In Silico Estimation of the Safety of Pharmacologically Active Substances Using Machine Learning Methods: A Review

Scientific relevance. Currently, machine learning (ML) methods are widely used in the research and development of new pharmaceuticals. ML methods are particularly important for assessing the safety of pharmacologically active substances early in the research process because such safety assessments significantly reduce the risk of obtaining negative results in the future.

Aim. This study aimed to review the main information and prediction resources that can be used for the assessment of the safety of pharmacologically active substances in silico.

Discussion. Novel ML methods can identify the most likely molecular targets for a specific compound to interact with, based on structure–activity relationship analysis. In addition, ML methods can be used to search for potential therapeutic and adverse effects, as well as to study acute and specific toxicity, metabolism, and other pharmacodynamic, pharmacokinetic, and toxicological characteristics of investigational substances. Obtained at early stages of research, this information helps to prioritise areas for experimental testing of biological activity, as well as to identify compounds with a low probability of producing adverse and toxic effects. This review describes free online ML-based information and prediction resources for assessing the safety of pharmacologically active substances using their structural formulas. Special attention is paid to the Russian computational products presented on the Way2Drug platform (https://www.way2drug.com/dr/).

Conclusions. Contemporary approaches to the assessment of pharmacologically active substances in silico based on structure–activity relationship analysis using ML methods provide information about various safety characteristics and allow developers to select the most promising candidates for further in-depth preclinical and clinical studies.

1. Jorgensen WL. The many roles of computation in drug discovery. Science. 2004;303(5665):1813–8. https://doi.org/10.1126/science.1096361

2. Bezhentsev VM, Druzhilovskii DS, Ivanov SM, Filimonov DA, Sastry GN, Poroikov VV. Web resources for discovery and development of new medicines. Pharm Chem J. 2017;51(2):91–9. https://doi.org/10.1007/s11094-017-1563-x

3. Bajorath J, Overington J, Jenkins JL, Walters P. Drug discovery and development in the era of Big Data. Future Med Chem. 2016;8(15):1807–13. https://doi.org/10.4155/fmc-2014-0081

4. Fourches D, Muratov E, Tropsha A. Trust, but verify II: a practical guide to chemogenomics data curation. J Chem Inf Model. 2016;56(7):1243–52. https://doi.org/10.1021/acs.jcim.6b00129

5. Muratov EN, Bajorath J, Sheridan RP, Tetko IV, Filimonov D, Poroikov V, et al. QSAR without borders. Chem Soc Rev. 2020;49(11):3525–64. https://doi.org/10.1039/D0CS00098A

6. Pun FW, Ozerov IV, Zhavoronkov A. AI-powered therapeutic target discovery. Trends Pharmacol Sci. 2023;44(9):561–72. https://doi.org/10.1016/j.tips.2023.06.010

7. Bender A, Cortés-Ciriano I. Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 1: Ways to make an impact, and why we are not there yet. Drug Discov Today. 2021;26(2):511–24. https://doi.org/10.1016/j.drudis.2020.12.009

8. Bender A, Cortes-Ciriano I. Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data. Drug Discov Today. 2021;26(4):1040–52. https://doi.org/10.1016/j.drudis.2020.11.037

9. Hasselgren C, Oprea TI. Artificial intelligence for drug discovery: are we there yet? Annu Rev Pharmacol Toxicol. 2024;64:12023. https://doi.org/10.1146/annurev-pharmtox-040 323-040828

10. Wadman M. FDA no longer has to require animal testing for new drugs. Science. 2023;379(6628):127–8. https://doi.org/10.1126/science.adg6276

11. Luo M, Wang XS, Tropsha A. Comparative analysis of QSAR-based vs. chemical similarity based predictors of GPCRs binding affinity. Mol Inform. 2016;35(1):36–41. https://doi.org/10.1002/minf.201500038

12. Murtazalieva KA, Druzhilovskiy DS, Goel RK, Sastry GN, Poroikov VV. How good are publicly available web services that predict bioactivity profiles for drug repurposing? SAR QSAR Environ Res. 2017;28(10):843–62. https://doi.org/10.1080/1062936X.2017.1399448

13. Forouzesh A, Samadi Foroushani S, Forouzesh F, Zand E. Reliable target prediction of bioactive molecules based on chemical similarity without employing statistical methods. Front Pharmacol. 2019;10:835. https://doi.org/10.3389/fphar.2019.00835

14. Ji KY, Liu C, Liu ZQ, Deng YF, Hou TJ, Cao DS. Comprehensive assessment of nine target prediction web services: which should we choose for target fishing? Brief Bioinform. 2023;24(2):bbad014. https://doi.org/10.1093/bib/bbad014

15. Burov YuV, Korolchenko LV, Poroikov VV. State system of registration and biological testing of chemical compounds: opportunities for finding new drugs. Bulletin of the All-Union Scientific Center for the Safety of Biologically Active Substances. 1990;(1):4–25 (In Russ.).

16. Lagunin A, Stepanchikova A, Filimonov D, Poroikov V. PASS: prediction of activity spectra for biologically active substances. Bioinformatics. 2000;16(8):747–8. https://doi.org/10.1093/bioinformatics/16.8.747

17. Filimonov DA, Druzhilovskiy DS, Lagunin AA, Gloriozova TA, Rudik AV, Dmitriev AV, et al. Computer-aided prediction of biological activity spectra for chemical compounds: opportunities and limitations. Biomedical Chemistry: Research and Methods. 2018;1(1):e00004 (In Russ.). https://doi.org/10.18097/bmcrm00004

18. Filimonov DA, Zakharov AV, Lagunin AA, Poroikov VV. QNA based “Star Track” QSAR approach. SAR QSAR Environ Res. 2009;20(7–8):679–709. https://doi.org/10.1080/10629360903438370

19. Lagunin A, Zakharov A, Filimonov D, Poroikov V. QSAR modelling of rat acute toxicity on the basis of PASS prediction. Mol Inform. 2011;30 (2–3);241–50. https://doi.org/10.1002/minf.201000151

20. Stolbov LA, Filimonov DA, Poroikov VV. SAR based on self-consistent classifier. SAR QSAR Environ Res. 2022;33(10):793–804. https://doi.org/10.1080/1062936X.2022.2139751

21. Sakamuru S, Huang R, Xia M. Use of Tox21 screening data to evaluate the COVID-19 drug candidates for their potential toxic effects and related pathways. Front Pharmacol. 2022;13:935399. https://doi.org/10.3389/fphar.2022.935399

22. Pogodin PV, Lagunin AA, Filimonov DA, Poroikov VV. PASS Targets: ligand-based multi-target computational system based on public data and Naïve Bayes approach. SAR QSAR Environ Res. 2015;26(10):783–93. https://doi.org/10.1080/1062936X.2015.1078407

23. Lagunin AA, Rudik AV, Pogodin PV, Savosina PI, Tarasova OA, Dmitriev AV, et al. CLC-Pred 2.0: a freely available web application for in silico prediction of human cell line cytotoxicity and molecular mechanisms of action for druglike compounds. Int J Mol Sci. 2023;24(2):1689. https://doi.org/10.3390/ijms24021689

24. Lagunin A, Ivanov S, Rudik A, Filimonov D, Poroikov V. DIGEP-Pred: web-service for in silico prediction of drug-induced expression profiles based on structural formula. Bioinformatics. 2013;29(16):2062–63. https://doi.org/10.1093/bioinformatics/btt322

25. Ivanov SM, Lagunin AA, Rudik AV, Filimonov DA, Poroikov VV. ADVERPred — web service for prediction of adverse effects of drugs. J Chem Inf Model. 2018;58(1):8–11. https://doi.org/10.1021/acs.jcim.7b00568

26. Lagunin A, Rudik A, Filimonov D, Druzhilovskiy D, Poroikov V. ROSC-Pred: web-service for rodent organ-specific carcinogenicity prediction. Bioinformatics. 2018;34(4):710–12. https://doi.org/10.1093/bioinformatics/btx678

27. Lagunin A, Zakharov A, Filimonov D, Poroikov V. QSAR modelling of rat acute toxicity on the basis of PASS prediction. Mol Inform. 2011;30 (2–3):241–50. https://doi.org/10.1002/minf.201000151

28. Zakharov AV, Lagunin AA, Filimonov DA, Poroikov VV. Quantitative prediction of antitarget interaction profiles for chemical compounds. Chem Res Toxicol. 2012;25(11):2378–85. https://doi.org/10.1021/tx300247r

29. Dmitriev AV, Filimonov DA, Rudik AV, Pogodin PV, Karasev DA, Lagunin AA, Poroikov VV. Drug-drug interaction prediction using PASS. SAR QSAR Environ Res. 2019;30(9):655–64. https://doi.org/10.1080/1062936X.2019.1653966

30. Korotkevich EI, Rudik AV, Dmitriev AV, Lagunin AA, Filimonov DA. Predict of metabolic stability of xenobiotics by the PASS and GUSAR programs. Biomeditsinskaya Khimiya. 2021;67(3):295–9 (In Russ.). https://doi.org/10.18097/PBMC20216703295

31. Rudik A, Dmitriev A, Lagunin A, Filimonov D, Poroikov V. SOMP: web-service for in silico prediction of sites of metabolism for drug-like compounds. Bioinformatics. 2015;31(12):2046–8. https://doi.org/10.1093/bioinformatics/btv087

32. Rudik AV, Dmitriev AV, Lagunin AA, Filimonov DA, Poroikov VV. Prediction of reacting atoms for the major biotransformation reactions of organic xenobiotics. J Cheminform. 2016;8:68. https://doi.org/10.1186/s13321-016-0183-x

33. Rudik AV, Dmitriev AV, Lagunin AA, Filimonov DA, Poroikov VV. Metabolism sites prediction based on xenobiotics structural formulae and PASS prediction algorithm. J Chem Inf Model. 2014;54(2):498–507. https://doi.org/10.1021/ci400472j

34. Rudik AV, Bezhentsev VM, Dmitriev AV, Druzhilovskiy DS, Lagunin AA, Filimonov DA, Poroikov VV. MetaTox: web application for predicting structure and toxicity of xenobiotics’ metabolites. J Chem Inf Model. 2017;57(4):638–42. https://doi.org/10.1021/acs.jcim.6b00662

35. Rudik A, Bezhentsev V, Dmitriev A, Lagunin A, Filimonov D, Poroikov V. MetaTox — web application for generation of metabolic pathways and toxicity estimation. J Bioinform Comput Biol. 2019;17(1):1940001. https://doi.org/10.1142/S0219720019400018

36. Rudik A, Dmitriev A, Lagunin A, Filimonov D, Poroikov V. MetaPASS: a web application for analyzing the biological activity spectrum of organic compounds taking into account their biotransformation. Mol Inform. 2021;40(4):2000231. https://doi.org/10.1002/minf.202000231

37. Raevsky OA, Solodova SL, Lagunin AA, Poroikov VV. Computer modeling of blood–brain barrier permeability of physiologically active compounds. Biomeditsinskaya Khimiya. 2014;60(2):161–81 (In Russ.). https://doi.org/10.18097/PBMC20146002161

38. Ivanov SM, Lagunin AA, Poroikov VV. In silico assessment of adverse drug reactions and associated mechanisms. Drug Discov Today. 2016;21(1):58–71. https://doi.org/10.1016/j.drudis.2015.07.018

39. Ivanov SM, Lagunin AA, Pogodin PV, Filimonov DA, Poroikov VV. Identification of drug targets related to the induction of ventricular tachyarrhythmia through systems chemical biology approach. Toxicol Sci. 2015;145(2):321–36. https://doi.org/10.1093/toxsci/kfv054

40. Koborova ON, Filimonov DA, Zakharov AV, Lagunin AA, Ivanov SM, Kel A, Poroikov VV. In silico method for identification of promising anticancer drug targets. SAR QSAR Environ Res. 2009;20 (7–8):755–66. https://doi.org/10.1080/10629360903438628

41. Ivanov SM, Lagunin AA, Pogodin PV, Filimonov DA, Poroikov VV. Identification of drug-induced myocardial infarction-related protein targets through the prediction of drug–target interactions and analysis of biological processes. Chem Res Toxicol. 2014;27(7):1263–81. https://doi.org/10.1021/tx500147d

42. Poroikov VV, Filimonov DA, Gloriozova TA, Lagunin AA, Druzhilovskiy DS, Rudik AV, et al. Computer-aided prediction of biological activity spectra for organic compounds: the possibilities and limitations. Russ Chem Bull. 2019;(12):2143–54. https://doi.org/10.1007/s11172-019-2683-0

43. Ivanov S, Lagunin A, Filimonov D, Poroikov V. Assessment of the cardiovascular adverse effects of drug–drug interactions through a combined analysis of spontaneous reports and predicted drug–target interactions. PLoS Comput Biol. 2019;15(7):e1006851. https://doi.org/10.1371/journal.pcbi.1006851

44. Ivanov S, Lagunin A, Filimonov D, Poroikov V. Relationships between the structure and severe drug-induced liver injury for low, medium and high doses of drugs. Chem Res Toxicol. 2022;35(3):402–11. https://doi.org/0.1021/acs.chemrestox.1c00307

45. Sukhachev VS, Ivanov SM, Dmitriev AV. Prediction of adverse effects of drug–drug interactions on cardiovascular system based on the analysis of structure–activity relationships. Biochemistry (Moscow). 2023;88(5):630-39. https://doi.org/10.1134/S0006297923050061

46. Irurzun-Arana I, Rackauckas C, McDonald TO, Trocóniz IF. Beyond deterministic models in drug discovery and development. Trends Pharmacol Sci. 2020;41(11):882–95. https://doi.org/10.1016/j.tips.2020.09.005

47. Blanco MJ, Gardinier KM, Namchuk MN. Advancing new chemical modalities into clinical studies. ACS Med Chem Lett. 2022;13(11):1691–8. https://doi.org/10.1021/acsmedchemlett.2c00375

48. Bonner S, Barrett IP, Ye C, Swiers R, Engkvist O, Bender A, Hoyt CT, Hamilton WL. A review of bio medical datasets relating to drug discovery: a knowledge graph perspective. Brief Bioinform. 2022;23(6):bbac404. https://doi.org/10.1093/bib/bbac404

49. Hopkins AL. Network pharmacology: the next paradigm in drug discovery. Nat Chem Biol. 2008;4(11): 682–90. https://doi.org/10.1038/nchembio.118

50. Loscalzo J, Kohane I, Barabasi AL. Human disease classification in the postgenomic era: a complex systems approach to human pathobiology. Mol Syst Biol. 2007;3:124. https://doi.org/10.1038/msb4100163

51. Tarasova OA, Urusova AF, Filimonov DA, Nicklaus MC, Zakharov AV, Poroikov VV. QSAR modeling using large-scale databases: case study for HIV-1 reverse transcriptase inhibitors. J Chem Inf Model. 2015;55(7):1388–99. https://doi.org/10.1021/acs.jcim.5b00019

52. Alharbi E, Gadiya Y, Henderson D, Zaliani A, Delfi nRossaro A, Cambon-Thomsen A, et al. Selection of data sets for FAIRification in drug discovery and development: which, why, and how? Drug Discov Today. 2022;27(8):2080–5. https://doi.org/10.1016/j.drudis.2022.05.010

53. Perfilova VN. Opportunities and prospects for preclinical drug safety assessment using alternative methods: experience from the Toxicology in the 21st Century (Tox21) programme in the USA. Safety and Risk of Pharmacotherapy. 2023 (In Russ). https://doi.org/10.30895/2312-7821-2023-379

54. Tarasova OA, Biziukova NYu, Filimonov DA, Poroikov VV, Nicklaus MC. Data mining approach for extraction of useful information about biologically active compounds from publications. Journal of Chemical Information and Modeling. 2019;59(9):3635–44. https://doi.org/10.1021/acs.jcim.9b00164

55. Tarasova OA, Biziukova NYu, Rudik AV, Dmitriev AV, Filimonov DA, Poroikov VV. Extraction of data on parent compounds and their metabolites from texts of scientific abstracts. J Chem Inf Model. 2021;61(4):1683–90. https://doi.org/10.1021/acs.jcim.0c01054

56. Tarasova OA, Rudik AV, Biziukova NYu, Filimonov DA, Poroikov VV. Cheminform. 2022;14:55. https://doi.org/10.1186/s13321-022-00633-4