In Silico Prediction of Toxicological and Pharmacokinetic Characteristics of Medicinal Compounds

Scientific relevance. Studies of the toxicological and pharmacokinetic properties of medicinal compounds are a crucial stage of preclinical research; unsatisfactory results may invalidate further drug development. Therefore, the development of in silico methods for a preliminary pre-experimental assessment of toxicological and pharmacokinetic properties is a relevant and crucial task.

Aim. The study aimed to review current approaches to in silico prediction of the absorption, distribution, metabolism, excretion, and toxicity (ADMET) parameters of pharmacologically active compounds, in particular, the most important toxicological and pharmacokinetic parameters, and to present the results of the authors’ own research in this area.

Discussion. According to the review of models for predicting the toxicological properties of chemical compounds (acute toxicity, carcinogenicity, mutagenicity, genotoxicity, endocrine toxicity, cytotoxicity, cardiotoxicity, hepatotoxicity, and immunotoxicity), the accuracy of predictions ranged from 74.0% to 98.0%. According to the review of models for predicting the pharmacokinetic properties of chemical compounds (gastrointestinal absorption; oral bioavailability; volume of distribution; total, renal, and hepatic clearance; and half-life), the coefficient of determination for the predictions ranged from 0.265 to 0.920. The literature review showed that the most widely used methods for in silico assessment of the ADMET parameters of pharmacologically active compounds included the random forest method and the support vector machines method. The authors compared the literature data with the results they obtained by modelling 12 toxicological and pharmacokinetic properties of chemical compounds using the consensus method in the IT Microcosm system and artificial neural networks. IT Microcosm outperformed the models described in the literature in terms of predicting 2 toxicological properties, including carcinogenicity and blood–brain barrier penetration (the prediction accuracy reached 93.4%). Neural network models were superior in predicting 4 toxicological properties, including acute toxicity, carcinogenicity, genotoxicity, and blood–brain barrier penetration (the prediction accuracy reached 93.8%). In addition, neural network models were better in predicting 3 pharmacokinetic properties, including gastrointestinal absorption, volume of distribution, and hepatic clearance (the coefficient of determination reached 0.825).

Conclusions. The data obtained suggest that artificial neural networks are the most promising and practically significant direction for the development of in silico systems for predicting the ADMET characteristics of new medicinal products.

1. Tsaioun K, Kates SA, eds. ADMET for Medicinal Chemists: A Practical Guide. New York: Wiley; 2011.

2. Durnev AD. Pharmaceutical toxicology is the most important component of preclinical studies. Bulletin of the Scientific Centre for Expert Evaluation of Medicinal Products. Regulatory Research and Medicine Evaluation. 2023;13(1): 8–13 (In Russ.). https://doi.org/10.30895/1991-2919-2023-13-1-8-13

3. Boroujerdi M. Pharmacokinetics and Toxicokinetics. New York: CRC Press; 2015.

4. Shaker B, Ahmad S, Lee J, Jung C, Na D. In silico methods and tools for drug discovery. Comput Biol Med. 2021;137:104851. https://doi.org/10.1016/j.compbiomed.2021.104851

5. Chang Y, Hawkins BA, Du JJ, Groundwater PW, Hibbs DE, Lai F. A guide to in silico drug design. Pharmaceutics. 2023;15(1):49. https://doi.org/10.3390/pharmaceutics15010049

6. Sammut C, Webb GI, eds. Encyclopedia of machine learning. New York: Springer; 2011.

7. Devillers J, Balaban AT, eds. Topological indices and related descriptors in QSAR and QSPR. New York: CRC Press; 2000.

8. Vassiliev PM, Spasov AA Fragmentary encoding languages of compound structure for computer prediction of biological activity. Žurnal Vsesoûznogo himičeskogo obŝestva im. D.I. Mendeleeva . 2006;50(2):108–27 (In Russ.). EDN: HTUUSP

9. Engel T, Gasteiger J, eds. Chemoinformatics: Basic Concepts and Methods. Weinheim: Wiley-VCH; 2018.

10. Wang L, Ding J, Pan L, Cao D, Jiang H, Ding X. Quantum chemical descriptors in quantitative structure–activity relationship models and their applications. Chemometr Intell Lab Syst. 2021;217:104384. https://doi.org/10.1016/j.chemolab.2021.104384

11. Batool M, Ahmad B, Choi S. A structure-based drug discovery paradigm. Int J Mol Sci. 2019;20(11):2783. https://doi.org/10.3390/ijms20112783

12. Kar S, Leszczynski J. Open access in silico tools to predict the ADMET profiling of drug candidates. Expert Opin Drug Discov. 2020;15(12):1473–87. https://doi.org/10.1080/17460441.2020.1798926

13. Fahrmeir L, Kneib T, Lang S, Marx BD. Regression: models, methods and applications. New York: Springer; 2021.

14. Gramatica P. Principles of QSAR modeling: comments and suggestions from personal experience. Int J Quant Struct Prop Relatsh. 2020;5(3):61–97. https://doi.org/10.4018/IJQSPR.20200701.oa1

15. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12(85):2825–30.

16. Poroikov VV, Filimonov DA, Borodina YV, Lagunin AA, Kos A. Robustness of biological activity spectra predicting by computer program pass for noncongeneric sets of chemical compounds. J Med Chem. 2000;40(6):1349–55. https://doi.org/10.1021/ci000383k

17. Zhang Z. Introduction to machine learning: K-nearest neighbors. Ann Trans Med. 2016;4(11):218–24. https://doi.org/10.21037/atm.2016.03.37

18. Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press; 2000.

19. Genuer R, Poggi J-M. Random forests with R (Use R!). New York: Springer; 2020.

20. Jang IS, Ghazoui Z, Ahsen ME, Vogel R, Neto EC, Norman T, et al. Community assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen. Nat Commun. 2019;10(1):2674. https://doi.org/10.1038/s41467-019-09799-2

21. Aggarwal CC. Neural networks and deep learning: a textbook. New York: Springer; 2018.

22. Han S-H, Kim KW, Kim S, Youn YC. Artificial neural network: understanding the basic concepts without mathematics. Dement Neurocogn Disord. 2018;17(3):83–9. https://doi.org/10.12779/dnd.2018.17.3.83

23. Che J, Chen L, Guo ZH, Wang S, Aorigele С. Drug target group prediction with multiple drug networks. Comb Chem High Throughput Screen. 2020;23(4):274–84. https://doi.org/10.2174/1386207322666190702103927

24. Pinzi L, Rastelli G. Molecular docking: shifting paradigms in drug discovery. Int J Mol Sci. 2019;20(18):4331. https://doi.org/10.3390/ijms20184331

25. Wang Z, Sun H, Yao X, Li D, Xu L, Li Y, et al. Comprehensive evaluation of ten docking programs on a diverse set of protein-ligand complexes: the prediction accuracy of sampling power and scoring power. Phys Chem Chem Phys. 2016;18(18):12964–75. https://doi.org/10.1039/c6cp01555g

26. Trott O, Olson AJ. AutoDock Vina: improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. J Comput Chem. 2010;31(2):455–61. https://doi.org/10.1002/jcc.21334

27. Dickson CJ, Velez-Vega C, Duca JS. Revealing molecular determinants of hERG blocker and activator binding. J Chem Inf Model. 2020;60(1):192–203. https://doi.org/10.1021/acs.jcim.9b00773

28. Plewczynski D, Łaźniewski M, Augustyniak R, Ginalski K. Can we trust docking results? Evaluation of seven commonly used programs on PDBbind database. J Comput Chem. 2011;32(4):742–55. https://doi.org/10.1002/jcc.21643

29. Joshi T, Sharma P, Joshi T, Pundir H, Mathpal S, Chandra S. Structure-based screening of novel lichen compounds against SARS Coronavirus main protease (Mpro) as potentials inhibitors of COVID-19. Mol Divers. 2021;25(3):1665–77. https://doi.org/10.1007/s11030-020-10118-x

30. Lipinski CA, Lombardo F, Dominy BW, Feeney PJ. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev. 2001;46(1-3):3–26. https://doi.org/10.1016/s0169-409x(00)00129-0

31. Oprea TI. Property distribution of drug-related chemical databases. J Comput Aided Mol Des. 2000;14(3):251–64. https://doi.org/10.1023/a:1008130001697

32. Veber DF, Johnson SR, Cheng H-Y, Smith BR, Ward KW, Kopple KD. Molecular properties that influence the oral bioavailability of drug candidates. J Med Chem. 2002;45(12):2615–23. https://doi.org/10.1021/jm020017n

33. Ghose AK, Viswanadhan VN, Wendoloski JJ. A knowledge-based approach in designing combinatorial or medicinal chemistry libraries for drug discovery. 1. A qualitative and quantitative characterization of known drug databases. J Comb Chem. 1999;1(1):55–68. https://doi.org/10.1021/cc9800071

34. Pardridge WM. CNS drug design based on principles of blood-brain barrier transport. J Neurochem. 1998;70(5):1781–92. https://doi.org/10.1046/j.1471-4159.1998.70051781.x

35. Bickerton GR, Paolini Gaia V, Besnard J, Muresan S, Hopkins AL. Quantifying the chemical beauty of drugs. Nat Chem. 2012;4(2):90–8. https://doi.org/10.1038/nchem.1243

36. Ahlberg E, Carlsson L, Boyer S. Computational derivation of structural alerts from large toxicology data sets. J Chem Inf Model. 2014;54(10):2945–52. https://doi.org/10.1021/ci500314a

37. Daina A, Michielin O, Zoeteb V. SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules. Sci Rep. 2017;7:42717. https://doi.org/10.1038/srep42717

38. O’Boyle NM, Banck M, James CA, Morley C, Vandermeersch T, Hutchison GR. Open Babel: an open chemical toolbox. J Cheminform. 2011;3(1):33. https://doi.org/10.1186/1758-2946-3-33

39. Banerjee P, Eckert AO, Schrey AK, Preissner R. ProTox-II: a webserver for the prediction of toxicity of chemicals. Nucleic Acids Res. 2018;46(W1):W257–63. https://doi.org/10.1093/nar/gky318

40. Pires DEV, Blundell TL, Ascher DB. pkCSM: predicting small-molecule pharmacokinetic and toxicity properties using graph-based signatures. J Med Chem. 2015;58:4066–72. https://doi.org/10.1021/acs.jmedchem.5b00104

41. Dong J, Wang N-N, Yao Z-J, Zhang L, Cheng Y, Ouyang D, et al. ADMETlab: a platform for systematic ADMET evaluation based on a comprehensively collected ADMET database. J Cheminform. 2018;10(1):29. https://doi.org/10.1186/s13321-018-0283-x

42. Yang H, Lou C, Sun L, Li J, Cai Y, Wang Z, et al. admetSAR 2.0: web-service for prediction and optimization of chemical ADMET properties. Bioinformatics. 2019;35(6):1067–69. https://doi.org/10.1093/bioinformatics/bty707

43. Lunghini F, Marcou G, Azam P, Horvath D, Patoux R, Van Miert E, et al. Consensus models to predict oral rat acute toxicity and validation on a dataset coming from the industrial context. SAR QSAR Environ Res. 2019;30(12):879–97. https://doi.org/10.1080/1062936X.2019.1672089

44. Ruggiu F, Marcou G, Varnek A, Horvath D. ISIDA property-labelled fragment descriptors. Mol Inform. 2010;29(12):855–68. https://doi.org/10.1002/minf.201000099

45. Sosnin S, Karlov D, Tetko IV, Fedorov MV. Comparative study of multitask toxicity modeling on a broad chemical space. J Chem Inf Model. 2018;59(3):1062–72. https://doi.org/10.1021/acs.jcim.8b00685

46. Tice RR, Bassan A, Amberg A, Anger LT, Beal MA, Bellion P, et al. In silico approaches in carcinogenicity hazard assessment: current status and future needs. Comput Toxicol. 2021;20:100191. https://doi.org/10.1016/j.comtox.2021.100191

47. Zhong M, Nie X, Yan A, Yuan Q. Carcinogenicity prediction of noncongeneric chemicals by a support vector machine. Chem Res Toxicol. 2013;26(5):741–9. https://doi.org/10.1021/tx4000182

48. Sushko I, Novotarskyi S, Körner R, Pandey AK, Kovalishyn VV, Prokopenko VV, et al. Applicability domain for in silico models to achieve accuracy of experimental measurements. J Chemom. 2010;24(3–4):202–8. https://doi.org/10.1002/cem.1296

49. Xu C, Cheng F, Chen L, Du Z, Li W, Liu G, et al. In silico prediction of chemical Ames mutagenicity. J Chem Inf Model. 2012;52(11):2840–7. https://doi.org/10.1021/ci300400a

50. Patlewicz G, Jeliazkova N, Safford RJ, Worth AP, Aleksiev B. An evaluation of the implementation of the Cramer classification scheme in the Toxtree software. SAR QSAR Environ Res. 2008;19(5–6):495–524. https://doi.org/10.1080/10629360802083871

51. Strelkova YuN. Concepts of “genotoxicity” and “mutagenicity”. In: Advances in science and technology. Collected papers of XXVI international scientific-practical conference. Moscow: Actualnost.RF; 2020. Part 1. P. 37–8 (In Russ.). EDN: IKZUNJ

52. Baderna D, Van Overmeire I, Lavado GJ, Gadaleta D, Mertens B. In silico Methods for chromosome damage. In: In silico methods for predicting drug toxicity. New York: Springer US; 2022. P. 185–200. https://doi.org/10.1007/978-1-0716-1960-5_8

53. Kusko R, Hong H. Machine learning and deep learning promote computational toxicology for risk assessment of chemicals. In: Machine learning and deep learning in computational toxicology. Cham: Springer International Publishing; 2023. P. 1–17. https://doi.org/10.1007/978-3-031-20730-3

54. Baderna D, Gadaleta D, Lostaglio E, Selvestrel G, Raitano G, Golbamaki A, et al. New in silico models to predict in vitro micronucleus induction as marker of genotoxicity. J Hazard Mater. 2020;385:121638. https://doi.org/10.1016/j.jhazmat.2019.121638

55. Ferrari T, Cattaneo D, Gini G, Bakhtyari NG, Manganaro A, Benfenati E. Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction. SAR QSAR Environ Res. 2013;24(5):365–83. https://doi.org/10.1080/1062936x.2013.773376

56. Combarnous Y, Diep Nguyen TM. Comparative overview of the mechanisms of action of hormones and endocrine disruptor compounds. Toxics. 2019;7(1):5–14. https://doi.org/10.3390/toxics7010005

57. La Merrill MA, Vandenberg LN, Smith MT, Goodson W, Browne P, Patisaul HB, et al. Consensus on the key characteristics of endocrine-disrupting chemicals as a basis for hazard identification. Nat Rev Endocrinol. 2020;16(1):45–57. https://doi.org/10.1038/s41574-019-0273-8

58. Ruiz P, Sack A, Wampole M, Bobst S, Vracko M. Integration of in silico methods and computational systems biology to explore endocrine-disrupting chemical binding with nuclear hormone receptors. Chemosphere. 2021;178:99–109. https://doi.org/10.1016/j.chemosphere.2017.03.026

59. Matsuzaka Y, Uesawa Y. Molecular image-based prediction models of nuclear receptor agonists and antagonists using the deepsnap-deep learning approach with the Tox21 10K library. Molecules. 2020;25(12):2764. https://doi.org/10.3390/MOLECULES25122764

60. Collins SP, Barton-Maclaren TS. Novel machine learning models to predict endocrine disruption activity for high-throughput chemical screening. Front Toxicol. 2022;4:1–13. https://doi.org/10.3389/ftox.2022.981928

61. Kim S, Chen J, Cheng T, Gindulyte A, He J, He S, et al. PubChem 2019 update: improved access to chemical data. Nucleic Acids Res. 2019;47(D1):D1102–D1109. https://doi.org/10.1093/nar/gky1033

62. Halle W, Halder M, Worth A, Genschow E. The registry of cytotoxicity: toxicity testing in cell cultures to predict acute toxicity (LD50) and to reduce testing in animals. Altern Lab Anim. 2003;31(2):89–198. https://doi.org/10.1177/026119290303100204

63. Petrescu AM, Paunescu V, Ilia G. The antiviral activity and cytotoxicity of 15 natural phenolic compounds with previously demonstrated antifungal activity. J Environ Sci Health B. 2019;54(6):498–504. https://doi.org/10.1080/03601234.2019.1574176

64. Chuipu C, Guo P, Zhou Y, Zhou J, Wang Q, Zhang F, et al. Deep learning-based prediction of drug-induced cardiotoxicity. J Chem Inf Model. 2019;59(3):1073–84. https://doi.org/10.1021/acs.jcim.8b00769

65. He S, Ye T, Wang R, Zhang C, Zhang X, Sun G, et al. An in s ilico model for predicting drug-induced hepatotoxicity. Int J Mol Sci. 2019;20(8):1897. https://doi.org/10.3390/ijms20081897

66. Ye H, Nelson LJ, Moral MGD, Martínez-Naves E, Cubero FJ. Dissecting the molecular pathophysiology of drug-induced liver injury. World J Gastroenterol. 2018;24(13):1373–85. https://doi.org/10.3748/wjg.v24.i13.1373

67. García-Cañaveras JC, Jiménez N, Gómez-Lechón MJ, Castell JV, Donato MT, Lahoz A. LC-MS untargeted metabolomic analysis of drug-induced hepatotoxicity in HepG2 cells. Electrophoresis. 2015;36(18):2294–302. https://doi.org/10.1002/elps.201500095

68. Kim E, Nam H. Prediction models for drug-induced hepatotoxicity by using weighted molecular fingerprints. BMC Bioinformatics. 2017;18(Suppl 7):25–34. https://doi.org/10.1186/s12859-017-1638-4

69. Turabekova M, Rasulev B, Theodore M, Jackman J, Leszczynska D, Leszczynski J. Immunotoxicity of nanoparticles: a computational study suggests that CNTs and C60 fullerenes might be recognized as pathogens by Toll-like receptors. Nanoscale. 2014;6(7):3488–95. https://doi.org/10.1039/C3NR05772K

70. Roos C. Intestinal absorption of drugs: the impact of regional permeability, nanoparticles, and absorption-modifying excipients. Uppsala: Acta Universitatis Upsaliensis; 2018.

71. Venkatraman V. FP-ADMET: a compendium of fingerprint-based ADMET prediction models. J Cheminform. 2021;13(1):75–86. https://doi.org/10.1186/s13321-021-00557-5

72. Wang N-N, Huang C, Dong J, Yao Z-J, Zhu M-F, Deng Z-K, et al. Predicting human intestinal absorption with modified random forest approach: a comprehensive evaluation of molecular representation, unbalanced data, and applicability domain issues. RSC Adv. 2017;7(31):19007–18. https://doi.org/10.1039/C6RA28442F

73. Kumar R, Sharma A, Siddiqui MH, Tiwari RK. Prediction of human intestinal absorption of compounds using artificial intelligence techniques. Curr Drug Discov Technol. 2017;14(4):244–54. https://doi.org/10.2174/1570163814666170404160911

74. Миронов АН, ред. Руководство по проведению доклинических исследований лекарственных средств. Ч. 2. М.: Гриф и К; 2012.

75. Fagerholm U, Hellberg S, Spjuth O. Advances in predictions of oral bioavailability of candidate drugs in man with new machine learning methodology. Molecules. 2021;26(9):2572–82. https://doi.org/10.3390/molecules26092572

76. Ye Z, Yang Y, Li X, Cao D, Ouyang D. An integrated transfer learning and multitask learning approach for pharmacokinetic parameter prediction. Mol Pharm. 2019;16(2):533–41. https://doi.org/10.1021/acs.molpharmaceut.8b00816

77. Currie GM. Pharmacology, part 2: Introduction to pharmacokinetics. J Nucl Med Technol. 2018;46(3):221–30. https://doi.org/10.2967/jnmt.117.199638

78. Murad N, Pasikanti KK, Madej BD, Minnich A, McComas JM, Crouch S, et al. Predicting volume of distribution in humans: performance of in silico methods for a large set of structurally diverse clinical compounds. Drug Metab Dispos. 2021;49(2):169–78. https://doi.org/10.1124/dmd.120.000202

79. Lombardo F, Bentzien J, Berellini G, Muegge I. In silico models of human PK parameters. Prediction of volume of distribution using an extensive data set and a reduced number of parameters. J Pharm Sci. 2021;110(1):500–9. https://doi.org/10.1016/j.xphs.2020.08.023

80. Kosugi Y, Hosea N. Direct comparison of total clearance prediction: computational machine learning model versus bottom-up approach using in vitro assay. Mol Pharm. 2020;17(7):2299–309. https://doi.org/10.1021/acs.molpharmaceut.9b01294

81. Wang Y, Liu H, Fan Y, Chen X, Yang Y, Zhu L, et al. In silico prediction of human intravenous pharmacokinetic parameters with improved accuracy. J Chem Inf Model. 2019;59(9):3968–80. https://doi.org/10.1021/acs.jcim.9b00300

82. Chen J, Yang H, Zhu L, Wu Z, Li W, Tang Y, et al. In silico prediction of human renal clearance of compounds using quantitative structure-pharmacokinetic relationship models. Chem Res Toxicol. 2020;33(2):640–50. https://doi.org/10.1021/acs.chemrestox.9b00447

83. Watanabe R, Ohashi R, Esaki T, Kawashima H, Natsume-Kitatani Y, Nagao C, et al. Development of an in silico prediction system of human renal excretion and clearance from chemical structure information incorporating fraction unbound in plasma as a descriptor. Sci Rep. 2019;9(1):18782– 92. https://doi.org/10.1038/s41598-019-55325-1

84. Dawson DE, Ingle BL, Phillips KA, Nichols JW, Wambaugh JF, Tornero-Velez R. Designing QSARs for parameters of high-throughput toxicokinetic models using open-source descriptors. Environ Sci Technol. 2021;55(9):6505–17. https://doi.org/10.1021/acs.est.0c06117

85. Feinberg EN, Joshi E, Pande VS, Cheng AC. Improvement in ADMET prediction with multitask deep featurization. J Med Chem. 2020;63(16):8835–48. https://dx.doi.org/10.1021/acs.jmedchem.9b02187

86. Vassiliev PM, Spasov AA, Kosolapov VA, Kucheryavenko AF, Gurova NA, Anisimova VA. Consensus drug design using IT Microcosm. In: Gorb L, Kuz’min V, Muratov E, eds. Application of computational techniques in pharmacy and medicine; challenges and advances in computational chemistry and physics. Vol. 17. Springer, Dordrecht; 2014. P. 369–431. https://doi.org/10.1007/978-94-017-9257-8_12

87. Вао//doi.org/10.19163/1994-9480-2020-1(73)-31-33

88. Vassiliev PM, Spasov AA, Kochetkov AN, Babkov DA, Litvinov RA. Consensus in silico prediction of the carcinogenic hazard of multitarget RAGE inhibitors. Volgograd Scientific and Medical Journal. 2020;(1):55–7 (In Russ.). EDN: TJAFRE

89. Vassiliev PM, Spasov AA, Kochetkov AN, Perfiliev MA, Koroleva AR, Golubeva AV, et al. In silico consensus assessment of the overall safety of multitarget RAGE inhibitors. Volgograd Scientific and Medical Journal. 2020;(2):47–51 (In Russ.). EDN: VYKKZP

90. Vassiliev PM, Spasov AA, Kochetkov AN, Perfiliev MA, Koroleva AR, Golubeva AV, et al. In silico consensus prediction of pharmacokinetic preference for multitarget RAGE inhibitors. Journal of Volgograd State Medical University. 2020;(2):100–4 (In Russ.). https://doi.org/10.19163/1994-9480-2020-2(74)-100-104

91. Tomasulo P. ChemIDplus — super source for chemical and drug information. Med Ref Serv. 2002;21(1):53–9. https://doi.org/10.1300/j115v21n01_04

92. IARC Monographs on the Evaluation of Carcinogenic Risks to Humans. Vol. 1–131. Lyon: IARC; 1972–2023.

93. Mendez D, Gaulton A, Bento AP, Chambers J, De Veij M, Felix E, et al. ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res. 2019;47(D1):D930–40. https://doi.org/10.1093/nar/gky1075

94. Karthikeyan BS, Ravichandran J, Aparna SR, Samal A. DEDuCT 2.0: An updated knowledgebase and an exploration of the current regulations and guidelines from the perspective of endocrine disrupting chemicals. Chemosphere. 2021;267:128898. https://doi.org/10.1016/j.chemosphere.2020.128898

95. Wang Z, Yang H, Wu Z, Wang T, Li W, Tang Y, et al. In silico prediction of blood–brain barrier permeability of compounds by machine learning and resampling methods. Chem Med Chem. 2018;13(20):2189–201. https://doi.org/10.1002/cmdc.201800533

96. Kolmogorov AN. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Proc. USSR Acad. Sci. 1957;114(5):953–6 (In Russ.).

97. Shen J, Cheng F, Xu Y, Li W, Tang Y. Estimation of ADME properties with substructure pattern recognition. J Chem Inf Model. 2010;50(6):1034–41. https://doi.org/10.1021/ci100104j

98. Hilbe JM. Statistica 7: an overview. Am Stat. 2007;61(1): 91–4.

99. Li H, Ung CY, Yap CW, Xue Y, Li ZR, Cao ZW, et al. Prediction of genotoxicity of chemical compounds by statistical learning methods. Chem Res Toxicol. 2005;18(6):1071–80. https://doi.org/10.1021/tx049652h

100. Yan A, Wang Z, Cai Z. Prediction of human intestinal absorption by GA feature selection and support vector machine regression. Int J Mol Sci. 2008;9(10):1961–76. https://doi.org/10.3390/ijms9101961