Design of Novel GSK-3β Inhibitors Based on Artificial Intelligence and Molecular Modeling

Azimi , M; Ebadi , SA

[Home ] [Archive]

[ فارسی ]

Main Menu

Home

Journal Information

Articles archive

For Authors

For Reviewers

Registration

Contact us

Site Facilities

Indexing & Abstracting

Publication Ethics

Search in website

Receive site information

Indexing & Abstracting

DOAJ
GOOGLE SCHOLAR

Volume 30, Issue 3 (4-2025)

__Armaghane Danesh__ 2025, 30(3): 388-409

Back to browse issues page

Design of Novel GSK-3β Inhibitors Based on Artificial Intelligence and Molecular Modeling

M Azimi¹

, SA Ebadi²

1- Medicinal Plants and Natural Products Research Center, Hamadan University of Medical Sciences, Hamadan, Iran
2- Medicinal Plants and Natural Products Research Center, Hamadan University of Medical Sciences, Hamadan, Iran , ahmadebadie@gmail.com

Abstract: (1058 Views)

Background & aim: Given the key role of GSK-3β in the pathogenesis of Parkinson's disease and the challenges in designing specific inhibitors, the aim of the present study was to identify and design new GSK-3β inhibitors based on artificial intelligence and molecular modeling.

Methods: The present descriptive–analytical computational (in silico) study was conducted in 2025. An AI-driven workflow was applied to design and evaluate novel GSK-3β inhibitors with potential therapeutic activity against Parkinson’s disease. Using CLMs, a set of de novo compounds was generated and subsequently filtered based on drug-likeness, structural diversity, and physicochemical properties. Data augmentation (20-fold) and temperature sampling (T = 0.8) were applied to enhance generalizability and molecular diversity. The collected data were analyzed using descriptive and comparative computational analyses based on model performance and physicochemical indices

Results: The model achieved a success rate of 73.1% in generating valid inhibitors. Among these, 78 compounds with predicted inhibitory potency below 20 μM were selected for molecular docking at the active site of GSK-3β. Docking analysis revealed that Compound A, featuring an isoquinoline scaffold, achieved a predicted binding energy of −16.5 kcal/mol, while Compound B, containing a quinoline scaffold, achieved −25.5 kcal/mol. Both compounds demonstrated favorable pharmacokinetic properties and full compliance with drug-likeness rules, including oral absorption criteria.

Conclusion: The integration of artificial intelligence with molecular modeling provides an efficient strategy for the design of selective and potent GSK-3β inhibitors, offering a promising pathway for the development of novel therapeutics for Parkinson’s disease.

Keywords: Artificial intelligence, Chemical language model, GSK-3β, Parkinson’s disease, Molecular docking.

Full-Text [PDF 1656 kb] (26 Downloads)

Type of Study: Research | Subject: Special
Received: 2025/06/8 | Accepted: 2025/09/8 | Published: 2025/09/17

References

1. Lin X, Li X, Lin XJM. A review on applications of computational methods in drug screening and design. Molecules 2020; 25(6): 1375.## [DOI:10.3390/molecules25061375] [PMID] []

2. Brogi S. Computational approaches for drug discovery. Molecules 2019; 24(17): 3061## [DOI:10.3390/molecules24173061] [PMID] []

3. Naithani U, Guleria V. Integrative computational approaches for discovery and evaluation of lead compound for drug design. Front Drug Discov 2024; 4: 1362456. ## [DOI:10.3389/fddsv.2024.1362456]

4. Sadybekov AV, Katritch V. Computational approaches streamlining drug discovery. Nature. 2023; 616(7958): 673-85. ## [DOI:10.1038/s41586-023-05905-z] [PMID]

5. Agamah FE, Mazandu GK, Hassan R, Bope CD, Thomford NE, Ghansah A, et al. Computational/in silico methods in drug target and lead prediction. Brief Bioinform 2020; 21(5): 1663-75. #### [DOI:10.1093/bib/bbz103] [PMID] []

6. Han R, Yoon H, Kim G, Lee H, Lee Y. Revolutionizing medicinal chemistry: the application of artificial intelligence (AI) in early drug discovery. Pharmaceuticals(Basel) 2023; 16(9): 1259. ## [DOI:10.3390/ph16091259] [PMID] []

7. Deng J, Yang Z, Ojima I, Samaras D, Wang F. Artificial intelligence in drug discovery: applications and techniques. Brief Bioinform 2022; 23(1): bbab430. ## [DOI:10.1093/bib/bbab430] [PMID]

8. Wu K, Xia Y, Deng P, Liu R, Zhang Y, Guo H, et al. TamGen: drug design with target-aware molecule generation through a chemical language model. Nat Commun 2024; 15(1): 9360. ## [DOI:10.1038/s41467-024-53632-4] [PMID] []

9. Bian Y, Xie XQ. Generative chemistry: drug discovery with deep learning generative models. J Mol Model 2021; 27: 1-18. ## [DOI:10.1007/s00894-021-04674-8] [PMID] []

10. Moret M, Pachon Angona I, Cotos L, Yan S, Atz K, Brunner C, et al. Leveraging molecular structure and bioactivity with chemical language models for de novo drug design. Nat Commun 2023; 14(1): 114. ## [DOI:10.1038/s41467-022-35692-6] [PMID] []

11. Dajani R, Fraser E, Roe SM, Yeo M, Good VM, Thompson V, et al. Structural basis for recruitment of glycogen synthase kinase 3β to the axin-APC scaffold complex. EMBO J 2003; 11(2): 495-507. ## [DOI:10.1093/emboj/cdg068] [PMID] []

12. Golpich M, Amini E, Hemmati F, Ibrahim NM, Rahmani B, Mohamed Z, et al. Glycogen synthase kinase-3 beta (GSK-3β) signaling: implications for Parkinson's disease. Pharmacol Res 2015; 97: 16-26## [DOI:10.1016/j.phrs.2015.03.010] [PMID]

13. Yu H, Xiong M, Zhang Z. The role of glycogen synthase kinase 3 beta in neurodegenerative diseases. Front Mol Neurosci 2023; 16: 1209703. ## [DOI:10.3389/fnmol.2023.1209703] [PMID] []

14. Li J, Ma S, Chen J, Hu K, Li Y, Zhang Z, et al. GSK-3β contributes to Parkinsonian dopaminergic neuron death: Evidence from conditional knockout mice and tideglusib. Front Mol Neurosci 2020; 13: 81. ## [DOI:10.3389/fnmol.2020.00081] [PMID] []

15. Li DW, Liu ZQ, Chen W, Yao M, Li GR. Association of glycogen synthase kinase 3β with Parkinson's disease. Mol Med Rep 2014; 9(6): 2043-50. ## [DOI:10.3892/mmr.2014.2080] [PMID] []

16. Morales-García JA, Susín C, Alonso-Gil S, Pérez DI, Palomo V, Pérez C, et al. Glycogen synthase kinase-3 inhibitors as potent therapeutic agents for the treatment of Parkinson disease. ACS Chem Neurosci 2013; 4(2): 350-60. ## [DOI:10.1021/cn300182g] [PMID] []

17. Park SH, Xu Y, Park YS, Seo JT, Gye MC. Glycogen synthase kinase-3 isoform variants and their inhibitory phosphorylation in human testes and spermatozoa. World J Mens Health 2022; 41(1): 215## [DOI:10.5534/wjmh.220108] [PMID] []

18. Jacobs KM, Bhave SR, Ferraro DJ, Jaboin JJ, Hallahan DE, Thotala D. GSK‐3β: a bifunctional role in cell death pathways. Int J Cell Biol 2012; 2012: 930710. ## [DOI:10.1155/2012/930710] [PMID] []

19. Stamos JL, Chu MLH, Enos MD, Shah N, Weis WI. Structural basis of GSK-3 inhibition by N-terminal phosphorylation and by the Wnt receptor LRP6. ELife 2014; 3: e01998. ## [DOI:10.7554/eLife.01998] [PMID] []

20. Beurel E, Grieco SF, Jope RS. Glycogen synthase kinase-3 (GSK3): regulation, actions, and diseases. Pharmacol Ther 2015; 148: 114-31. ## [DOI:10.1016/j.pharmthera.2014.11.016] [PMID] []

21. Hardt SE, Sadoshima J. Glycogen synthase kinase-3β: a novel regulator of cardiac hypertrophy and development. Circ Res 2002; 90(10): 1055-63. ## [DOI:10.1161/01.RES.0000018952.70505.F1] [PMID]

22. Luo J. Glycogen synthase kinase 3β (GSK3β) in tumorigenesis and cancer chemotherapy. Cancer Lett 2009; 273(2): 194-200. ## [DOI:10.1016/j.canlet.2008.05.045] [PMID] []

23. Asl FSS, Malverdi N, Mojahedian F, Baziyar P, Nabi-Afjadi M. Discovery of effective GSK-3β inhibitors as therapeutic potential against Alzheimer's disease: a computational drug design insight. Int J Biol Macromol 2025; 306: 141273. ## [DOI:10.1016/j.ijbiomac.2025.141273] [PMID]

24. Ganai SA, Mohan S, Padder SA. Exploring novel and potent glycogen synthase kinase-3β inhibitors through systematic drug designing approach. Sci Rep 2025; 15(1): 4118. ## [DOI:10.1038/s41598-025-85868-5] [PMID] []

25. Landrum G. RDKit: Open-source cheminformatics. Zenodo; 2006. Available from: https://www.rdkit.org ##

26. Skinnider MA. Invalid SMILES are beneficial rather than detrimental to chemical language models. Nat Mach Intell 2024; 6(4): 437-48. ## [DOI:10.1038/s42256-024-00821-x]

27. Bjerrum EJ. SMILES enumeration as data augmentation for neural network modeling of molecules. arXiv preprint arXiv:1703.07076. 2017. ##28.Segler MH, Kogej T, Tyrchan C, Waller MP. Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci 2018; 4(1): 120-31. ## [DOI:10.1021/acscentsci.7b00512] [PMID] []

28. Sheridan RP. Time-split cross-validation as a method for estimating the goodness of prospective prediction. J Chem Inf Model 2013; 53(4): 783-90. ## [DOI:10.1021/ci400084k] [PMID]

29. Thomas M, O'Boyle NM, Bender A, De Graaf C. MolScore: a scoring, evaluation and benchmarking framework for generative models in de novo drug design. J Cheminform 2024; 16(1): 64. ## [DOI:10.1186/s13321-024-00861-w] [PMID] []

30. Cafiero M. Variable-temperature token sampling in decoder-GPT molecule-generation can produce more robust and potent virtual screening libraries. Phys Chem Chem Phys 2025; 27(14): 18462-74. ## [DOI:10.1039/D5CP00692A] [PMID]

31. O'Boyle NM, Banck M, James CA, Morley C, Vandermeersch T, Hutchison GR. Open Babel: An open chemical toolbox. J Cheminform 2011; 3: 1-14. ##33.Neese F, Wennmohs F, Becker U, Riplinger C. The ORCA quantum chemistry program package. J Chem Phys 2020; 152(22): 224108; ## [DOI:10.1063/5.0004608] [PMID]

32. 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. [DOI:10.1002/jcc.21334] [PMID] []

33. Morris GM, Huey R, Lindstrom W, Sanner MF, Belew RK, Goodsell DS, et al. AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility. J Comput Chem 2009; 30(16): 2785-91. ## [DOI:10.1002/jcc.21256] [PMID] []

34. Wallace AC, Laskowski RA, Thornton JM. LIGPLOT: a program to generate schematic diagrams of protein-ligand interactions. Protein Eng Des Sel 1995; 8(2): 127-34. ## [DOI:10.1093/protein/8.2.127] [PMID]

35. Pettersen EF, Goddard TD, Huang CC, Couch GS, Greenblatt DM, Meng EC, et al. UCSF Chimera-a visualization system for exploratory research and analysis. J Comput Chem 2004; 25(13): 1605-12. ## [DOI:10.1002/jcc.20084] [PMID]

36. Dajani R, Fraser E, Roe SM, Young N, Good V, Dale TC, et al. Crystal structure of glycogen synthase kinase 3β: structural basis for phosphate-primed substrate specificity and autoinhibition. Cell 2001; 105(6): 721-32. ## [DOI:10.1016/S0092-8674(01)00374-9] [PMID]

37. Shri SR, Manandhar S, Nayak Y, Pai KSR. Role of GSK-3β inhibitors: new promises and opportunities for Alzheimer's disease. Adv Pharm Bull 2023; 13(4): 688. ## [DOI:10.34172/apb.2023.071] [PMID] []

38. Daina A, Michielin O, Zoete V. SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules. Sci Rep 2017; 7(1): 42717. ## [DOI:10.1038/srep42717] [PMID] []

39. Naithani U, Guleria V. Integrative computational approaches for discovery and evaluation of lead compounds for drug design. Front Drug Discov 2024; 4: 1362456. ## [DOI:10.3389/fddsv.2024.1362456]

40. Bian Y, Xie XQ. Generative chemistry: drug discovery with deep learning generative models. J Mol Model 2021; 27(1): 1-18. ## [DOI:10.1007/s00894-021-04674-8] [PMID] []

41. Arús-Pous J, Johansson SV, Prykhodko O, Bjerrum EJ, Tyrchan C, Reymond JL, et al. Randomized SMILES strings improve the quality of molecular generative models. J Cheminform 2019; 11(1): 1-13. ## [DOI:10.1186/s13321-019-0393-0] [PMID] []

42. Kong W, Hu Y, Zhang J, Tan Q. Application of SMILES-based molecular generative model in new drug design. Front Pharmacol 2022; 13: 1046524. ## [DOI:10.3389/fphar.2022.1046524] [PMID] []

43. Wang F, Feng X, Guo X, Xu L, Xie L, Chang S. Improving de novo molecule generation by embedding LSTM and attention mechanism in CycleGAN. Front Genet 2021; 12: 709500. ## [DOI:10.3389/fgene.2021.709500] [PMID] []

44. Ballarotto M, Willems S, Stiller T, Nawa F, Marschner JA, Grisoni F, et al. De novo design of Nurr1 agonists via fragment-augmented generative deep learning in low-data regime. J Med Chem 2023; 66(12): 8170-7. ## [DOI:10.1021/acs.jmedchem.3c00485] [PMID] []

45. Moret M, Pachon Angona I, Cotos L, Yan S, Atz K, Brunner C, et al. Leveraging molecular structure and bioactivity with chemical language models for de novo drug design. Nat Commun 2023; 14(1): 114. ## [DOI:10.1038/s41467-022-35692-6] [PMID] []

46. Armaghane-danesh, Yasuj University of Original Article Medical Sciences Journal (YUMSJ)

Send email to the article author

Add your comments about this article

Mendeley

Zotero

RefWorks

Azimi M, Ebadi S. Design of Novel GSK-3β Inhibitors Based on Artificial Intelligence and Molecular Modeling. armaghanj 2025; 30 (3) :388-409
URL: http://armaghanj.yums.ac.ir/article-1-3816-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 30, Issue 3 (4-2025)

Back to browse issues page

Persian site map - English site map - Created in 0.11 seconds with 37 queries by YEKTAWEB 4732