & Co., Inc","institution_ids":["https://openalex.org/I1285764155"]},{"raw_affiliation_string":"Modeling & Informatics","institution_ids":["https://openalex.org/I4210105725"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083026456"],"corresponding_institution_ids":["https://openalex.org/I1285764155","https://openalex.org/I4210105725"],"apc_list":null,"apc_paid":null,"fwci":3.1074,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91992702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"65","issue":"12","first_page":"5887","last_page":"5898"},"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":0.9993000030517578,"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":0.95169997215271,"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/drug-discovery","display_name":"Drug discovery","score":0.717793345451355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7002924680709839},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.675864040851593},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5942868590354919},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5645660161972046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5436933636665344},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4951454699039459},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4618346691131592},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.454652339220047},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.433165967464447},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.41597023606300354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38826462626457214},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.15602612495422363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1157245934009552},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08463522791862488}],"concepts":[{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.717793345451355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002924680709839},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.675864040851593},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5942868590354919},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5645660161972046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436933636665344},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4951454699039459},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4618346691131592},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.454652339220047},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.433165967464447},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.41597023606300354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38826462626457214},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.15602612495422363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1157245934009552},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08463522791862488},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002626","descriptor_name":"Chemistry, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c00538","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00538","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:40454949","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40454949","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/2","display_name":"Zero hunger","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307776","display_name":"Merck","ror":"https://ror.org/02891sr49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2019678805","https://openalex.org/W2060531713","https://openalex.org/W2082903631","https://openalex.org/W2295598076","https://openalex.org/W2556851635","https://openalex.org/W2892573863","https://openalex.org/W2966357564","https://openalex.org/W2995345309","https://openalex.org/W3001279689","https://openalex.org/W3015208165","https://openalex.org/W3096097684","https://openalex.org/W3116202926","https://openalex.org/W3181995918","https://openalex.org/W3198664897","https://openalex.org/W3208713691","https://openalex.org/W3216996162","https://openalex.org/W4283654384","https://openalex.org/W4377232456","https://openalex.org/W4387874094","https://openalex.org/W4390221451","https://openalex.org/W4391014809","https://openalex.org/W4391925761","https://openalex.org/W4398134375","https://openalex.org/W4398223058","https://openalex.org/W4399940463","https://openalex.org/W4400441613","https://openalex.org/W4401398496","https://openalex.org/W4403136288","https://openalex.org/W4404153423"],"related_works":["https://openalex.org/W2973074952","https://openalex.org/W4399416193","https://openalex.org/W4320732452","https://openalex.org/W135095951","https://openalex.org/W4286980196","https://openalex.org/W4385588199","https://openalex.org/W3199987505","https://openalex.org/W4385760073","https://openalex.org/W2600435468","https://openalex.org/W2324927567"],"abstract_inverted_index":{"Predictive":[0],"models":[1,25,89,140],"hold":[2],"considerable":[3],"promise":[4],"in":[5,121,170],"enabling":[6],"the":[7,20,84,119,137],"faster":[8],"discovery":[9,156],"of":[10,22,87,118,139],"safer,":[11],"more":[12,159],"efficacious":[13],"therapeutics.":[14],"To":[15],"better":[16],"understand":[17],"and":[18,36,62,102,127,147],"improve":[19],"performance":[21,58,86,123,138,169],"small-molecule":[23],"predictive":[24,88],"for":[26,141,154,165],"drug":[27,155,171],"discovery,":[28],"we":[29],"conduct":[30],"multiple":[31],"experiments":[32,55],"with":[33],"deep":[34],"learning":[35,39],"traditional":[37,97],"machine":[38],"approaches,":[40],"leveraging":[41],"our":[42],"large":[43],"internal":[44],"data":[45,52,64,128,158],"sets":[46],"as":[47,49,67,69,100,151,153],"well":[48,68,152],"publicly":[50],"available":[51],"sets.":[53],"The":[54,161],"include":[56],"assessing":[57],"on":[59],"random,":[60],"temporal,":[61],"reverse-temporal":[63],"ablation":[65],"tasks":[66,70],"testing":[71],"model":[72,122,168],"extrapolation":[73],"to":[74,83,96,110,135],"different":[75],"property":[76],"spaces.":[77],"We":[78],"identify":[79],"factors":[80],"that":[81,115],"contribute":[82],"higher":[85],"built":[90],"using":[91],"graph":[92],"neural":[93],"networks":[94],"compared":[95],"methods":[98],"such":[99],"XGBoost":[101],"random":[103],"forest.":[104],"These":[105],"insights":[106],"were":[107],"successfully":[108],"used":[109,134],"develop":[111],"a":[112],"scaling":[113],"relationship":[114,131],"explains":[116],"81%":[117],"variance":[120],"across":[124],"various":[125],"assays":[126],"regimes.":[129],"This":[130],"can":[132],"be":[133],"estimate":[136],"ADMET":[142],"(absorption,":[143],"distribution,":[144],"metabolism,":[145],"excretion,":[146],"toxicity)":[148],"end":[149],"points,":[150],"assay":[157],"broadly.":[160],"findings":[162],"offer":[163],"guidance":[164],"further":[166],"improving":[167],"discovery.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}