Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

In silico prediction of drug-induced cardiotoxicity with ensemble machine learning and structural pattern recognition.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: In silico prediction of drug-induced cardiotoxicity with ensemble machine learning and structural pattern recognition.
Συγγραφείς: Li S; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China., Xu H; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China.; School of Pharmaceutical Sciences, Shandong University, Jinan, 250014, China., Liu F; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China., Ni R; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China., Shi Y; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China., Li X; Shandong Engineering and Technology Research Center for Pediatric Drug Development, Shandong Medicine and Health Key Laboratory of Clinical Pharmacy, Department of Clinical Pharmacy, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, 250014, China. lixiao1688@163.com.
Πηγή: Molecular diversity [Mol Divers] 2026 Apr; Vol. 30 (2), pp. 1885-1896. Date of Electronic Publication: 2025 Jun 26.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: ESCOM Science Publishers Country of Publication: Netherlands NLM ID: 9516534 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1573-501X (Electronic) Linking ISSN: 13811991 NLM ISO Abbreviation: Mol Divers Subsets: MEDLINE
Imprint Name(s): Original Publication: Leiden, The Netherlands : ESCOM Science Publishers, c1995-
Ιατρικοί όροι (MeSH): Cardiotoxicity*/etiology , Machine Learning* , Computer Simulation*, Humans ; Drug-Related Side Effects and Adverse Reactions
Περίληψη: Drug-induced cardiotoxicity poses a significant risk to human health, and reliable predictive models are needed for safety assessment. In this study, a range of machine and deep learning models were developed for five cardiotoxicity end points, including heart failure (HF), arrhythmia (ARR), heart block (HB), hypertension (HP), and heart attack (HA). A total of 110 predictive models were constructed for each cardiotoxicity endpoint using various algorithms and molecular descriptors, and consensus models were developed based on the best-performing individual classifiers. The consensus models consistently outperformed individual models in cross-validation and external validation. Further molecular property analysis revealed that cardiotoxic compounds tend to exhibit higher molecular weight, increased lipophilicity (logP), lower hydrogen bonding capacity (HBD and HBA), and reduced topological polar surface area (TPSA). Additionally, key structural alerts (SAs), including secondary amines, benzene derivatives, sulfonamide/sulfonylurea groups, and heterocyclic structures, were identified. These SAs may mediate cardiotoxicity through ion channel inhibition, oxidative stress induction, and calcium homeostasis disruption. This study provides an integrated machine learning and deep learning computational framework for drug cardiotoxicity assessment and provides an exploration of the structural characteristics of cardiotoxic compounds, which is helpful for the discovery of safer drugs and chemical risk assessment.
(© 2025. The Author(s), under exclusive licence to Springer Nature Switzerland AG.)
Competing Interests: Declarations. Conflict of interest: The authors declare no competing interests.
References: Cai C, Guo P, Zhou Y et al (2019) Deep learning-based prediction of drug-induced cardiotoxicity. J Chem Inf Model 59(3):1073–1084. https://doi.org/10.1021/acs.jcim.8b00769. (PMID: 10.1021/acs.jcim.8b00769307158736489130)
Iftkhar S, de Sá AGC, Velloso JPL et al (2022) cardioToxCSM: a web server for predicting cardiotoxicity of small molecules. J Chem Inf Model 62(20):4827–4836. https://doi.org/10.1021/acs.jcim.2c00822. (PMID: 10.1021/acs.jcim.2c0082236219164)
Yang H, Xiu J, Yan W et al (2025) Large language models as tools for molecular toxicity prediction: AI insights into cardiotoxicity. J Chem Inf Model 65(5):2268–2282. https://doi.org/10.1021/acs.jcim.4c01371. (PMID: 10.1021/acs.jcim.4c0137139982968)
Yang P-C, DeMarco KR, Aghasafari P et al (2020) A computational pipeline to predict cardiotoxicity. Circ Res 126(8):947–964. https://doi.org/10.1161/CIRCRESAHA.119.316404. (PMID: 10.1161/CIRCRESAHA.119.316404320919727155920)
Li X, Zhang Y, Li H et al (2017) Modeling of the hERG K+ channel blockage using online chemical database and modeling environment (OCHEM). Mol Inf 36(12):1700074. https://doi.org/10.1002/minf.201700074. (PMID: 10.1002/minf.201700074)
Liu J, Hasan KMK, Wenjing G et al (2024) Machine learning and deep learning approaches for enhanced prediction of hERG blockade: a comprehensive QSAR modeling study. Expert Opin Drug Metab Toxicol 20(7):665–684. https://doi.org/10.1080/17425255.2024.2377593. (PMID: 10.1080/17425255.2024.237759338968091)
Liu K, Cui H, Yu X et al (2025) Predicting cardiotoxicity in drug development: a deep learning approach. J Pharm Anal. https://doi.org/10.1016/j.jpha.2025.101263. (PMID: 10.1016/j.jpha.2025.1012634205796713122219)
Sanches IH, Mendonca SS, Alves VM et al (2024) Chapter 26—QSAR models for predicting cardiac toxicity of drugs. In: Hong H (ed) QSAR in safety evaluation and risk assessment. Academic Press, pp 351–362. (PMID: 10.1016/B978-0-443-15339-6.00039-4)
Cai C, Fang J, Guo P et al (2018) In silico pharmacoepidemiologic evaluation of drug-induced cardiovascular complications using combined classifiers. J Chem Inf Model 58(5):943–956. https://doi.org/10.1021/acs.jcim.7b00641. (PMID: 10.1021/acs.jcim.7b00641297124295975252)
Alejandro S-P, Cordeiro MNDS (2013) Simultaneous modeling of antimycobacterial activities and ADMET profiles: a chemoinformatic approach to medicinal chemistry. Curr Top Med Chem 13(14):1656–1665. https://doi.org/10.2174/15680266113139990116. (PMID: 10.2174/15680266113139990116)
Alejandro S-P, Soeiro MND (2014) Review of current chemoinformatic tools for modeling important aspects of CYPsmediated drug metabolism integrating metabolism data with other biological profiles to enhance drug discovery. Curr Drug Metab 15(4):429–440. https://doi.org/10.2174/1389200215666140605124002. (PMID: 10.2174/1389200215666140605124002)
Valeria VK, Feng L, Alejandro S-P et al (2015) In Silico assessment of the acute toxicity of chemicals: recent advances and new model for multitasking prediction of toxic effect. Mini-Rev Med Chem 15(8):677–686. https://doi.org/10.2174/1389557515666150219143604. (PMID: 10.2174/1389557515666150219143604)
Speck-Planche A, Cordeiro MNDS (2017) De novo computational design of compounds virtually displaying potent antibacterial activity and desirable in vitro ADMET profiles. Med Chem Res 26(10):2345–2356. https://doi.org/10.1007/s00044-017-1936-4. (PMID: 10.1007/s00044-017-1936-4)
Speck-Planche A, Dias Soeiro Cordeiro MN (2017) Speeding up early drug discovery in antiviral research: a fragment-based in silico approach for the design of virtual anti-hepatitis C leads. ACS Comb Sci 19(8):501–512. https://doi.org/10.1021/acscombsci.7b00039. (PMID: 10.1021/acscombsci.7b0003928437091)
Kleandrova VV, Speck-Planche A (2023) Optimizing drug discovery using multitasking models for quantitative structure–biological effect relationships: an update of the literature. Expert Opin Drug Discov 18(11):1231–1243. https://doi.org/10.1080/17460441.2023.2251385. (PMID: 10.1080/17460441.2023.225138537639708)
Kleandrova VV, Cordeiro MNDS, Speck-Planche A (2025) In silico approach for antibacterial discovery: PTML modeling of virtual multi-strain inhibitors against staphylococcus aureus. Pharmaceuticals 18(2):196. (PMID: 10.3390/ph180201964000601011858522)
Chen Z, Li N, Zhang P et al (2024) CardioDPi: an explainable deep-learning model for identifying cardiotoxic chemicals targeting hERG, Cav1.2, and Nav1.5 channels. J Hazard Mater 474:134724. https://doi.org/10.1016/j.jhazmat.2024.134724. (PMID: 10.1016/j.jhazmat.2024.13472438805819)
Fu J, Le XC (2025) Improving groundwater vulnerability assessment using machine learning. J Environ Sci 153:6–9. https://doi.org/10.1016/j.jes.2024.12.024. (PMID: 10.1016/j.jes.2024.12.024)
Mubeen M, He S, Rahman MS et al (2025) Smart prediction and optimization of air quality index with artificial intelligence. J Environ Sci. https://doi.org/10.1016/j.jes.2025.02.041. (PMID: 10.1016/j.jes.2025.02.041)
Bento AP, Hersey A, Félix E et al (2020) An open source chemical structure curation pipeline using RDKit. J Cheminf 12(1):51. https://doi.org/10.1186/s13321-020-00456-1. (PMID: 10.1186/s13321-020-00456-1)
Han Z, Xia Z, Xia J et al (2025) The state-of-the-art machine learning model for plasma protein binding prediction: Computational modeling with OCHEM and experimental validation. Eur J Pharm Sci 204:106946. https://doi.org/10.1016/j.ejps.2024.106946. (PMID: 10.1016/j.ejps.2024.10694639490636)
Sushko I, Novotarskyi S, Körner R et al (2011) Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information. J Comput Aided Mol Des 25(6):533–554. https://doi.org/10.1007/s10822-011-9440-2. (PMID: 10.1007/s10822-011-9440-2216605153131510)
Kovalishyn V, Abramenko N, Kopernyk I et al (2018) Modelling the toxicity of a large set of metal and metal oxide nanoparticles using the OCHEM platform. Food Chem Toxicol 112:507–517. https://doi.org/10.1016/j.fct.2017.08.008. (PMID: 10.1016/j.fct.2017.08.00828802948)
Rusanov AI, Dmitrieva OA, Mamardashvili NZ et al (2022) More is not always better: local models provide accurate predictions of spectral properties of porphyrins. Int J Mol Sci 23(3):1201. (PMID: 10.3390/ijms23031201351631238835262)
Zhang R, Chen Z, Wang B et al (2023) Modeling and insights into the structural characteristics of chemical mitochondrial toxicity. ACS Omega 8(35):31675–31682. https://doi.org/10.1021/acsomega.3c01725. (PMID: 10.1021/acsomega.3c017253769223910483523)
Zhang R, Guo H, Hua Y et al (2022) Modeling and insights into the structural basis of chemical acute aquatic toxicity. Ecotoxicol Environ Saf 242:113940. https://doi.org/10.1016/j.ecoenv.2022.113940. (PMID: 10.1016/j.ecoenv.2022.11394035999760)
Zhang R, Wang B, Li L et al (2023) Modeling and insights into the structural characteristics of endocrine-disrupting chemicals. Ecotoxicol Environ Saf 263:115251. https://doi.org/10.1016/j.ecoenv.2023.115251. (PMID: 10.1016/j.ecoenv.2023.11525137451095)
Hua Y, Shi Y, Cui X et al (2021) In silico prediction of chemical-induced hematotoxicity with machine learning and deep learning methods. Mol Diversity 25(3):1585–1596. https://doi.org/10.1007/s11030-021-10255-x. (PMID: 10.1007/s11030-021-10255-x)
Huang X, Tang F, Hua Y et al (2021) In silico prediction of drug-induced ototoxicity using machine learning and deep learning methods. Chem Biol Drug Des 98(2):248–257. https://doi.org/10.1111/cbdd.13894. (PMID: 10.1111/cbdd.1389434013639)
Hunklinger A, Hartog P, Šícho M et al (2024) The openOCHEM consensus model is the best-performing open-source predictive model in the First EUOS/SLAS joint compound solubility challenge. SLAS Discov. https://doi.org/10.1016/j.slasd.2024.01.005. (PMID: 10.1016/j.slasd.2024.01.00538316342)
Makarov DM, Ksenofontov AA, Budkov YA (2025) Consensus modeling for predicting chemical binding to transthyretin as the winning solution of the Tox24 challenge. Chem Res Toxicol 38(3):392–399. https://doi.org/10.1021/acs.chemrestox.4c00421. (PMID: 10.1021/acs.chemrestox.4c0042139969008)
Yap CW (2011) PaDEL-descriptor: an open source software to calculate molecular descriptors and fingerprints. J Comput Chem 32(7):1466–1474. https://doi.org/10.1002/jcc.21707. (PMID: 10.1002/jcc.2170721425294)
Bauer FJ, Thomas PC, Fouchard SY et al (2018) High-accuracy prediction of mechanisms of action using structural alerts. Comput Toxicol 7:36–45. https://doi.org/10.1016/j.comtox.2018.06.004. (PMID: 10.1016/j.comtox.2018.06.004)
Hua Y, Cui X, Liu B et al (2022) SApredictor: an expert system for screening chemicals against structural alerts. Front Chem. https://doi.org/10.3389/fchem.2022.916614. (PMID: 10.3389/fchem.2022.916614359107299326022)
Yang H, Lou C, Li W et al (2020) Computational approaches to identify structural alerts and their applications in environmental toxicology and drug discovery. Chem Res Toxicol 33(6):1312–1322. https://doi.org/10.1021/acs.chemrestox.0c00006. (PMID: 10.1021/acs.chemrestox.0c0000632091207)
Monnery BD, Wright M, Cavill R et al (2017) Cytotoxicity of polycations: relationship of molecular weight and the hydrolytic theory of the mechanism of toxicity. Int J Pharm 521(1):249–258. https://doi.org/10.1016/j.ijpharm.2017.02.048. (PMID: 10.1016/j.ijpharm.2017.02.04828232268)
Vogel A, Brunner JS, Hajto A et al (1867) (2022) Lipid scavenging macrophages and inflammation. Biochim Biophys Acta 1:159066. https://doi.org/10.1016/j.bbalip.2021.159066. (PMID: 10.1016/j.bbalip.2021.159066)
Meanwell NA (2011) Improving drug candidates by design: a focus on physicochemical properties as a means of improving compound disposition and safety. Chem Res Toxicol 24(9):1420–1456. https://doi.org/10.1021/tx200211v. (PMID: 10.1021/tx200211v21790149)
Labby KJ, Xue F, Kraus JM et al (2012) Intramolecular hydrogen bonding: a potential strategy for more bioavailable inhibitors of neuronal nitric oxide synthase. Bioorg Med Chem 20(7):2435–2443. https://doi.org/10.1016/j.bmc.2012.01.037. (PMID: 10.1016/j.bmc.2012.01.037223703373303928)
Prasanna S, Doerksen RJ (2009) Topological polar surface area: a useful descriptor in 2D-QSAR. Curr Med Chem 16(1):21–41. https://doi.org/10.2174/092986709787002817. (PMID: 10.2174/092986709787002817191495617549127)
Srivastava R (2021) Theoretical studies on the molecular properties, toxicity, and biological efficacy of 21 new chemical entities. ACS Omega 6(38):24891–24901. https://doi.org/10.1021/acsomega.1c03736. (PMID: 10.1021/acsomega.1c03736346046708482469)
Brotzel F, Chu YC, Mayr H (2007) Nucleophilicities of primary and secondary amines in water. J Org Chem 72(10):3679–3688. https://doi.org/10.1021/jo062586z. (PMID: 10.1021/jo062586z17411095)
Dash UC, Bhol NK, Swain SK et al (2025) Oxidative stress and inflammation in the pathogenesis of neurological disorders: Mechanisms and implications. Acta Pharm Sin B 15(1):15–34. https://doi.org/10.1016/j.apsb.2024.10.004. (PMID: 10.1016/j.apsb.2024.10.00440041912)
Son SM (2012) Reactive oxygen and nitrogen species in pathogenesis of vascular complications of diabetes. Diabetes Metab J 36(3):190–198. https://doi.org/10.4093/dmj.2012.36.3.190. (PMID: 10.4093/dmj.2012.36.3.190227376583380122)
Ferraroni M, Angeli A, Pinteala M et al (2022) Sulfonamide diuretic azosemide as an efficient carbonic anhydrase inhibitor. J Mol Struct 1268:133672. https://doi.org/10.1016/j.molstruc.2022.133672. (PMID: 10.1016/j.molstruc.2022.133672)
Rai SK, Patil RI, Sharma K et al (2025) Identification and evaluation of cyclic urea based 4H-triazolo pyridine substituted derivatives as novel ASK1 inhibitors. Bioorg Chem 159:108375. https://doi.org/10.1016/j.bioorg.2025.108375. (PMID: 10.1016/j.bioorg.2025.10837540117753)
Grant Information: QYPY2020NSFC0618 Cultivation Fund of the First Affiliated Hospital of Shandong First Medical University; SDACM202206 Shandong Association of Traditional Chinese Medicine Clinical Pharmacy Research Special Fund Project; hlyy-2024-01 Shandong Pharmaceutical Association Hospital Rational Drug Use Young and Middle-aged Scientific Research; ywjj-2024-01 Shandong Pharmaceutical Association Medical Institution Pharmacovigilance Young and Middle-aged Project
Contributed Indexing: Keywords: Artificial intelligence model; Chemical risk assessment; Drug-induced cardiotoxicity; Structural alerts; Toxicity mechanisms
Entry Date(s): Date Created: 20250626 Date Completed: 20260504 Latest Revision: 20260504
Update Code: 20260504
DOI: 10.1007/s11030-025-11266-8
PMID: 40569519
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1573-501X
DOI:10.1007/s11030-025-11266-8