{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:08:34Z","timestamp":1792692514871,"version":"4.5.0"},"reference-count":53,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["22173065"],"award-info":[{"award-number":["22173065"]}]},{"name":"National Natural Science Foundation of China","award":["21575094"],"award-info":[{"award-number":["21575094"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>The accurate prediction of adverse drug reactions (ADRs) is essential for comprehensive drug safety evaluation. Pre-trained deep chemical language models have emerged as powerful tools capable of automatically learning molecular structural features from large-scale datasets, showing promising capabilities for the downstream prediction of molecular properties. However, the performance of pre-trained chemical language models in predicting ADRs, especially idiosyncratic ADRs induced by marketed drugs, remains largely unexplored. In this study, we propose MoLFormer-XL, a pre-trained model for encoding molecular features from canonical SMILES, in conjunction with a CNN-based model to predict drug-induced QT interval prolongation (DIQT), drug-induced teratogenicity (DIT), and drug-induced rhabdomyolysis (DIR). Our results demonstrate that the proposed model outperforms conventional models applied in previous studies for predicting DIQT, DIT, and DIR. Notably, an analysis of the learned linear attention maps highlights amines, alcohol, ethers, and aromatic halogen compounds as strongly associated with the three types of ADRs. These findings hold promise for enhancing drug discovery pipelines and reducing the drug attrition rate due to safety concerns.<\/jats:p>","DOI":"10.3390\/ijms25084516","type":"journal-article","created":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T07:44:09Z","timestamp":1713771849000},"page":"4516","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Advancing Adverse Drug Reaction Prediction with Deep Chemical Language Model for Drug Safety Evaluation"],"prefix":"10.3390","volume":"25","author":[{"given":"Jinzhu","family":"Lin","sequence":"first","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"He","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengxiang","family":"Ru","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wulin","family":"Long","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglong","family":"Li","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0477-4906","authenticated-orcid":false,"given":"Zhining","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Chemistry, Sichuan University, Chengdu 610064, China"},{"name":"Medical Big Data Center, Sichuan University, Chengdu 610064, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.ymeth.2016.07.023","article-title":"Improving drug safety: From adverse drug reaction knowledge discovery to clinical implementation","volume":"110","author":"Tan","year":"2016","journal-title":"Methods"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1002\/pds.4184","article-title":"Burden of hospitalizations related to adverse drug events in the USA: A retrospective analysis from large inpatient database","volume":"26","author":"Poudel","year":"2017","journal-title":"Pharmacoepidemiol. Drug Saf."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.coph.2012.04.002","article-title":"Drug induced rhabdomyolysis","volume":"12","author":"Hohenegger","year":"2012","journal-title":"Curr. Opin. Pharmacol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1021\/tx400409c","article-title":"Drug-Induced Rhabdomyolysis: From Systems Pharmacology Analysis to Biochemical Flux","volume":"27","author":"Hur","year":"2014","journal-title":"Chem. Res. Toxicol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1007\/s00415-019-09185-4","article-title":"A systematic review on the definition of rhabdomyolysis","volume":"267","author":"Stahl","year":"2019","journal-title":"J. Neurol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.clpt.2004.01.017","article-title":"Postmarketing surveillance for drug safety: Surely we can do better","volume":"75","author":"Griffin","year":"2004","journal-title":"Clin. Pharmacol. Ther."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2042098620938595","DOI":"10.1177\/2042098620938595","article-title":"Post marketing surveillance of suspected adverse drug reactions through spontaneous reporting: Current status, challenges and the future","volume":"11","author":"Alomar","year":"2020","journal-title":"Ther. Adv. Drug Saf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2618","DOI":"10.1021\/acs.jcim.7b00274","article-title":"Interpretation of Quantitative Structure-Activity Relationship Models: Past, Present, and Future","volume":"57","author":"Polishchuk","year":"2017","journal-title":"J. Chem. Inf. Model."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100","DOI":"10.2174\/157488608784529224","article-title":"Advances in machine learning prediction of toxicological properties and adverse drug reactions of pharmaceutical agents","volume":"3","author":"Ma","year":"2008","journal-title":"Curr. Drug Saf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1021\/acs.chemrestox.5b00388","article-title":"Current and Future Perspectives on the Development, Evaluation, and Application of in Silico Approaches for Predicting Toxicity","volume":"29","author":"Patlewicz","year":"2016","journal-title":"Chem. Res. Toxicol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1002\/minf.201500055","article-title":"In silico Prediction of Drug Induced Liver Toxicity Using Substructure Pattern Recognition Method","volume":"35","author":"Zhang","year":"2016","journal-title":"Mol. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"747935","DOI":"10.3389\/fphar.2022.747935","article-title":"Structure-Activity Relationship (SAR) Model for Predicting Teratogenic Risk of Antiseizure Medications in Pregnancy by Using Support Vector Machine","volume":"13","author":"Kang","year":"2022","journal-title":"Front. Pharmacol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Long, W., Li, S., He, Y., Lin, J., Li, M., and Wen, Z. (2023). Unraveling Structural Alerts in Marketed Drugs for Improving Adverse Outcome Pathway Framework of Drug-Induced QT Prolongation. Int. J. Mol. Sci., 24.","DOI":"10.3390\/ijms24076771"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1093\/toxsci\/kfh082","article-title":"Prediction of Torsade-Causing Potential of Drugs by Support Vector Machine Approach No funding was used to assist in conducting the study and the authors do not have any conflicts of interest directly relevant to the contents of the manuscript","volume":"79","author":"Yap","year":"2004","journal-title":"Toxicol. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1093\/toxsci\/kfx099","article-title":"In Silico Prediction of Drug-Induced Liver Injury Based on Adverse Drug Reaction Report","volume":"158","year":"2017","journal-title":"Toxicol. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1021\/acs.chemrestox.0c00347","article-title":"Quantitative Structure\u2013Activity Relationship (QSAR) Model for the Severity Prediction of Drug-Induced Rhabdomyolysis by Using Random Forest","volume":"34","author":"Zhou","year":"2021","journal-title":"Chem. Res. Toxicol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1186\/s12967-019-1918-z","article-title":"Computational models for the prediction of adverse cardiovascular drug reactions","volume":"17","author":"Jamal","year":"2019","journal-title":"J. Transl. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"17311","DOI":"10.1038\/s41598-017-17701-7","article-title":"Development of Decision Forest Models for Prediction of Drug-Induced Liver Injury in Humans Using A Large Set of FDA-approved Drugs","volume":"7","author":"Hong","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1093\/toxsci\/kft189","article-title":"Quantitative Structure-Activity Relationship Models for Predicting Drug-Induced Liver Injury Based on FDA-Approved Drug Labeling Annotation and Using a Large Collection of Drugs","volume":"136","author":"Chen","year":"2013","journal-title":"Toxicol. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2628","DOI":"10.1021\/acs.molpharmaceut.0c00326","article-title":"Comparing Machine Learning Algorithms for Predicting Drug-Induced Liver Injury (DILI)","volume":"17","author":"Minerali","year":"2020","journal-title":"Mol. Pharm."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.yrtph.2009.11.005","article-title":"Prediction of drug-related cardiac adverse effects in humans-B: Use of QSAR programs for early detection of drug-induced cardiac toxicities","volume":"56","author":"Frid","year":"2010","journal-title":"Regul. Toxicol. Pharmacol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1016\/j.drudis.2021.10.009","article-title":"Drug-induced QT Prolongation Atlas (DIQTA) for enhancing cardiotoxicity management","volume":"27","author":"Li","year":"2022","journal-title":"Drug Discov. Today"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.drudis.2018.06.006","article-title":"Drug-Induced Rhabdomyolysis Atlas (DIRA) for idiosyncratic adverse drug reaction management","volume":"24","author":"Wen","year":"2019","journal-title":"Drug Discov. Today"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1884","DOI":"10.1093\/bib\/bbaa040","article-title":"Prediction of drug adverse events using deep learning in pharmaceutical discovery","volume":"22","author":"Lee","year":"2021","journal-title":"Brief. Bioinform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1340860","DOI":"10.3389\/ftox.2023.1340860","article-title":"Computational models for predicting liver toxicity in the deep learning era","volume":"5","author":"Mostafa","year":"2024","journal-title":"Front. Toxicol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules","volume":"4","author":"Wei","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1039\/C8SC04175J","article-title":"Learning continuous and data-driven molecular descriptors by translating equivalent chemical representations","volume":"10","author":"Winter","year":"2019","journal-title":"Chem. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"10378","DOI":"10.1039\/D0SC03115A","article-title":"Neuraldecipher\u2013reverse-engineering extended-connectivity fingerprints (ECFPs) to their molecular structures","volume":"11","author":"Le","year":"2020","journal-title":"Chem. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"14174","DOI":"10.1039\/D1SC01839F","article-title":"Img2Mol\u2013accurate SMILES recognition from molecular graphical depictions","volume":"12","author":"Clevert","year":"2021","journal-title":"Chem. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4","DOI":"10.34133\/research.0004","article-title":"Pushing the Boundaries of Molecular Property Prediction for Drug Discovery with Multitask Learning BERT Enhanced by SMILES Enumeration","volume":"2022","author":"Zhang","year":"2022","journal-title":"Research"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1021\/acs.jcim.0c01127","article-title":"SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning","volume":"61","author":"Li","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wu, C.-K., Wu, C.-K., Zhang, X.-C., Zhang, X.-C., Yang, Z.-J., Yang, Z.-J., Lu, A.-P., Lu, A.-P., Hou, T.-J., and Hou, T.-J. (2021). Learning to SMILES: BAN-based strategies to improve latent representation learning from molecules. Brief. Bioinform., 22.","DOI":"10.1093\/bib\/bbab327"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1186\/s13321-023-00725-9","article-title":"Improving the quality of chemical language model outcomes with atom-in-SMILES tokenization","volume":"15","author":"Ucak","year":"2023","journal-title":"J. Cheminformatics"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale chemical language representations capture molecular structure and properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.vascn.2016.06.002","article-title":"The Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative\u2014Update on progress","volume":"81","author":"Colatsky","year":"2016","journal-title":"J. Pharmacol. Toxicol. Methods"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2310","DOI":"10.1021\/ci300245q","article-title":"ToxAlerts: A Web Server of Structural Alerts for Toxic Chemicals and Compounds with Potential Adverse Reactions","volume":"52","author":"Sushko","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s10822-011-9440-2","article-title":"Online chemical modeling environment (OCHEM): Web platform for data storage, model development and publishing of chemical information","volume":"25","author":"Sushko","year":"2011","journal-title":"J. Comput. Aided Mol. Des."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"379","DOI":"10.2174\/1389200023337360","article-title":"On the Diversity of Oxidative Bioactivation Reactions on Nitrogen- Containing Xenobiotics","volume":"3","author":"Kalgutkar","year":"2002","journal-title":"Curr. Drug Metab."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6276","DOI":"10.1021\/acs.jmedchem.9b00917","article-title":"Designing around Structural Alerts in Drug Discovery","volume":"63","author":"Kalgutkar","year":"2019","journal-title":"J. Med. Chem."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2954","DOI":"10.1021\/jm00114a003","article-title":"Structure-activity studies of antitumor agents based on pyrrolo[1,2-a]benzimidazoles: New reductive alkylating DNA cleaving agents","volume":"34","author":"Islam","year":"1991","journal-title":"J. Med. Chem."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1016\/S1474-4422(11)70107-7","article-title":"Dose-dependent risk of malformations with antiepileptic drugs: An analysis of data from the EURAP epilepsy and pregnancy registry","volume":"10","author":"Tomson","year":"2011","journal-title":"Lancet Neurol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.1212\/WNL.0b013e3182574f39","article-title":"Comparative safety of antiepileptic drugs during pregnancy","volume":"78","author":"Smith","year":"2012","journal-title":"Neurology"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.1136\/jnnp-2013-306318","article-title":"Malformation risks of antiepileptic drug monotherapies in pregnancy: Updated results from the UK and Ireland Epilepsy and Pregnancy Registers","volume":"85","author":"Campbell","year":"2014","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/S1474-4422(18)30107-8","article-title":"Comparative risk of major congenital malformations with eight different antiepileptic drugs: A prospective cohort study of the EURAP registry","volume":"17","author":"Tomson","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"161","DOI":"10.2174\/1389200054021799","article-title":"A comprehensive listing of bioactivation pathways of organic functional groups.pdf","volume":"6","author":"Kalgutkar","year":"2005","journal-title":"Curr. Drug Metab."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s12302-016-0094-5","article-title":"Screening for potential endocrine disruptors in fish: Evidence from structural alerts and in vitro and in vivo toxicological assays","volume":"28","author":"Nendza","year":"2016","journal-title":"Environ. Sci. Eur."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1021\/tx200168d","article-title":"Structural Alert\/Reactive Metabolite Concept as Applied in Medicinal Chemistry to Mitigate the Risk of Idiosyncratic Drug Toxicity: A Perspective Based on the Critical Examination of Trends in the Top 200 Drugs Marketed in the United States","volume":"24","author":"Stepan","year":"2011","journal-title":"Chem. Res. Toxicol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"S325","DOI":"10.2337\/dcS13-2038","article-title":"Intolerance to Statins: Mechanisms and Management","volume":"36","author":"Bitzur","year":"2013","journal-title":"Diabetes Care"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.nmd.2013.09.011","article-title":"Statin myotoxicity: A review of genetic susceptibility factors","volume":"24","author":"Needham","year":"2014","journal-title":"Neuromuscul. Disord."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1038\/nrd1720","article-title":"Elucidating mechanisms of drug-induced toxicity","volume":"4","author":"Liebler","year":"2005","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.mrrev.2008.05.003","article-title":"Structure alerts for carcinogenicity, and the Salmonella assay system: A novel insight through the chemical relational databases technology","volume":"659","author":"Benigni","year":"2008","journal-title":"Mutat. Res.\/Rev. Mutat. Res."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: A major update to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref_53","unstructured":"Bjerrum, E.J. (2017). SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules. arXiv."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/25\/8\/4516\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:31:29Z","timestamp":1760106689000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/25\/8\/4516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,20]]},"references-count":53,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["ijms25084516"],"URL":"https:\/\/doi.org\/10.3390\/ijms25084516","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,20]]}}}