An AI-Guided End-to-End Framework: Deep Eutectic Solvent Synthesis, In-Silico Characterization, and Computational Pharmacology of Novel Benzimidazole Derivatives
DOI:
https://doi.org/10.55544/jrasb.5.1.19Keywords:
Artificial Intelligence (AI) in Drug Discovery, Green Chemistry, Deep Eutectic Solvents (DES), Benzimidazole Scaffolds, Molecular Docking, Phosphodiesterase Type 5 (PDE5) Inhibitors, Structure-Activity Relationship (SAR), Computational PharmacologyAbstract
The conventional development of novel bioactive benzimidazole scaffolds is often hindered by resource-intensive synthetic protocols and prolonged iterative testing cycles. This study presents an innovative, integrated, end-to-end framework driven by generative artificial intelligence (Gemini AI) to streamline the design, sustainable synthesis, and comprehensive pharmacological evaluation of new 2-substituted benzimidazole derivatives specifically targeting Phosphodiesterase Type 5 (PDE5). Leveraging advanced prompt engineering, a green synthetic pathway was designed and optimized via virtual Design of Experiments (DoE), utilizing a biodegradable Choline Chloride:Urea Deep Eutectic Solvent (DES) coupled with microwave irradiation. Theoretical product formation was validated using AI-predicted FT-IR and NMR spectral data. Concurrently, therapeutic potential was assessed through rigorous molecular docking simulations against the PDE5 catalytic domain, informing subsequent detailed Structure-Activity Relationship (SAR) mapping, Mechanism of Action (MOA) elucidation, and multi-target protein-ligand network analysis. The AI-optimized oxidative cyclocondensation protocol demonstrated exceptional sustainability, achieving a theoretical isolated yield of >92% with an Environmental Factor (E-factor) of <0.5 within a 5-minute reaction time at 80 °C. imidazole docked in PDE5 active site] Computational profiling revealed a highly favorable global binding energy of -8.4 kcal/mol against the PDE5 receptor. SAR analysis identified the benzimidazole core as a critical hinge binder forming essential hydrogen bonds with residue Gln817, while the para-chlorophenyl tail effectively occupied the active site's hydrophobic pocket through π-π stacking and specific halogen interactions with Met816. Network analysis further supported the scaffold’s viability for targeted cardiovascular applications and suggested potential secondary antimicrobial activity. This research successfully demonstrates a transformative AI-guided approach that accelerates therapeutic lead discovery by coupling highly efficient, low-waste green chemistry principles with robust predictive pharmacology. The validated in-silico metrics establish the synthesized benzimidazole derivative as a promising, sustainably produced PDE5 inhibitor candidate, providing a strong rationale for immediate progression to wet-lab synthesis and in-vitro biological assays.
Downloads
References
[1] Abbott, A. P., Boothby, D., Catchpole, G., & Davies, A. W. (2004). Deep eutectic solvents formed between choline chloride and carboxylic acids: Versatile alternatives to ionic liquids. Journal of the American Chemical Society, 126(29), 9142–9147.
[2] Anastas, P. T., & Warner, J. C. (1998). Green chemistry: Theory and practice. Oxford University Press.
[3] Bansal, Y., & Silakari, O. (2012). The therapeutic journey of benzimidazoles: A review. Bioorganic & Medicinal Chemistry, 20(21), 6208–6236.
[4] Baskin, I. I., Winkler, D., & Tetko, I. V. (2016). A renaissance of neural networks in drug discovery. Expert Opinion on Drug Discovery, 11(8), 785–795.
[5] Boobier, S., Osbourn, A., & Mitchell, J. B. O. (2020). Can machine learning identify the next synthetic methodology sweet spot? Nature Reviews Chemistry, 4(8), 385–386.
[6] Constable, D. J. C., Jimenez-Gonzalez, C., & Henderson, R. K. (2007). Perspective on solvent use in the pharmaceutical industry. Organic Process Research & Development, 11(1), 133–137.
[7] Corbin, J. D., Turko, I. V., Beasley, A., & Francis, S. H. (2002). Phosphodiesterase type 5 as a pharmacologic target in erectile dysfunction. Urology, 60(2), 4–11.
[8] Hopkins, A. L. (2008). Network pharmacology: The next paradigm in drug discovery. Nature Chemical Biology, 4(11), 682–690.
[9] Kappe, C. O. (2004). Controlled microwave heating in modern organic synthesis. Angewandte Chemie International Edition, 43(46), 6250–6284.
[10] Lipinski, C. A., Lombardo, F., Dominy, B. W., & Feeney, P. J. (2001). Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Advanced Drug Delivery Reviews, 46(1-3), 3–26.
[11] Morris, G. M., & Lim-Wilby, M. (2008). Molecular docking. Methods in Molecular Biology, 443, 365–382.
[12] Rybalkin, S. D., Yan, C., Bornfeldt, K. E., & Beavo, J. A. (2003). Cyclic GMP phosphodiesterases and regulation of smooth muscle function. Circulation Research, 93(4), 280–291.
[13] Scannell, J. W., Blanckley, A., Boldon, H., & Warrington, B. (2012). Diagnosing the decline in pharmaceutical R&D efficiency. Nature Reviews Drug Discovery, 11(3), 191–200.
[14] Schneider, G. (2018). Automating drug discovery. Nature Reviews Drug Discovery, 17(2), 97–113.
[15] Sheldon, R. A. (2007). The E factor: Fifteen years on. Green Chemistry, 9(12), 1273–1283.
[16] Sheldon, R. A. (2017). The E factor 25 years on: The rise of green chemistry and sustainability. Green Chemistry, 19(1), 18–43.
[17] Sung, B. J., Hwang, K. Y., Jeon, Y. H., Lee, J. I., Heo, Y. S., Alvarez, R. A., ... & Cho, Y. (2003). Structure of the catalytic domain of human phosphodiesterase 5 with bound drug molecules. Nature, 425(6953), 98–102.
[18] Trost, B. M. (1991). The atom economy—A search for synthetic efficiency. Science, 254(5037), 1471–1477.
[19] Wright, J. B., Smith, D. R., & Buchanan, R. L. (2000). Biological activity of benzimidazole derivatives. Journal of Medicinal Chemistry, 43(21), 4005-4015.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Monesh Kumar Sahu, Bhupesh Sahu, Mayank Kumar Gupta, Akshya Kumar Mishra
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
10.55544/jrasb
editor@jrasb.com or mailtojrasb@gmail.com | 
+91-8874396939
This work is licensed under a 