The search for polyphenolic inhibitors of BTK (Bruton’s tyrosine kinase) for the treatment of multiple sclerosis using machine learning methods

Objective: development of a machine learning model to predict the inhibitory activity of natural compounds, predominantly of a polyphenolic nature, against Bruton’s tyrosine kinase (BTK), with the aim of identifying potential candidates for the treatment of multiple sclerosis (MS) with a favourable safety profile.

Material and methods. To construct the model, data from the ChEMBL database on BTK inhibitors (CHEMBL5251) were used, containing values for the concentration required to inhibit 50 per cent of the activity (IC₅₀). The IC₅₀ values were converted to the pIC₅₀ format. Molecular structures were represented as ECFP6 fingerprints using the RDKit library. To model the ‘structure–activity’ relationship, the Bayesian Ridge Regression method from the scikit-learn library was applied. Model quality was assessed using the coefficient of determination (R2), as well as Pearson’s and Spearman’s correlation coefficients between the experimental and predicted pIC₅₀ values. The resulting model was used to screen polyphenolic compounds.

Results. A machine learning model was developed to predict the inhibitory activity of compounds against BTK. The Pearson and Spearman correlation coefficients between the experimental and predicted pIC₅₀ values were 0.8; the coefficient of determination (R2) was 0.6. In a virtual screening of 21 compounds, rutin demonstrated the highest predicted activity among the polyphenols (predicted IC₅₀ – 24 nM). High predicted BTK inhibitory activity was also identified for luteolin, baicalein, epicatechin and quercetin.

Conclusion. Machine learning methods represent a promising tool for identifying new BTK inhibitors amongst natural compounds. The results obtained indicate the potential ability of a number of polyphenols to inhibit BTK and confirm the value of further experimental investigation of these compounds as candidates for the treatment of MS.

1. Torke S, Weber MS. Inhibition of Bruton s tyrosine kinase as a novel therapeutic approach in multiple sclerosis. Expert Opin Investig Drugs. 2020;29:1143-50. doi: 10.1080/13543784.2020.1807934

2. Cohen P, Cross D, Janne PA. Kinase drug discovery 20 years after imatinib: progress and future directions. Nat Rev Drug Discov. 2021;20:551-69. doi: 10.1038/s41573-021-00195-4

3. Druker BJ, Talpaz M, Resta DJ, et al. Efficacy and safety of a specific inhibitor of the BCR-ABL tyrosine kinase in chronic myeloid leukemia. N Engl J Med. 2001;344:1031-7. doi: 10.1056/NEJM200104053441401

4. McDonald C, Xanthopoulos C, Kostareli E. The role of Bruton's tyrosine kinase in the immune system and disease. Immunology. 2021;164:722-36. doi: 10.1111/imm.13416

5. Kramer J, Bar-Or A, Turner TJ, Wiendl H. Bruton tyrosine kinase inhibitors for multiple sclerosis. Nat Rev Neurol. 2023;19:289-304. doi: 10.1038/s41582-023-00800-7

6. Airas L, Bermel RA, Chitnis T, et al. A review of Bruton's tyrosine kinase inhibitors in multiple sclerosis. Ther Adv Neurol Disord. 2024;17:17562864241233041. doi: 10.1177/17562864241233041

7. Elkjaer ML, Waede MR, Kingo C, et al. Expression of Bruton s tyrosine kinase in different type of brain lesions of multiple sclerosis patients and during experimental demyelination. Front Immunol. 2023;14:1264128. doi: 10.3389/fimmu.2023.1264128

8. Broccoli A, Del Re M, Danesi R, Zinzani PL. Covalent Bruton tyrosine kinase inhibitors across generations: A focus on zanubrutinib. J Cell Mol Med. 2025;29:e70170. doi: 10.1111/jcmm.70170

9. Byrd JC, Brown JR, O’Brien S, et al. Ibrutinib versus ofatumumab in previously treated chronic lymphoid leukemia. N Engl J Med. 2014;371:213-23. doi: 10.1056/NEJMoa1400376

10. Fraga CG, Croft KD, Kennedy DO, Tomas-Barberan FA. The effects of polyphenols and other bioactives on human health. Food Funct. 2019;10:514-28. doi: 10.1039/c8fo01997e

11. Jeong H, Phan ANH, Choi JW. Anti-cancer Effects of Polyphenolic Compounds in Epidermal Growth Factor Receptor Tyrosine Kinase Inhibitor-resistant Non-small Cell Lung Cancer. Pharmacogn Mag. 2017;13:595-9. doi: 10.4103/pm.pm_535_16

12. Dirimanov S, Hogger P. Screening of Inhibitory Effects of Polyphenols on Akt-Phosphorylation in Endothelial Cells and Determination of Structure-Activity Features. Biomolecules. 2019;9(6):219. doi: 10.3390/biom9060219

13. Stokes JM, Yang K, Swanson K, et al. A Deep Learning Approach to Antibiotic Discovery. Cell. 2020;180:688-702. doi: 10.1016/j.cell.2020.01.021

14. Zdrazil B, Felix E, Hunter F, et al. The ChEMBL Database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Res. 2024;52:D1180-D1192. doi: 10.1093/nar/gkad1004

15. Davies M, Nowotka M, Papadatos G, et al. ChEMBL web services: streamlining access to drug discovery data and utilities. Nucleic Acids Res. 2015;43:W612-20. doi: 10.1093/nar/gkv352

16. Bar-Or A, Dufek M, Budincevic H, et al. Safety and efficacy of fenebrutinib in relapsing multiple sclerosis (FENopta): a multicentre, double-blind, randomised, placebo-controlled, phase 2 trial and open-label extension study. Lancet Neurol. 2025;24:656-66. doi: 10.1016/S1474-4422(25)00174-7

17. Hoessel R, Leclerc S, Endicott JA, et al. Indirubin, the active constituent of a Chinese antileukaemia medicine, inhibits cyclindependent kinases. Nat Cell Biol. 1999;1:60-7. doi: 10.1038/9035

18. Boly R, Gras T, Lamkami T, et al. Quercetin inhibits a large panel of kinases implicated in cancer cell biology. Int J Oncol. 2011;38:833-42. doi: 10.3892/ijo.2010.890

19. Oh KS, Oh BK, Park CH, et al. Baicalein potently inhibits Rho kinase activity and suppresses actin stress fiber formation in angiotensin II-stimulated H9c2 cells. Biol Pharm Bull. 2012;35:1281-6. doi: 10.1248/bpb.b12-00121

20. Zhu Y, Bao G, Zhu G, et al. Discovery and characterization of natural product luteolin as an effective inhibitor of human pyridoxal kinase. Bioorg Chem. 2024;143:107057. doi: 10.1016/j.bioorg.2023.107057

21. Tian H, Zhang Y, Xiao S, et al. Luteolin rescues myelin integrity and cognitive-motor function via Nrf2 pathway activation: a natural candidate vs. dimethyl fumarate in cuprizoneinduced multiple sclerosis. Nutr Neurosci. 2026 Jun;29(6):764-80. doi: 10.1080/1028415X.2025.2599459

22. Zhang Y, Li X, Ciric B, et al. Therapeutic effect of baicalin on experimental autoimmune encephalomyelitis is mediated by SOCS3 regulatory pathway. Sci Rep. 2015;5:17407. doi: 10.1038/srep17407

23. Petracca M, Quarantelli M, Moccia M, et al. ProspeCtive study to evaluate efficacy, safety and tOlerability of dietary supplemeNT of Curcumin (BCM95) in subjects with Active relapsing MultIple Sclerosis treated with subcutaNeous Interferon beta 1a 44 mcg TIW (CONTAIN): A randomized, controlled trial. Mult Scler Relat Disord. 2021;56:103274. doi: 10.1016/j.msard.2021.103274

24. Kukushkina A, Rogovskii V, Zhilenkova O, et al. Anti-Inflammatory Properties of Curcumin as Add-On Therapy in Patients with MS – Prospective, Comparative, Randomized, Pilot Study. Pharmaceutics. 2026;18:519.

25. Dolati S, Ahmadi M, Aghebti-Maleki L, et al. Nanocurcumin is a potential novel therapy for multiple sclerosis by influencing inflammatory mediators. Pharmacol Rep. 2018;70:1158- 67. doi: 10.1016/j.pharep.2018.05.008

26. Golonko A, Lewandowska H, Swislocka R, et al. Curcumin as tyrosine kinase inhibitor in cancer treatment. Eur J Med Chem. 2019;181:111512. doi: 10.1016/j.ejmech.2019.07.015

27. Muvhulawa N, Dludla PV, Ziqubu K, et al. Rutin ameliorates inflammation and improves metabolic function: A comprehensive analysis of scientific literature. Pharmacol Res. 2022;178:106163, doi: 10.1016/j.phrs.2022.106163

28. Manach C, Morand C, Demigne C, et al. Bioavailability of rutin and quercetin in rats. FEBS Lett. 1997;409:12-6. doi: 10.1016/s0014-5793(97)00467-5

29. Erlund I, Kosonen T, Alfthan, G, et al. Pharmacokinetics of quercetin from quercetin aglycone and rutin in healthy volunteers. Eur J Clin Pharmacol. 2000;56:545-53. doi: 10.1007/s00228000019