A Review of In Silico Toxicity Prediction

Abstract

Introduction: Toxicity assessment is essential in drug development, chemical safety evaluation, ecological monitoring, and regulatory decision-making. Conventional methods involving laboratory experiments and animal studies are time-consuming, expensive, and ethically challenging. In silico toxicity prediction provides a rapid, cost-effective approach for identifying potential toxicological risks.

Aim & Objective: This review aims to describe the principles, methodologies, applications, advantages, limitations, and future perspectives of in silico toxicity prediction, emphasizing its role in improving safety screening and reducing experimental requirements.

Materials & Methods: A narrative review was conducted examining computational toxicity assessment methodologies and their applicatiosns in pharmaceutical research and chemical safety evaluation. Major approaches included quantitative structure–activity relationship (QSAR) models, read-across methods, molecular docking, machine learning, deep learning, and systems toxicology frameworks. Their predictive capabilities, applications, and limitations were evaluated.

Results: In silico approaches facilitate rapid toxicity screening, prioritization of potentially hazardous compounds, and prediction of adverse biological effects. QSAR models estimate toxicity using chemical structures, while read-across methods utilize information from structurally related compounds. Molecular docking investigates interactions between chemicals and biological targets. Machine learning and deep learning enable analysis of complex datasets and identification of toxicity-associated patterns. Integrating computational models with toxicological databases and mechanistic approaches may improve predictive performance. However, data quality, model interpretability, validation, and inadequate representation of biological complexity remain significant challenges.

Conclusion: In silico toxicity prediction represents a promising approach to modern toxicological research, offering efficient and potentially cost-effective alternatives to conventional screening methods. Integrating artificial intelligence, reliable toxicological databases, and mechanistic modelling may enhance prediction accuracy and support next-generation risk assessment. Nevertheless, rigorous model validation and complementary experimental evidence remain essential for reliable safety evaluation and regulatory acceptance.

REFERENCES

1. Pammolli F, Magazzini L, Riccaboni M. The productivity crisis in pharmaceutical R&D. Nat Rev Drug Discov. 2011;10(6):428-438. https://doi.org/10.1038/nrd3405
2. Dowden H, Munro J. Trends in clinical success rates and therapeutic focus. Nat Rev Drug Discov. 2019;18(7):495-496. https://doi.org/10.1038/d41573-019-00074-z
3. Van Tran TT, Wibowo AS, Tayara H, Chong KT. Artificial intelligence in drug toxicity prediction: recent advances, challenges, and future perspectives. J Chem Inf Model. 2023;63(9):2628-2643.
4. Kavlock RJ, Ankley GT, Blancato JN, Collette TW, Francis EZ, Gray LE Jr, et al. A framework for a computational toxicology research program in ORD. Washington (DC): US Environmental Protection Agency; 2003:1-49
5. Hartung T. Lessons learned from alternative methods and their validation for a new toxicology in the 21st century. J Toxicol Environ Health B Crit Rev. 2010;13(4):277-290. https://doi.org/10.1080/10937404.2010.483945
6. Pereira S, Veeraraghavan P, Ghosh S, Gandhi M. Animal experimentation and ethics in India: the CPCSEA makes a difference. Altern Lab Anim. 2004;32(1):411-415. https://doi.org/10.1177/026119290403201s67
7. Gozalbes R, De Julián-Ortiz JV. Applications of chemoinformatics in predictive toxicology for regulatory purposes, especially in the context of the EU REACH legislation. Int J Quant Struct Prop Relat. 2017;3(1):1-24. https://doi.org/10.4018/ijqspr.2018010101
8. Raunio H. In silico toxicology-non-testing methods. Front Pharmacol. 2011;2:1-8. https://doi.org/10.3389/fphar.2011.00033
9. Luechtefeld T. Computational approaches to chemical hazard assessment. ALTEX. 2017;34(4):459-478. https://doi.org/10.14573/altex.1710141
10. Bueso-Bordils JI, Antón-Fos GM, Martín-Algarra R, Alemán-López PA. Overview of computational toxicology methods applied in drug and green chemical discovery. J Xenobiot. 2024;14(4):1901-1918. https://doi.org/10.3390/jox14040101
11. Grisoni F, Consonni V, Todeschini R. Impact of molecular descriptors on computational models. In: Methods in molecular biology. New York: Humana Press; 2018:171-209. https://doi.org/10.1007/978-1-4939-8639-2_5
12. Mao J, Akhtar J, Zhang X, Sun L, Guan S, Li X, et al. Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models. iScience. 2021;24(9):1-20. https://doi.org/10.1016/j.isci.2021.103052
13. Seal S, Mahale M, García-Ortegón M, Joshi CK, Hosseini-Gerami L, Beatson A, et al. Machine learning for toxicity prediction using chemical structures: pillars for success in the real world. Chem Res Toxicol. 2025;38(5):759-807. https://doi.org/10.1021/acs.chemrestox.5c00033
14. Raies AB, Bajic VB. In silico toxicology: computational methods for the prediction of chemical toxicity. Wiley Interdiscip Rev Comput Mol Sci. 2016;6(2):147-172. https://doi.org/10.1002/wcms.1240
15. G A, Kamala G, D C, J S, D B, K RD, et al. Quantitative structure-activity relationship (QSAR) in drug discovery and development. J Pharma Insights Res. 2025;3(1):241-251. https://doi.org/10.69613/d091zy53
16. Deeb O, Goodarzi M. In silico quantitative structure toxicity relationship of chemical compounds: some case studies. Curr Drug Saf. 2012;7(4):289-297. https://doi.org/10.2174/157488612804096533
17. Yang H, Sun L, Li W, Liu G, Tang Y. In silico prediction of chemical toxicity for drug design using machine learning methods and structural alerts. Front Chem. 2018;6:1-12. https://doi.org/10.3389/fchem.2018.00030
18. Idakwo G, Luttrell J, Chen M, Hong H, Zhou Z, Gong P, et al. A review on machine learning methods for in silico toxicity prediction. J Environ Sci Health C Toxicol Carcinog. 2018;36(4):169-191. https://doi.org/10.1080/10590501.2018.1537118
19. Meng XY, Zhang HX, Mezei M, Cui M. Molecular docking: a powerful approach for structure-based drug discovery. Curr Comput Aided Drug Des. 2011;7(2):146-157. https://doi.org/10.2174/157340911795677602
20. Organisation for Economic Co-operation and Development. Guidance on grouping of chemicals. 3rd ed. Paris: OECD Publishing; 2025:1-265. https://doi.org/10.1787/b254a158-en
21. Omer A, Singh P, Yadav NK, Singh RK. An overview of data mining algorithms in drug-induced toxicity prediction. Mini Rev Med Chem. 2014;14(4):345-354. https://doi.org/10.2174/1389557514666140219110244
22. Omer A. Role of machine learning in computational toxicity prediction. J Recent Adv Appl Sci. 2023;9(1):1-4.
23. Davis AP, Wiegers TC, Johnson RJ, Sciaky D, Wiegers J, Mattingly CJ. Comparative Toxicogenomics Database (CTD): update 2023. Nucleic Acids Res. 2023;51(1):1257-1262. https://doi.org/10.1093/nar/gkw838
24. Williams AJ, Grulke CM, Edwards J, McEachran AD, Mansouri K, Baker NC, et al. The CompTox Chemistry Dashboard: a community data resource for environmental chemistry. J Cheminform. 2017;9(1):1-27. https://doi.org/10.1186/s13321-017-0247-6
25. Kavlock R, Dix D. Computational toxicology as implemented by the U.S. EPA: providing high-throughput decision support tools for screening and assessing chemical exposure, hazard and risk. J Toxicol Environ Health B Crit Rev. 2010;13(2-4):197-217. https://doi.org/10.1080/10937404.2010.483935
26. Attene-Ramos MS, Miller N, Huang R, Michael S, Itkin M, Kavlock RJ, et al. The Tox21 robotic platform for the assessment of environmental chemicals-from vision to reality. Drug Discov Today. 2013;18(15-16):716-723. https://doi.org/10.1016/j.drudis.2013.05.015
27. Sarkans U, Gostev M, Athar A, Behrangi E, Melnichuk O, Ali A, et al. The BioStudies database-one stop shop for all data supporting a life sciences study. Nucleic Acids Res. 2018;46(1):1266–1270. https://doi.org/10.1093/nar/gkx965
28. Dix DJ, Houck KA, Martin MT, Richard AM, Setzer RW, Kavlock RJ. The ToxCast program for prioritizing toxicity testing of environmental chemicals. Toxicol Sci. 2007;95(1):5-12. https://doi.org/10.1093/toxsci/kfl103
29. Fonger GC. Hazardous Substances Data Bank (HSDB) as a source of environmental fate information on chemicals. Toxicology. 1995;103(2):137-145. https://doi.org/10.1016/0300-483x(95)03145-6
30. Olker JH, Elonen CM, Pilli A, Anderson A, Kinziger B, Erickson S, et al. The ECOTOXicology Knowledgebase: a curated resource of ecologically relevant toxicity tests to support environmental research and risk assessment. Environ Toxicol Chem. 2022;41(6):1520-1539. https://doi.org/10.1002/etc.5324
31. Banerjee P, Kemmler E, Dunkel M, Preissner R. ProTox 3.0: a webserver for the prediction of toxicity of chemicals. Nucleic Acids Res. 2024;52(1):513–520. https://doi.org/10.1093/nar/gkae303
32. Banerjee P, Eckert AO, Schrey AK, Preissner R. ProTox-II: a webserver for the prediction of toxicity of chemicals. Nucleic Acids Res. 2018;46(1):257–263. https://doi.org/10.1093/nar/gky318
33. Wishart D, Arndt D, Pon A, Sajed T, Guo AC, Djoumbou Y, et al. T3DB: the toxic exposome database. Nucleic Acids Res. 2015;43(D1):928–934. https://doi.org/10.1093/nar/gku1004
34. Lim E, Pon A, Djoumbou Y, Knox C, Shrivastava S, Guo AC, et al. T3DB: a comprehensively annotated database of common toxins and their targets. Nucleic Acids Res. 2010;38(1):781–786. https://doi.org/10.1093/nar/gkp934
35. Sanderson DM, Earnshaw CG. Computer prediction of possible toxic action from chemical structure: the DEREK system. Hum Exp Toxicol. 1991;10(4):261-273. https://doi.org/10.1177/096032719101000405
36. Organisation for Economic Co-operation and Development. eChemPortal: the global portal to information on chemical substances. Paris: OECD;2007. https://www.echemportal.org/
37. De Marcellus S. EChemPortal-the global portal to information on chemical substances. In: Elsevier eBooks. 2023:1017-1029. https://doi.org/10.1016/b978-0-12-824315-2.01159-3
38. Wall JT, Sayre RR, Smith D, Winter S, Groover M, Hope J, et al. Development of the toxicity values database, ToxValDB: a curated resource for experimental and derived human health-relevant toxicity data. Comput Toxicol. 2025;35:1-10. https://doi.org/10.1016/j.comtox.2025.100365
39. Feshuk M, Kolaczkowski L, Watford S, Friedman KP. ToxRefDB v2.1: update to curated in vivo study data in the Toxicity Reference Database. Front Toxicol. 2023;5:1-4. https://doi.org/10.3389/ftox.2023.1260305
40. Gold LS, Slone TH, Manley NB, Garfinkel GB, Hudes ES, Rohrbach L, et al. The Carcinogenic Potency Database: analyses of 4000 chronic animal cancer experiments published in the general literature and by the US National Cancer Institute/National Toxicology Program. Environ Health Perspect. 1991;96:11-15. https://doi.org/10.1289/ehp.919611
41. Accelrys Inc. TOxicity Prediction by Komputer Assisted Technology (TOPKAT) [computer program]. San Diego (CA): Accelrys Inc.; 2015:1-9. http://accelrys.com/
42. Benfenati E, Chaudhry Q, Gini G, Dorne JL. Integrating in silico models and read-across methods for predicting toxicity of chemicals: a step-wise strategy. Environ Int. 2019;131:1-15. https://doi.org/10.1016/j.envint.2019.105060
43. Hemmerich J, Ecker GF. In silico toxicology: from structure-activity relationships towards deep learning and adverse outcome pathways. Wiley Interdiscip Rev Comput Mol Sci. 2020;10(4):1-23. https://doi.org/10.1002/wcms.1475
44. Bureau R. Nontest methods to predict acute toxicity: state of the art for applications of in silico methods. In: Methods in molecular biology. New York: Humana Press; 2018:519-534. https://doi.org/10.1007/978-1-4939-7899-1_24
45. Rim KT. In silico prediction of toxicity and its applications for chemicals at work. Toxicol Environ Health Sci. 2020;12(3):191-202. https://doi.org/10.1007/s13530-020-00056-4
46. Patlewicz G, Fitzpatrick JM. Current and future perspectives on the development, evaluation, and application of in silico approaches for predicting toxicity. Chem Res Toxicol. 2016;29(4):438-451. https://doi.org/10.1021/acs.chemrestox.5b00388
47. Cronin MTD, Enoch SJ, Mellor CL, Przybylak KR, Richarz AN, Madden JC. In silico prediction of organ level toxicity: linking chemistry to adverse effects. Toxicol Res. 2017;33(3):173-182. https://doi.org/10.5487/tr.2017.33.3.173
48. Organisation for Economic Co-operation and Development. (Q)SAR assessment framework: guidance for the regulatory assessment of (quantitative) structure-activity relationship models predictions and results based on multiple predictions. Paris: OECD Publishing; 2023:1-54. https://doi.org/10.1787/d96118f6-en
49. Sinha M, Jamal T, Dhawan A, Parthasarathi R. In silico approaches in predictive genetic toxicology. In: Methods in molecular biology. New York: Humana Press; 2025:565-586. https://doi.org/10.1007/978-1-0716-4976-3_26
50. Bassan A, Alves VM, Amberg A, Anger LT, Beilke L, Bender A, et al. In silico approaches in organ toxicity hazard assessment: current status and future needs for predicting heart, kidney and lung toxicities. Comput Toxicol. 2021;20:1-4. https://doi.org/10.1016/j.comtox.2021.100188
51. Gianquinto E, Bersani M, Armando L, Davani L, Cena C, De Simone A, et al. Toward integrative predictive toxicology: advanced methods for drug toxicity and safety prediction. Wiley Interdiscip Rev Comput Mol Sci. 2026;16(1):1-61. https://doi.org/10.1002/wcms.70065
52. Van Der Burg B, Wedebye EB, Dietrich DR, Jaworska J, Mangelsdorf I, Paune E, et al. The ChemScreen project to design a pragmatic alternative approach to predict reproductive toxicity of chemicals. Reprod Toxicol. 2015;55:114-123. https://doi.org/10.1016/j.reprotox.2015.01.008
53. Astuto MC, Di Nicola MR, Tarazona JV, Rortais A, Devos Y, Liem AKD, et al. In silico methods for environmental risk assessment: principles, tiered approaches, applications, and future perspectives. In: Methods in molecular biology. New York: Humana Press; 2022:589-636. https://doi.org/10.1007/978-1-0716-1960-5_23
54. Organisation for Economic Co-operation and Development. Guidance document for aquatic effects assessment. Paris: OECD; 1995:1-118. https://doi.org/10.1787/29111f91-en
55. Pistollato F, Madia F, Corvi R, Munn S, Grignard E, Paini A, et al. Current EU regulatory requirements for the assessment of chemicals and cosmetic products: challenges and opportunities for introducing new approach methodologies. Arch Toxicol. 2021;95(6):1867-1897. https://doi.org/10.1007/s00204-021-03034-y
56. European Chemicals Agency. Guidance on information requirements and chemical safety assessment: chapter R.6: QSARs and grouping of chemicals. Helsinki: European Chemicals Agency; 2008:1-134. https://doi.org/10.1016/b978-0-12-386454-3.00575-3
57. Kalikar MV, Dakhale G. Preparing for Central Drugs Standard Control Organization ethics committee inspections in India: a review of regulatory expectations and readiness strategies. Perspect Clin Res. 2026;17(2):115-117. https://doi.org/10.4103/picr.picr_395_25
58. Organisation for Economic Co-operation and Development. Guidance document on the validation of (quantitative) structure-activity relationship [(Q)SAR] models. Paris: OECD Publishing; 2014:1-154. https://doi.org/10.1787/9789264085442-en