A generative neural network based on a hetero-encoder model for de novo design of potential anticancer drugs: application to Bcr-Abl tyrosine kinase

Objectives. The problem of developing a generative hetero-encoder model for computer-aided design of potential inhibitors of Bcr-Abl tyrosine kinase, an enzyme whose activity is the pathophysiological cause of chronic myeloid leukemia, is being solved.

Methods. A generative hetero-encoder model was designed based on the recurrent and fully connected neural networks of direct propagation. Training and testing of this model were carried out on a set of chemical compounds containing 2-arylaminopyrimidine, which is present as the main pharmacophore in the structures of many small-molecule inhibitors of protein kinases.

Results. The developed neural network was tested in the process of generating a wide range of new molecules and subsequent analysis of their chemical affinity for Bcr-Abl tyrosine kinase using molecular docking methods.

Conclusion. It is shown that the developed neural network is a promising mathematical model for de novo design of small molecules which are potentially active against Bcr-Abl tyrosine kinase and can be used to develop effective broad-spectrum anticancer drugs.

1. Vamathevan J., Clark D., Czodrowski P., Dunham I., Ferran E., ..., Zhao S. Applications of machine learning in drug discovery and development. Nature Reviewers. Drug Discovery, 2019, vol. 18, no. 6, pp. 463-477. https://doi.org/10.1038/s41573-019-0024-5

2. Lipinski C. F., Maltarollo V. G., Oliveira P. R., da Silva A. B. F., Honorio K. M. Advances and perspectives in applying deep learning for drug design and discovery. Frontiers in Robotics and AI, 2019, vol. 6, art. 108. Available at: https://www.frontiersin.org/artides/10.3389/frobt.2019.00108/full (accessed 07.08.2023). https://doi.org/10.3389/frobt.2019.00108

3. Cramer P. AlphaFold2 and the future of structural biology. Nature Structural & Molecular Biology, 2021, vol. 28, no. 9, pp. 704-705.

4. Bryant P., Pozzati G., Elofsson A. Improved prediction of protein-protein interactions using AlphaFold2. Nature Communications, 2022, vol. 13, no. 1, art. 1265. Available at: https://www.nature.com/articles/s41467-022-29480-5 (accessed 07.08.2023). https://doi.org/10.1038/s41467-022-29480-5

5. David A., Islam S., Tankhilevich E., Sternberg M. J. The AlphaFold database of protein structures: a biologist's guide. Journal of Molecular Biology, 2022, vol. 434, no. 2, p. 167336.

6. Timmons P. B., Hewage C. M. ENNAVIA is a novel method which employs neural networks for antiviral and anti-coronavirus activity prediction for therapeutic peptides. Briefings in Bioinformatics, 2021, vol. 22, iss. 6, art. bbab258. Available at: https://academic.oup.com/bib/article/22/6/bbab258/6326528 (accessed 07.08.2023). https://doi.org/10.1093/bib/bbab258

7. Andrianov A. M., Nikolaev G. I., Shuldov N. A., Bosko I. P., Anischenko A. I., Tuzikov A. V. Application of deep learning and molecular modeling to identify small drug-like compounds as potential HIV-1 entry inhibitors. Journal if Biomolecular Structure and Dynamics, 2022, vol. 40, no. 16, pp. 7555-7573. https://doi.org/10.1080/07391102.2021.1905559

8. Zhang Y., Ye T., Xi H., Juhas M., Li J. Deep learning driven drug discovery: Tackling Severe Acute Respiratory Syndrome Coronavirus 2. Frontiers in Microbiology, 2021, vol. 12. Available at: https://www.frontiersin.org/articles/10.3389/fmicb.2021.739684/full (accessed 07.08.2023). https://doi.org/10.3389/fmicb.2021.739684

9. Stokes J. M., Yang K., Swanson K., Jin W., Cubillos-Ruiz A., .., Collins J. J. A deep learning approach to antibiotic discovery. Cell, 2020, vol. 180, no. 4, art. e13, pp. 688-702. https://doi.org/10.1016/j.cell.2020.01.021

10. Mercado R., Rastemo T., Lindelof E., Klambauer G., Engkvist O., Bjerrum E. J. Practical notes on building molecular graph generative models. ChemRxiv, 2020. Available at: https://chemrxiv.org/engage/chemrxiv/article-details/60c74f55567dfe705bec5672 (accessed 07.08.2023). https://doi.org/10.26434/chemrxiv.12888383

11. Arús-Pous J., Blaschke T., Ulander S., Reymond J. L., Chen H., Engkvist O. Exploring the GDB-13 chemical space using deep generative models. Journal of Cheminformatics, 2019, vol. 11, art. 20. Available at: https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0341-z (accessed 07.08.2023). https://doi.org/10.1186/s13321-019-0341-z

12. Prykhodko O., Johansson S. V., Kotsias P. C., Arus-Pous J., Bjerrum E. J., ., Chen H. A de novo molecular generation method using latent vector based generative adversarial network. Journal of Cheminformatics, 2019, vol. 11, no 1, art. 74. Available at: https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0397-9 (accessed 07.08.2023). https://doi.org/10.1186/s13321-019-0397-9

13. Polykovskiy D., Zhebrak A., Vetrov D., Ivanenkov Y., Aladinskiy V., ., Kadurin A. Entangled conditional adversarial autoencoder for de novo drug discovery. Molecular Pharmaceutics, 2018, vol. 15, no. 10, pp. 4398-4405. https://doi.org/10.1021/acs.molpharmaceut.8b00839s

14. Zhang J., Mercado R., Engkvist O., Chen H. Comparative study of deep generative models on chemical space coverage. Journal of Chemical Information and Modeling, 2021, vol. 61, no. 6, pp. 2572-2581. https://doi.org/10.26434/chemrxiv.13234289.v1

15. Zhavoronkov A., Ivanenkov Y. A., Aliper A., Veselov M. S., Aladinskiy V. A., ., Aspuru-Guzik A. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nature Biotechnology, 2019, vol. 37, no. 9, pp. 1038-1040. https://doi.org/10.1038/s41587-019-0224-x

16. Kostler W. J., Zielinski C. C. Targeting receptor tyrosine kinases in cancer. Receptor Tyrosine Kinases: Structure, Functions and Role in Human Disease. New York, Springer, 2015, pp. 225-278.

17. Kantarjian H. M., Hochhaus A., Saglio G., De Souza C., Flinn I. W., Hughes T. P. Nilotinib versus imatinib for the treatment of patients with newly diagnosed chronic phase, Philadelphia chromosome-positive, chronic myeloid leukaemia: 24-month minimum follow-up of the phase 3 randomised ENESTnd trial. The Lancet Oncology, 2011, vol. 12, no. 9, pp. 841-851. https://doi.org/10.1016/S1470-2045(11)70201-7

18. Tan F. H., Putoczki T. L., Stylli S. S., Luwor R. B. Ponatinib: a novel multi-tyrosine kinase inhibitor against human malignancies. OncoTargets and Therapy, 2019, vol. 12, pp. 635-645. https://doi.org/10.2147/OTT.S189391

19. O'Hare T. A decade of nilotinib and dasatinib: From in vitro studies to first-line tyrosine kinase inhibitors. Cancer Research, 2016, vol. 76, no. 20, pp. 5911-5913. https://doi.org/10.1158/0008-5472.CAN-16-2483

20. Brummendorf T. H., Cortes J. E., de Souza C. A., Guilhot F., Duvillie L., ...., Gambacorti-Passerini C. Bosutinib versus imatinib in newly diagnosed chronic-phase chronic myeloid leukaemia: Results from the 24-month follow-up of the BELA trial. British Journal of Haematology, 2015, vol. 168, no. 1, pp. 69-81. https://doi.org/10.1111/bjh.13108

21. Bhullar K. S., Lagaron N. O., McGowan E. M., Parmar I., Jha A., Rupasinghe H. P. V. Kinase- targeted cancer therapies: progress, challenges and future directions. Molecular Cancer, 2018, vol. 17, art. 48. Available at: https://molecular-cancer.biomedcentral.com/articles/10.1186/s12943-018-0804-2 (accessed 07.08.2023). https://doi.org/10.1186/s12943-018-0804-2

22. Koroleva E. V., Ignatovich Zh. I., Sinyutich Yu. V., Gusak K. N. Aminopyrimidine derivatives as protein kinases inhibitors. Molecular design, synthesis, and biologic activity. Russian Journal of Organic Chemistry, 2016, vol. 52, no. 2, pp. 139-177. https://doi.org/10.1134/S1070428016020019

23. Patel A. B., O'Hare T., Deininger M. W. Mechanisms of resistance to ABL kinase inhibition in CML and the development of next generation ABL kinase inhibitors. Hematoogy/Oncology Clinics of North America, 2017, vol. 31, no. 4, pp. 589-612. https://doi.org/10.1016/j.hoc.2017.04.007

24. Liu J., Zhang Y., Huang H., Lei X., Tang G., ., Peng J. Recent advances in Bcr-Abl tyrosine kinase inhibitors for overriding T315I mutation. Chemical Biology and Drug Design, 2021, vol. 97, no. 3, pp. 649-664. https://doi.org/10.1111/cbdd.13801

25. Trott O., Olson A. J. AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading. Journal of Computational Chemistry, 2010. vol. 31, no. 2, pp. 455-461. https://doi.org/10.1002/jcc.21334

26. Durrant J. D., McCammon J. A. NNScore 2.0: A neural-network receptor-ligand scoring function. Journal of Chemical Information and Modeling, 2011, vol. 51, no. 11, pp. 2897-2903. https://doi.org/+-10.1021/ci2003889

27. Wójcikowski M., Ballester P. J., Siedlecki P. Performance of machine-learning scoring functions in structure-based virtual screening. Scientific Reports, 2017, vol. 7, no. 1, pp. 1-10.

28. Hinton G. E., Salakhutdinov R. R. Reducing the dimensionality of data with neural networks. Science, 2006, vol. 313, no. 5786, pp. 504-507.

29. Hwang M., Qian Y., Wu C., Jiang W. C., Wang D., ..., Hwang K. S. A local region proposals approach to instance segmentation for intestinal polyp detection. International Journal of Machine Learning and Cybernetics, 2023, vol. 14, no. 5, pp. 1591-1603.

30. Huang A., Ju X., Lyons J., Murnane D., Pettee M., Reed L. Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC. Available at: https://arxiv.org/pdf/2301.00501.pdf (accessed 07.08.2023).

31. Weininger D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information and Computer Sciences, 1988, vol. 28, no. 1, pp. 31-36. https://doi.org/10.1021/ci00057a005

32. Weininger D., Weininger A., Weininger, J. L. SMILES. 2. Algorithm for generation of unique SMILES notation. Journal of Chemical Information and Computer Sciences, 1989, vol. 29, no. 2, pp. 97-101.

33. O'Boyle N. M. Towards a Universal SMILES representation-A standard method to generate canonical SMILES based on the InChI. Journal of Cheminformatics, 2012, vol. 4, art. 22, pp. 1-14.

34. Kim S., Chen J., Cheng T., Gindulyte A., He J., ..., Bolton E. E. PubChem 2019 update: improved access to chemical data. Nuclear Acids Research, 2019, vol. 47(D1), pp. D1102-D1109.

35. Ho Y., Wookey S. The real-world-weight cross-entropy loss function: Modeling the costs of mislabeling. IEEE Access, 2019, vol. 8, pp. 4806-4813.

36. Kingma D. P., Ba J. Adam: A Method for Stochastic Optimization, 2014. Available at: https://arxiv.org/pdf/1412.6980.pdf (accessed 07.08.2023).

37. Landrum G. RDKit: A Software Suite for Cheminformatics, Computational Chemistry, and Predictive Modeling, 2013. Available at: https://www.rdkit.org/RDKit_Overview.pdf (accessed 07.08.2023).

38. Palacio-Rodríguez K., Lans I., Cavasotto C. N., Cossio P. Exponential consensus ranking improves the outcome in docking and receptor ensemble docking. Scientific Reports, 2019, vol. 9, no. 1, art. 5142. Available at: https://www.nature.com/articles/s41598-019-41594-3 (accessed 07.08.2023). https://doi.org/10.1038/s41598-019-41594-3

39. Lipinski C. A. Lead-and drug-like compounds: the rule-of-five revolution. Drug Discovery Today: Technologies, 2004, vol. 1, no. 4, pp. 337-341.

40. Verma J., Khedkar V. M., Coutinho E. C. 3D-QSAR in drug design-a review. Current Topics in Medicinal Chemistry, 2010, vol. 10, no. 1, pp. 95-115. https://doi.org/10.2174/156802610790232260

41. Kuseva C., Schultz T. W., Yordanova D., Tankova K., Kutsarova S., ..., Mekenyan O. G. The implementation of RAAF in the OECD QSAR Toolbox. Regulatory Toxicology and Pharmacology, 2019, vol. 105, pp. 51-61. https://doi.org/10.1016Zj.yTtph.2019.03.018