{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:09:04Z","timestamp":1789996144000,"version":"4.0.1"},"reference-count":115,"publisher":"American Chemical Society (ACS)","issue":"9","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/na","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2022YFC3902100"],"award-info":[{"award-number":["2022YFC3902100"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["22136001"],"award-info":[{"award-number":["22136001"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Evaluating chemical hazards, such as cardiotoxicity, is critical for sound chemical management but is challenging due to the labor-intensive and time-consuming nature of in vivo testing. In silico models can efficiently and cost-effectively screen potential cardiotoxic compounds from a large number of chemicals. However, the available small-scale in vivo toxicity data sets prevent models from achieving superior prediction accuracy. Herein, a transfer learning-based graph neural network (TL-GNN) model for predicting in vivo cardiotoxicity was developed by fine-tuning from a pretrained model on a data set regarding the human ether-a-go-go-related gene binding, a molecular initiating event that may ultimately cause cardiotoxicity. The TL-GNN model not only outperformed the GNN without TL and classic machine learning models, but also those fine-tuned from GNN models pretrained on a nonmechanistic octanol\u2013water partition coefficient data set and Bidirectional Encoder Representations from Transformers models pretrained on a data set with over a million unlabeled compounds. A structure\u2013activity landscape-based method was adopted to characterize the applicability domains of the TL-GNN model. The TL-GNN model with defined applicability domains was applied to screen approximately 600,000 chemicals across diverse categories, identifying over 25,000 as cardiotoxic. The robustness of the TL-GNN model suggests the potential of the modeling strategy for complex in vivo toxicity by learning from adverse outcome pathway (AOP)-related in vitro targets.<\/jats:p>","DOI":"10.1021\/acs.chemrestox.6c00190","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:01:57Z","timestamp":1786618917000},"page":"1787-1800","source":"Crossref","is-referenced-by-count":0,"title":["Transfer\nLearning Empowers the Development of Better-Performing\nModels for\n                    <i>In Vivo<\/i>\n                    Cardiotoxicity by Learning from\n                    <i>In Vitro<\/i>\n                    hERG Binding Data"],"prefix":"10.1021","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2182-4623","authenticated-orcid":true,"given":"Yuxuan","family":"Zhang","sequence":"first","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3786-4499","authenticated-orcid":true,"given":"Yuwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9268-1144","authenticated-orcid":true,"given":"Guijia","family":"Bi","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5756-3336","authenticated-orcid":true,"given":"Jingwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Dalian University of Technology , , ,","place":["Dalian, China, 116024"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"issue":"6","key":"2026092108065071400_cit1","doi-asserted-by":"publisher","first-page":"e535","DOI":"10.1016\/S2542-5196(22)00090-0","article-title":"Pollution and Health:\nA Progress Update","volume":"6","author":"Fuller","year":"2022","journal-title":"Lancet Planet. Health"},{"key":"2026092108065071400_cit2","unstructured":"Cardiovascular\ndiseases (CVDs); https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds) (accessed 2023\u201309\u201318)."},{"issue":"1","key":"2026092108065071400_cit3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s12916-016-0553-2","article-title":"Post-Marketing Withdrawal of 462\nMedicinal Products Because of Adverse Drug Reactions: A Systematic\nReview of the World Literature","volume":"14","author":"Onakpoya","year":"2016","journal-title":"BMC Med."},{"issue":"3","key":"2026092108065071400_cit4","doi-asserted-by":"publisher","first-page":"100216","DOI":"10.1016\/j.xcrm.2021.100216","article-title":"Toward a Broader View of Mechanisms\nof Drug Cardiotoxicity","volume":"2","author":"Mamoshina","year":"2021","journal-title":"Cell Rep. Med."},{"issue":"2","key":"2026092108065071400_cit5","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1021\/acs.chemrestox.0c00382","article-title":"High-Throughput\nScreening to Identify\nChemical Cardiotoxic Potential","volume":"34","author":"Krishna","year":"2021","journal-title":"Chem. Res. Toxicol."},{"issue":"2","key":"2026092108065071400_cit6","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s12012-018-9486-7","article-title":"Cardiotoxicity\nof Pesticides: Are Africans at Risk?","volume":"19","author":"Anakwue","year":"2019","journal-title":"Cardiovasc.\nToxicol."},{"issue":"1","key":"2026092108065071400_cit7","doi-asserted-by":"publisher","first-page":"9426","DOI":"10.1038\/s41598-017-09956-x","article-title":"Early Markers of Cardiovascular Disease\nAre Associated with Occupational Exposure to Polycyclic Aromatic Hydrocarbons","volume":"7","author":"Alhamdow","year":"2017","journal-title":"Sci. Rep."},{"key":"2026092108065071400_cit8","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1016\/j.chemosphere.2019.02.115","article-title":"Cardiovascular Toxicity of Decabrominated\nDiphenyl\nEthers (BDE-209) and Decabromodiphenyl Ethane (DBDPE) in Rats","volume":"223","author":"Jing","year":"2019","journal-title":"Chemosphere"},{"issue":"7","key":"2026092108065071400_cit9","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1038\/nrd.2015.34","article-title":"Evolution\nof Strategies to Improve\nPreclinical Cardiac Safety Testing","volume":"15","author":"Gintant","year":"2016","journal-title":"Nat. Rev.\nDrug Discovery"},{"issue":"4","key":"2026092108065071400_cit10","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1111\/bph.12979","article-title":"Physiological, pharmacological\nand toxicological considerations of drug-induced structural cardiac\ninjury","volume":"172","author":"Cross","year":"2015","journal-title":"Br. J. Pharmacol."},{"issue":"10","key":"2026092108065071400_cit11","doi-asserted-by":"publisher","first-page":"e75","DOI":"10.1161\/RES.0000000000000291","article-title":"Use of Human Induced\nPluripotent Stem Cell\u2013Derived Cardiomyocytes in Preclinical\nCancer Drug Cardiotoxicity Testing: A Scientific Statement From the\nAmerican Heart Association","volume":"125","author":"Gintant","year":"2019","journal-title":"Circ. Res."},{"issue":"9","key":"2026092108065071400_cit12","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1002\/jat.3611","article-title":"Moving beyond the Comprehensive in Vitro Proarrhythmia Assay: Use of Human-Induced Pluripotent Stem Cell-Derived\nCardiomyocytes to Assess Contractile Effects Associated with Drug-Induced\nStructural Cardiotoxicity","volume":"38","author":"Yang","year":"2018","journal-title":"J. Appl. Toxicol."},{"key":"2026092108065071400_cit13","doi-asserted-by":"publisher","first-page":"100188","DOI":"10.1016\/j.comtox.2021.100188","article-title":"In Silico Approaches\nin Organ Toxicity Hazard Assessment: Current Status and Future Needs\nfor Predicting Heart, Kidney and Lung Toxicities","volume":"20","author":"Bassan","year":"2021","journal-title":"Comput. Toxicol."},{"issue":"5","key":"2026092108065071400_cit14","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1021\/acs.est.9b06379","article-title":"Toward a Global\nUnderstanding of Chemical Pollution: A First Comprehensive Analysis\nof National and Regional Chemical Inventories","volume":"54","author":"Wang","year":"2020","journal-title":"Environ. Sci. Technol."},{"issue":"11","key":"2026092108065071400_cit15","doi-asserted-by":"publisher","first-page":"3525","DOI":"10.1039\/D0CS00098A","article-title":"QSAR without Borders","volume":"49","author":"Muratov","year":"2020","journal-title":"Chem. Soc.\nRev."},{"issue":"4","key":"2026092108065071400_cit16","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.1021\/acs.est.1c06157","article-title":"Data-Driven\nMachine Learning in Environmental Pollution: Gains and Problems","volume":"56","author":"Liu","year":"2022","journal-title":"Environ. Sci. Technol."},{"issue":"46","key":"2026092108065071400_cit17","doi-asserted-by":"publisher","first-page":"17690","DOI":"10.1021\/acs.est.3c00653","article-title":"Advancing\nComputational Toxicology\nby Interpretable Machine Learning","volume":"57","author":"Jia","year":"2023","journal-title":"Environ.\nSci. Technol."},{"issue":"9","key":"2026092108065071400_cit18","doi-asserted-by":"publisher","first-page":"2628","DOI":"10.1021\/acs.jcim.3c00200","article-title":"Artificial Intelligence\nin Drug Toxicity Prediction: Recent Advances, Challenges, and Future\nPerspectives","volume":"63","author":"Tran","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"2026092108065071400_cit19","doi-asserted-by":"publisher","first-page":"116250","DOI":"10.1016\/j.taap.2022.116250","article-title":"Prediction\nof Drug-Induced Liver\nInjury and Cardiotoxicity Using Chemical Structure and in Vitro Assay Data","volume":"454","author":"Ye","year":"2022","journal-title":"Toxicol. Appl. Pharmacol."},{"issue":"3","key":"2026092108065071400_cit20","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1021\/acs.chemrestox.9b00305","article-title":"Predictive Models\nfor Human Organ Toxicity Based on In Vitro Bioactivity\nData and Chemical Structure","volume":"33","author":"Xu","year":"2020","journal-title":"Chem. Res. Toxicol."},{"issue":"4","key":"2026092108065071400_cit21","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1021\/acs.chemrestox.4c00428","article-title":"DICTrank is a Reliable\nDataset for Cardiotoxicity Prediction Using Machine Learning Methods","volume":"38","author":"Qu","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"4","key":"2026092108065071400_cit22","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1021\/acs.jcim.3c01834","article-title":"Insights\ninto Drug Cardiotoxicity from Biological and Chemical Data: The First\nPublic Classifiers for FDA Drug-Induced Cardiotoxicity Rank","volume":"64","author":"Seal","year":"2024","journal-title":"J. Chem. Inf. Model."},{"issue":"7","key":"2026092108065071400_cit23","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1021\/acs.chemrestox.2c00411","article-title":"In Silico Prediction of Human Organ Toxicity via\nArtificial Intelligence Methods","volume":"36","author":"Hu","year":"2023","journal-title":"Chem. Res.\nToxicol."},{"issue":"3","key":"2026092108065071400_cit24","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1002\/etc.34","article-title":"Adverse\nOutcome Pathways: A Conceptual Framework to Support Ecotoxicology\nResearch and Risk Assessment","volume":"29","author":"Ankley","year":"2009","journal-title":"Environ. Toxicol.\nChem."},{"issue":"7083","key":"2026092108065071400_cit25","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/nature04710","article-title":"hERG Potassium Channels and Cardiac Arrhythmia","volume":"440","author":"Sanguinetti","year":"2006","journal-title":"Nature"},{"issue":"9","key":"2026092108065071400_cit26","doi-asserted-by":"publisher","first-page":"095001","DOI":"10.1289\/EHP9321","article-title":"Key Characteristics of Cardiovascular\nToxicants","volume":"129","author":"Lind","year":"2021","journal-title":"Environ. Health Perspect."},{"issue":"3","key":"2026092108065071400_cit27","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1080\/03602530600632063","article-title":"The Role of Aryl\nHydrocarbon Receptor in the Pathogenesis\nof Cardiovascular Diseases","volume":"38","author":"Korashy","year":"2006","journal-title":"Drug Metab. Rev."},{"issue":"3","key":"2026092108065071400_cit28","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1517\/14740338.4.3.509","article-title":"ICH S7B Draft Guideline on the Non-Clinical Strategy for Testing\nDelayed Cardiac Repolarisation Risk of Drugs: A Critical Analysis","volume":"4","author":"Cavero","year":"2005","journal-title":"Expert Opin. Drug Saf."},{"issue":"9","key":"2026092108065071400_cit29","doi-asserted-by":"publisher","first-page":"1460","DOI":"10.1021\/acs.chemrestox.5c00065","article-title":"Enlarged Datasets\nand Innovative Applicability Domain Characterization Empower ML Models\nto Reliably Bridge hERG Binding Data Gaps in Diverse Chemicals","volume":"38","author":"Zhang","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"31","key":"2026092108065071400_cit30","doi-asserted-by":"publisher","DOI":"10.1002\/slct.202201221","article-title":"A Review of Computational\nMethods in Predicting hERG Channel Blockers","volume":"7","author":"Shan","year":"2022","journal-title":"ChemistrySelect"},{"key":"2026092108065071400_cit31","doi-asserted-by":"publisher","first-page":"966261","DOI":"10.3389\/fcvm.2022.966261","article-title":"Pharmacogenomics\nin Drug-Induced\nCardiotoxicity: Current Status and the Future","volume":"9","author":"Li","year":"2022","journal-title":"Front. Cardiovasc. Med."},{"issue":"2\u20134","key":"2026092108065071400_cit32","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1080\/10937404.2010.483940","article-title":"Biokinetic\nModeling and in Vitro\u2013in Vivo Extrapolations","volume":"13","author":"Blaauboer","year":"2010","journal-title":"J. Toxicol. Environ. Health, Part B"},{"key":"2026092108065071400_cit33","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/B978-0-443-15339-6.00034-5","article-title":"Chapter 37 - In Vitro to in Vivo Extrapolation\nMethods\nin Chemical Hazard Identification and Risk Assessment","volume-title":"QSAR in Safety Evaluation and Risk Assessment","author":"Zhang","year":"2023"},{"issue":"5","key":"2026092108065071400_cit34","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1021\/acs.chemrestox.5c00033","article-title":"Machine Learning for Toxicity Prediction\nUsing Chemical Structures: Pillars for Success in the Real World","volume":"38","author":"Seal","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"23","key":"2026092108065071400_cit35","doi-asserted-by":"publisher","first-page":"5601","DOI":"10.1021\/jm049509l","article-title":"Application of ALOGPS\n2.1 to Predict Log D Distribution Coefficient for\nPfizer Proprietary Compounds","volume":"47","author":"Tetko","year":"2004","journal-title":"J. Med. Chem."},{"issue":"3","key":"2026092108065071400_cit36","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1021\/ci010379o","article-title":"Neural\nNetwork Studies. 4. Introduction to Associative Neural Networks","volume":"42","author":"Tetko","year":"2002","journal-title":"J. Chem. Inf. Comput. Sci."},{"issue":"7","key":"2026092108065071400_cit37","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1016\/j.jinorgbio.2007.12.029","article-title":"Calculation\nof Lipophilicity for Pt(II) Complexes: Experimental Comparison of\nSeveral Methods","volume":"102","author":"Tetko","year":"2008","journal-title":"J. Inorg. Biochem."},{"issue":"10","key":"2026092108065071400_cit38","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on\nTransfer Learning |","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans.\nKnowl. Data Eng."},{"issue":"16","key":"2026092108065071400_cit39","doi-asserted-by":"publisher","first-page":"8683","DOI":"10.1021\/acs.jmedchem.9b02147","article-title":"Transfer Learning\nfor Drug Discovery","volume":"63","author":"Cai","year":"2020","journal-title":"J. Med. Chem."},{"issue":"35","key":"2026092108065071400_cit40","doi-asserted-by":"publisher","first-page":"15650","DOI":"10.1021\/acs.est.4c02421","article-title":"Integrated Transfer\nLearning and Multitask Learning Strategies to Construct Graph Neural\nNetwork Models for Predicting Bioaccumulation Parameters of Chemicals","volume":"58","author":"Xiao","year":"2024","journal-title":"Environ. Sci. Technol."},{"issue":"6","key":"2026092108065071400_cit41","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1021\/acs.chemrestox.4c00192","article-title":"Tox24 Challenge","volume":"37","author":"Tetko","year":"2024","journal-title":"Chem. Res. Toxicol."},{"issue":"9","key":"2026092108065071400_cit42","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1021\/acs.chemrestox.5c00273","article-title":"Which Modern AI\nMethods Provide Accurate Predictions\nof Toxicological End Points? Analysis of Tox24 Challenge Results","volume":"38","author":"Eytcheson","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"6","key":"2026092108065071400_cit43","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1021\/acs.chemrestox.5c00018","article-title":"Consensus Modeling Strategies for Predicting Transthyretin\nBinding Affinity from Tox24 Challenge Data","volume":"38","author":"Cirino","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"6","key":"2026092108065071400_cit44","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1021\/acs.chemrestox.3c00074","article-title":"Machine Learning\nModel for Screening Thyroid Stimulating Hormone Receptor Agonists\nBased on Updated Datasets and Improved Applicability Domain Metrics","volume":"36","author":"Liu","year":"2023","journal-title":"Chem. Res. Toxicol."},{"key":"2026092108065071400_cit45","volume-title":"OECD Guidance document on the validation of (quantitative)\nstructure\nactivity relationships (Q)SAR models, Technical Report for OECD Environment\nHealth and Safety Publications Series on Testing and Assessment No.\n69","year":"2007"},{"issue":"6","key":"2026092108065071400_cit46","doi-asserted-by":"publisher","first-page":"1382","DOI":"10.1021\/acs.chemrestox.9b00498","article-title":"Applicability\nDomains Enhance Application\nof PPAR\u03b3 Agonist Classifiers Trained by Drug-like Compounds\nto Environmental Chemicals","volume":"33","author":"Wang","year":"2020","journal-title":"Chem. Res. Toxicol."},{"issue":"2","key":"2026092108065071400_cit47","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1021\/acs.chemrestox.0c00305","article-title":"Systematic\nIdentification of Molecular Targets and Pathways Related to Human\nOrgan Level Toxicity","volume":"34","author":"Xu","year":"2021","journal-title":"Chem. Res. Toxicol."},{"issue":"11","key":"2026092108065071400_cit48","doi-asserted-by":"publisher","first-page":"103770","DOI":"10.1016\/j.drudis.2023.103770","article-title":"DICTrank: The Largest\nReference List of 1318 Human Drugs Ranked by Risk of Drug-Induced\nCardiotoxicity Using FDA Labeling","volume":"28","author":"Qu","year":"2023","journal-title":"Drug Discovery\nToday"},{"issue":"D1","key":"2026092108065071400_cit49","doi-asserted-by":"publisher","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The SIDER Database\nof Drugs and Side Effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res."},{"issue":"15","key":"2026092108065071400_cit50","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1021\/jm9602928","article-title":"The Properties of Known Drugs. 1 Molecular Frameworks","volume":"39","author":"Bemis","year":"1996","journal-title":"J. Med. Chem."},{"issue":"16","key":"2026092108065071400_cit51","doi-asserted-by":"publisher","first-page":"5035","DOI":"10.1021\/acs.jcim.3c00554","article-title":"Evaluating the Use\nof Graph Neural Networks and Transfer\nLearning for Oral Bioavailability Prediction","volume":"63","author":"Ng","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"2026092108065071400_cit52","unstructured":"Landrum, G.\n          \n          RDKit: Open-source cheminformatics; https:\/\/rdkit.org\/ (accessed\n2023\u201309\u201321)."},{"key":"2026092108065071400_cit53","unstructured":"Ramsundar, B.; Eastman, P.; Eastman, P.; Pande, V.\n          Deep Learning for the Life Sciences; https:\/\/www.oreilly.com\/library\/view\/deep-learning-for\/9781492039822\/ (accessed 2025\u201302\u201321)."},{"issue":"9","key":"2026092108065071400_cit54","doi-asserted-by":"publisher","first-page":"4518","DOI":"10.1021\/acs.est.4c12247","article-title":"Predicting Toxicity toward Nitrifiers\nby Attention-Enhanced Graph Neural Networks and Transfer Learning\nfrom Baseline Toxicity","volume":"59","author":"Zhang","year":"2025","journal-title":"Environ. Sci. Technol."},{"issue":"9","key":"2026092108065071400_cit55","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1021\/tx200211v","article-title":"Improving\nDrug Candidates by Design: A Focus on Physicochemical Properties as\na Means of Improving Compound Disposition and Safety","volume":"24","author":"Meanwell","year":"2011","journal-title":"Chem. Res. Toxicol."},{"issue":"1","key":"2026092108065071400_cit56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42004-021-00528-9","article-title":"Exploring\nthe Octanol\u2013Water\nPartition Coefficient Dataset Using Deep Learning Techniques and Data\nAugmentation","volume":"4","author":"Ulrich","year":"2021","journal-title":"Commun. Chem."},{"issue":"17","key":"2026092108065071400_cit57","doi-asserted-by":"publisher","first-page":"4872","DOI":"10.1016\/j.bmcl.2008.07.071","article-title":"Physiochemical\nDrug Properties Associated with in Vivo Toxicological\nOutcomes","volume":"18","author":"Hughes","year":"2008","journal-title":"Bioorg. Med. Chem. Lett."},{"key":"2026092108065071400_cit58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.15853","article-title":"Understanding and Improving Early\nStopping for Learning with Noisy Labels","author":"Bai","year":"2021","journal-title":"arXiv"},{"key":"2026092108065071400_cit59","volume-title":"Automatic Differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"2026092108065071400_cit60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.10902","article-title":"Optuna: A Next-Generation Hyperparameter\nOptimization Framework","author":"Akiba","year":"2019","journal-title":"arXiv"},{"issue":"16","key":"2026092108065071400_cit61","doi-asserted-by":"publisher","first-page":"6410","DOI":"10.1021\/acs.jcim.4c01102","article-title":"Semisupervised\nLearning to Boost\nhERG, Nav1.5, and Cav1.2 Cardiac Ion Channel Toxicity Prediction by\nMining a Large Unlabeled Small Molecule Data Set","volume":"64","author":"Arab","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026092108065071400_cit62","doi-asserted-by":"publisher","first-page":"7181815","DOI":"10.1155\/2021\/7181815","article-title":"Mol-BERT: An Effective\nMolecular Representation with\nBERT for Molecular Property Prediction","volume":"2021","author":"Li","year":"2021","journal-title":"Wirel.\nCommun. Mob. Comput."},{"key":"2026092108065071400_cit63","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4","article-title":"Uni-Mol: A Universal 3D Molecular\nRepresentation Learning Framework","author":"Zhou","year":"2023","journal-title":"ChemRxiv"},{"issue":"D1","key":"2026092108065071400_cit64","doi-asserted-by":"publisher","first-page":"D930","DOI":"10.1093\/nar\/gky1075","article-title":"ChEMBL:\nTowards\nDirect Deposition of Bioassay Data","volume":"47","author":"Mendez","year":"2019","journal-title":"Nucleic\nAcids Res."},{"issue":"1","key":"2026092108065071400_cit65","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1021\/ci050457y","article-title":"ErG: 2D Pharmacophore\nDescriptions for Scaffold Hopping","volume":"46","author":"Stiefl","year":"2006","journal-title":"J. Chem.\nInf. Model."},{"issue":"5","key":"2026092108065071400_cit66","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity\nFingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"issue":"1","key":"2026092108065071400_cit67","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s13321-018-0258-y","article-title":"Mordred: A Molecular\nDescriptor Calculator","volume":"10","author":"Moriwaki","year":"2018","journal-title":"J. Cheminf."},{"issue":"1","key":"2026092108065071400_cit68","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1061\/(ASCE)1084-0699(2007)12:1(42)","article-title":"Improved K-Nearest\nNeighbor Weather Generating Model","volume":"12","author":"Sharif","year":"2007","journal-title":"J. Hydrol.\nEng."},{"issue":"3","key":"2026092108065071400_cit69","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-Vector Networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach.\nLearn."},{"key":"2026092108065071400_cit70","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: A Scalable\nTree Boosting System","author":"Chen","year":"2016","journal-title":"arXiv"},{"issue":"10","key":"2026092108065071400_cit71","doi-asserted-by":"publisher","first-page":"6857","DOI":"10.1021\/acs.est.0c07040","article-title":"Developing QSAR Models with Defined\nApplicability Domains on PPAR\u03b3 Binding Affinity Using Large\nData Sets and Machine Learning Algorithms","volume":"55","author":"Wang","year":"2021","journal-title":"Environ.\nSci. Technol."},{"key":"2026092108065071400_cit72","first-page":"2825","article-title":"Scikit-Learn: machine\nLearning In Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"issue":"44","key":"2026092108065071400_cit73","doi-asserted-by":"publisher","first-page":"16906","DOI":"10.1021\/acs.est.3c03860","article-title":"Applicability Domains\nBased on Molecular Graph Contrastive Learning Enable Graph Attention\nNetwork Models to Accurately Predict 15 Environmental End Points","volume":"57","author":"Wang","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"2026092108065071400_cit74","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2009.00909","article-title":"A Survey on Negative Transfer","author":"Zhang","year":"2020","journal-title":"arXiv"},{"issue":"1","key":"2026092108065071400_cit75","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1038\/s41467-025-58687-5","article-title":"Transfer Learning\nacross Different Photocatalytic Organic Reactions","volume":"16","author":"Noto","year":"2025","journal-title":"Nat. Commun."},{"issue":"10","key":"2026092108065071400_cit76","doi-asserted-by":"publisher","first-page":"4031","DOI":"10.1021\/acs.jcim.4c00160","article-title":"Quantifying\nthe Hardness of Bioactivity\nPrediction Tasks for Transfer Learning","volume":"64","author":"Fooladi","year":"2024","journal-title":"J. Chem.\nInf. Model."},{"key":"2026092108065071400_cit77","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1038\/s41597-026-07357-2","article-title":"SangsterLogP - the Largest Publicly Available Dataset\nof logP Values","volume":"13","author":"Cirino","year":"2026","journal-title":"Sci. Data"},{"key":"2026092108065071400_cit78","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"BERT: Pre-Training of Deep\nBidirectional Transformers for Language Understanding","author":"Devlin","year":"2018","journal-title":"arXiv"},{"issue":"8","key":"2026092108065071400_cit79","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1021\/acs.chemrestox.4c00015","article-title":"Improved Detection of Drug-Induced\nLiver Injury by Integrating Predicted In Vivo and In Vitro Data","volume":"37","author":"Seal","year":"2024","journal-title":"Chem. Res. Toxicol."},{"issue":"4","key":"2026092108065071400_cit80","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1021\/acs.chemrestox.4c00453","article-title":"Predicting Liver-Related In Vitro Endpoints\nwith Machine Learning to Support Early Detection of Drug-Induced Liver\nInjury","volume":"38","author":"Garcia de Lomana","year":"2025","journal-title":"Chem. Res. Toxicol."},{"issue":"1","key":"2026092108065071400_cit81","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could Graph Neural\nNetworks Learn Better Molecular\nRepresentation for Drug Discovery? A Comparison Study of Descriptor-Based\nand Graph-Based Models","volume":"13","author":"Jiang","year":"2021","journal-title":"J. Cheminf."},{"issue":"16","key":"2026092108065071400_cit82","doi-asserted-by":"publisher","first-page":"8705","DOI":"10.1021\/acs.jmedchem.0c00385","article-title":"Learning\nMolecular Representations\nfor Medicinal Chemistry","volume":"63","author":"Chuang","year":"2020","journal-title":"J. Med. Chem."},{"issue":"13","key":"2026092108065071400_cit83","doi-asserted-by":"publisher","first-page":"8736","DOI":"10.1021\/acs.chemrev.3c00189","article-title":"Machine\nLearning Methods for Small Data Challenges\nin Molecular Science","volume":"123","author":"Dou","year":"2023","journal-title":"Chem. Rev."},{"issue":"12","key":"2026092108065071400_cit84","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1038\/s41551-022-00898-y","article-title":"Shifting Machine\nLearning for Healthcare from Development to Deployment and from Models\nto Data","volume":"6","author":"Zhang","year":"2022","journal-title":"Nat. Biomed. Eng."},{"key":"2026092108065071400_cit85","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1903.03894","article-title":"GNNExplainer: Generating Explanations\nfor Graph Neural Networks","author":"Ying","year":"2019","journal-title":"arXiv"},{"issue":"15","key":"2026092108065071400_cit86","doi-asserted-by":"publisher","first-page":"11542","DOI":"10.1021\/acs.est.5c16775","article-title":"Counted Fingerprint-Enhanced\nGraph Neural Network Models Enable Accurate Screening of hERG Blockers\nfrom Diverse Categories of Chemicals","volume":"60","author":"Zhang","year":"2026","journal-title":"Environ.\nSci. Technol."},{"issue":"15","key":"2026092108065071400_cit87","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.1021\/acs.jcim.3c00365","article-title":"DCABM-TCM:\nA Database of Constituents Absorbed into the Blood and Metabolites\nof Traditional Chinese Medicine","volume":"63","author":"Liu","year":"2023","journal-title":"J. Chem. Inf.\nModel."},{"issue":"D1","key":"2026092108065071400_cit88","doi-asserted-by":"publisher","first-page":"D1276","DOI":"10.1093\/nar\/gkac1085","article-title":"DrugCentral 2023\nExtends Human Clinical\nData and Integrates Veterinary Drugs","volume":"51","author":"Avram","year":"2023","journal-title":"Nucleic\nAcids Res."},{"issue":"1","key":"2026092108065071400_cit89","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13321-020-00478-9","article-title":"COCONUT Online:\nCollection of Open Natural Products Database","volume":"13","author":"Sorokina","year":"2021","journal-title":"J. Cheminf."},{"issue":"3","key":"2026092108065071400_cit90","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1254\/jphs.08102FP","article-title":"Molecular\nDeterminants of hERG Channel Block by Terfenadine and Cisapride","volume":"108","author":"Kamiya","year":"2008","journal-title":"J. Pharmacol. Sci."},{"issue":"4","key":"2026092108065071400_cit91","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1007\/BF02980219","article-title":"Maprotiline\nBlock of the Human Ether-a-Go-Go-Related Gene (HERG)\nK+ Channel","volume":"30","author":"Jo","year":"2007","journal-title":"Arch. Pharm. Res."},{"issue":"3","key":"2026092108065071400_cit92","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1056\/NEJMoa0806994","article-title":"Atypical\nAntipsychotic Drugs and the Risk of Sudden Cardiac Death","volume":"360","author":"Ray","year":"2009","journal-title":"N. Engl. J. Med."},{"key":"2026092108065071400_cit93","doi-asserted-by":"publisher","first-page":"115225","DOI":"10.1016\/j.ecoenv.2023.115225","article-title":"Additive\nCardiotoxicity of a Bisphenol\nMixture in Zebrafish Embryos: The Involvement of Calcium Channel and\nPump","volume":"263","author":"Arrokhman","year":"2023","journal-title":"Ecotoxicol. Environ. Saf."},{"issue":"5","key":"2026092108065071400_cit94","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1177\/009286150804200501","article-title":"VigiBase,\nthe WHO Global ICSR Database System: Basic Facts","volume":"42","author":"Lindquist","year":"2008","journal-title":"Drug Inf. J. DIJ. Drug Inf. Assoc."},{"key":"2026092108065071400_cit95","doi-asserted-by":"publisher","first-page":"1472008","DOI":"10.3389\/fphar.2024.1472008","article-title":"Cardiovascular Toxicity\nRisk Assessment of Tyrosine Kinase Inhibitors: A Pharmacovigilance\nStudy Using the VigiBase Database","volume":"15","author":"Igawa","year":"2024","journal-title":"Front. Pharmacol."},{"issue":"6476","key":"2026092108065071400_cit96","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1126\/science.aay6637","article-title":"Learning from the Past and Considering\nthe Future of Chemicals in the Environment","volume":"367","author":"Johnson","year":"2020","journal-title":"Science"},{"issue":"1","key":"2026092108065071400_cit97","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/s13321-016-0174-y","article-title":"ClassyFire: Automated\nChemical Classification with a Comprehensive, Computable Taxonomy","volume":"8","author":"Feunang","year":"2016","journal-title":"J. Cheminf."},{"issue":"3","key":"2026092108065071400_cit98","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.taap.2011.02.016","article-title":"Identification\nof Quaternary Ammonium\nCompounds as Potent Inhibitors of hERG Potassium Channels","volume":"252","author":"Xia","year":"2011","journal-title":"Toxicol. Appl. Pharmacol."},{"key":"2026092108065071400_cit99","doi-asserted-by":"publisher","first-page":"138562","DOI":"10.1016\/j.chemosphere.2023.138562","article-title":"Proarrhythmic Toxicity\nof Low Dose Bisphenol A and Its Analogs in Human iPSC-Derived Cardiomyocytes\nand Human Cardiac Organoids through Delay of Cardiac Repolarization","volume":"328","author":"Ma","year":"2023","journal-title":"Chemosphere"},{"key":"2026092108065071400_cit100","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.3389\/fphar.2018.01035","article-title":"Experimentally Validated\nPharmacoinformatics Approach to Predict hERG Inhibition Potential\nof New Chemical Entities","volume":"9","author":"Munawar","year":"2018","journal-title":"Front. Pharmacol."},{"issue":"9","key":"2026092108065071400_cit101","doi-asserted-by":"publisher","first-page":"3160","DOI":"10.1016\/j.bmc.2005.12.032","article-title":"New Insights\nabout HERG Blockade Obtained from Protein Modeling, Potential Energy\nMapping, and Docking Studies","volume":"14","author":"Farid","year":"2006","journal-title":"Bioorg. Med. Chem."},{"issue":"5","key":"2026092108065071400_cit102","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1021\/acs.jcim.4c01371","article-title":"Large Language Models\nas Tools for Molecular Toxicity\nPrediction: AI Insights into Cardiotoxicity","volume":"65","author":"Yang","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"11","key":"2026092108065071400_cit103","doi-asserted-by":"publisher","first-page":"10120","DOI":"10.1074\/jbc.M310683200","article-title":"Physicochemical\nFeatures of the hERG Channel Drug Binding Site","volume":"279","author":"Fernandez","year":"2004","journal-title":"J. Biol. Chem."},{"issue":"10","key":"2026092108065071400_cit104","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1016\/j.tips.2017.06.004","article-title":"Towards\na Structural\nView of Drug Binding to hERG K+ Channels","volume":"38","author":"Vandenberg","year":"2017","journal-title":"Trends Pharmacol. Sci."},{"issue":"4","key":"2026092108065071400_cit105","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1038\/bjp.2008.287","article-title":"Interaction\nwith the hERG Channel and Cytotoxicity of Amiodarone and Amiodarone\nAnalogues","volume":"155","author":"Waldhauser","year":"2008","journal-title":"Br. J. Pharmacol."},{"issue":"7378","key":"2026092108065071400_cit106","doi-asserted-by":"publisher","first-page":"S82","DOI":"10.1038\/480S82a","article-title":"TCM: Made in China","volume":"480","author":"Cheung","year":"2011","journal-title":"Nature"},{"issue":"1","key":"2026092108065071400_cit107","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13020-023-00741-9","article-title":"Machine Learning in TCM with Natural Products and Molecules:\nCurrent\nStatus and Future Perspectives","volume":"18","author":"Ma","year":"2023","journal-title":"Chin. Med."},{"key":"2026092108065071400_cit108","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.toxlet.2024.05.001","article-title":"Matrine Induces Cardiotoxicity\nby Promoting Ferroptosis\nthrough the Nrf2 Antioxidant System in H9c2 Cells","volume":"397","author":"Wang","year":"2024","journal-title":"Toxicol. Lett."},{"issue":"8","key":"2026092108065071400_cit109","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1142\/S0192415X1850091X","article-title":"High-Throughput\nElectrophysiology Screen Revealed Cardiotoxicity of Strychnine by\nSelectively Targeting hERG Channel","volume":"46","author":"Wang","year":"2018","journal-title":"Am. J. Chin.\nMed."},{"key":"2026092108065071400_cit110","doi-asserted-by":"publisher","first-page":"4037","DOI":"10.1007\/978-3-642-22144-6_175","article-title":"Oleoresins from Pine: Production and\nIndustrial Uses","volume-title":"Natural Products: phytochemistry,\nBotany and Metabolism\nof Alkaloids, Phenolics and Terpenes","author":"da Silva Rodrigues-Corre\u0302a","year":"2013"},{"issue":"11","key":"2026092108065071400_cit111","doi-asserted-by":"publisher","first-page":"998","DOI":"10.3390\/toxics13110998","article-title":"From Euphoria to Cardiac Stress: Role of Oxidative\nStress on the Cardiotoxicity of Methylone and 3,4-DMMC","volume":"13","author":"Moreira","year":"2025","journal-title":"Toxics"},{"issue":"7","key":"2026092108065071400_cit112","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.1021\/acs.jcim.2c01393","article-title":"MolTaut: A Tool for the Rapid Generation\nof Favorable Tautomer in Aqueous Solution","volume":"63","author":"Pan","year":"2023","journal-title":"J.\nChem. Inf. Model."},{"issue":"7","key":"2026092108065071400_cit113","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1021\/acs.jcim.1c00075","article-title":"MolGpka: A Web Server for Small Molecule pKa Prediction Using a Graph-Convolutional\nNeural Network","volume":"61","author":"Pan","year":"2021","journal-title":"J. Chem. Inf. Model."},{"issue":"6","key":"2026092108065071400_cit114","doi-asserted-by":"publisher","first-page":"3132","DOI":"10.1021\/acs.jctc.5c00041","article-title":"Fast and\nAccurate Prediction of Tautomer Ratios in Aqueous Solution via a Siamese\nNeural Network","volume":"21","author":"Pan","year":"2025","journal-title":"J. Chem. Theory Comput."},{"issue":"1","key":"2026092108065071400_cit115","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1038\/s41467-024-55082-4","article-title":"Multi-Channel\nLearning for Integrating Structural Hierarchies into Context-Dependent\nMolecular Representation","volume":"16","author":"Wan","year":"2025","journal-title":"Nat. Commun."}],"container-title":["Chemical Research in Toxicology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.chemrestox.6c00190","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/crtoec\/article-pdf\/39\/9\/1787\/66522503\/acs.chemrestox.6c00190.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/crtoec\/article-pdf\/39\/9\/1787\/66522503\/acs.chemrestox.6c00190.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:19:30Z","timestamp":1789993170000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/crtoec\/article\/39\/9\/1787\/5254129\/Transfer-Learning-Empowers-the-Development-of"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":115,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,8,13]]},"published-print":{"date-parts":[[2026,9,21]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.chemrestox.6c00190","relation":{},"ISSN":["0893-228X","1520-5010"],"issn-type":[{"value":"0893-228X","type":"print"},{"value":"1520-5010","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}