INTEGRATING MACHINE LEARNING AND DOCKING SIMULATIONS  FOR THE SCREENING AND DESIGN OF NOVEL HDAC2 INHIBITORS  AS ANTICANCER AGENTS

Nguyễn Ngọc An; Đào Quang Tùng; Thái Chính Tâm; Nguyễn Thành Công; Phạm Thị Kim Anh; Phan Thị Phương Dung; Đỗ Thị Mai Dung

doi:10.34238/tnu-jst.11797

INTEGRATING MACHINE LEARNING AND DOCKING SIMULATIONS FOR THE SCREENING AND DESIGN OF NOVEL HDAC2 INHIBITORS AS ANTICANCER AGENTS

About this article

Received: 02/01/25 Revised: 27/03/25 Published: 28/03/25

Authors

1. Nguyen Ngoc An, VNU University of Engineering and Technology
2. Dao Quang Tung, Stockholm University
3. Thai Chinh Tam, Hanoi University of Pharmacy
4. Nguyen Thanh Cong, VNU University of Engineering and Technology
5. Pham Thi Kim Anh, Hanoi University of Pharmacy
6. Phan Thi Phuong Dung, Hanoi University of Pharmacy
7. Do Thi Mai Dung , Hanoi University of Pharmacy

Abstract

Histone deacetylase 2 (HDAC2) is a promising molecular target for anticancer drug design. This study collected and analyzed 2,809 compounds to train machine-learning models for identifying potential HDAC2 inhibitors. Virtual screening of 140 million structures identified 88 compounds with predicted HDAC2 inhibition superior to SAHA, confirmed by the top four models with over 85% accuracy. Docking studies further evaluated these, revealing 60 compounds with ΔG values between -12.3 to -16.5 kcal/mol, surpassing SAHA. Structural analysis led to the design of 16 new compounds with enhanced binding affinity. Two compounds, I and II, were predicted to outperform the original lead, forming additional interactions with the active site while maintaining zinc ion coordination. This research developed a machine learning model and proposed a screening procedure combined with docking to identify new compound structures with good inhibitory potential. This approach is not only suitable for HDAC2 but can be also applied to many biological targets.

Keywords

Machine learning; QSAR; Drug design; Docking simulation; HDAC2 inhibitors

Full Text:

PDF (Tiếng Việt)

References

[1] W. Xu, "Current Status of Computational Approaches for Small Molecule Drug Discovery," Journal of Medicinal Chemistry, vol. 67, no. 21, pp. 18633-18636, 2024.

[2] S. Saikia and M. Bordoloi, “Molecular docking: challenges, advances and its use in drug discovery perspective,” Current Drug Targets, vol. 20, no. 5, pp. 501-521, 2019.

[3] X. Liu, D. Shi, S. Zhou, et al., “Molecular dynamics simulations and novel drug discovery,” Expert Opinion on Drug Discovery, vol. 13 no. 1, pp. 23-37, 2017.

[4] M. D. Vivo, M. Masetti, G. Bottegoni, et al., “Role of molecular dynamics and related methods in drug discovery,” Journal of Medicinal Chemistry, vol. 59 no. 9, pp. 4035-4061, 2016.

[5] J. E. Audia and R. M. Campbell, “Histone Modifications and Cancer,” Cold Spring Harbor Perspectives in Biology, vol. 8, no. 4, 2016, Art. no. a019521.

[6] N. Basant, X. Lin, T. E. Reid, et al., “Discovery of a Novel HDAC2 Inhibitor by a Scaffold-Merging Hybrid Query,” Combinatorial Chemistry & High Throughput Screening, vol. 18, no. 7, pp. 693-700, 2015.

[7] B. M. Müller, L. Jana, A. Kasajima, et al., “Differential expression of histone deacetylases HDAC1, 2 and 3 in human breast cancer-overexpression of HDAC2 and HDAC3 is associated with clinicopathological indicators of disease progression,” BMC Cancer, vol. 13, pp. 1-8, 2013.

[8] Greg Landrum, Paolo Tosco, Brain Kelley, et al., “RDKit: Open-source cheminformatics,” September 13, 2006 [Online]. https://www.rdkit.org/. [Accessed August 20, 2024].

[9] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 15, no. 1, p. 73, 2016.

[10] F. Pedregosa, G. Varoquaux, A. Gramfort, et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, no. 85, pp. 2825-2830, 2011, doi: 10.5555/1953048.2078195.

[11] K. G. Micheal, L. Tiqing, M. Baitaluk, et al., “BindingDB in 2015: A public database for medicinal chemistry, computational chemistry and systems pharmacology,” Nucleic Acids Research, vol. 44, no. D1, pp. D1045-D1053, 2016, doi: 10.1093/nar/gkv1072.

[12] S. Kim, J. Chen, T. Cheng, et al., “PubChem 2023 update,” Nucleic Acids Research, vol. 51, no. D1, pp. D1373-D1380, 2023, doi: 10.1093/nar/gkac956.

[13] J. Aqvist, C. Medina, and J. E. Samuelsson, “A new method for predicting binding affinity in computer-aided drug design,” Protein Engineering, vol. 7, no. 3, pp. 385-391, 1994, doi: 10.1093/protein/7.3.385.

[14] H. M. Berman, “The Protein Data Bank,” Nucleic Acids Research, vol. 28, no. 1, pp. 235-242, 2000, doi: 10.1093/nar/28.1.235.

[15] T. N. H. Pham, T. H. Nguyen, N. M. Tam, et al., “Improving ligand‐ranking of AutoDock Vina by changing the empirical parameters,” The Journal of Computational Chemistry, vol. 43, no. 3, pp. 160-169, 2022, doi: 10.1002/jcc.26779.

[16] M. F. Adasme, K. L. Linnemann, S. N. Bolz, et al., “PLIP 2021: expanding the scope of the protein–ligand interaction profiler to DNA and RNA,” Nucleic Acids Research, vol. 49, no. W1, pp. W530-W534, 2021, doi: 10.1093/nar/gkab294.

[17] B. S. Urias, A. R. Pavan, G. R. Albuquerque, I. M. Prokopczyk, T. M. F. Alves, T. R. F. de Melo, G. R. Sartori, J. H. M. da Silva, C. M. Chin, and J. L. D. Santos, “Optimization of resveratrol used as a scaffold to design histone deacetylase (HDAC-1 and HDAC-2) inhibitors,” Pharmaceuticals, vol. 15, 2022, Art. no. 1260, doi: 10.3390/ph15101260.

[18] S. Tateing and N. Suree, “Decoding molecular recognition of inhibitors targeting HDAC2 via molecular dynamics simulations and configurational entropy estimation,” PLoS One, vol. 17, no. 8, 2022, Art. no. e0273265, doi: 10.1371/journal.pone.0273265.

[19] S. Kandasamy, P. Subramani, K. Srinivasan, et al., “Design and synthesis of imidazole-based zinc binding groups as novel small molecule inhibitors targeting histone deacetylase enzymes in lung cancer,” Journal of Molecular Structure, vol. 1214, 2020, Art. no. 128177, doi: 10.1016/j.molstruc.2020.128177.

DOI: https://doi.org/10.34238/tnu-jst.11797

Refbacks

There are currently no refbacks.



Remember me