2026-10-08T03:12:10Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34025076 2026-09-29T16:16:26Z category_4 category_13 category_14 category_15 category_16 category_19 category_873 category_734 category_931 category_64 portal_63 item_type_6 month_year_09_2026

Generative AI-Assisted Molecular Design of AChEIs Dhairiya Agarwal (17261506) Rakesh Kumar Gautam (25137918) Vaibhav Gupta (3525740) Vishal Chaurasia (25137921) Anju Sharma (2900093) Tanmaykumar Varma (17013628) Gyan Modi (803693) Sankar K. Guchhait (1622386) Prabha Garg (1625956) Biochemistry Genetics Molecular Biology Neuroscience Physiology Pharmacology Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified Cancer noncompetitive inhibition mechanism major neurodegenerative disorder limited therapeutic options lead molecule exhibiting experimental workflow demonstrates biased molecular generation assisted molecular design based cardiotoxicity screening acheis alzheimer ’ molecular docking based framework acheis ), reinforcement learning novel leads generative modeling generative ai generated compounds deep learning chemical synthesis biological evaluation Alzheimer’s disease (AD) remains a major neurodegenerative disorder with limited therapeutic options, while currently approved acetylcholinesterase inhibitors (AChEIs), such as donepezil, are associated with adverse effects including cardiotoxicity. Here, we integrated a deep learning-based framework to design novel AChEIs candidates with improved predicted cardiac safety. A reinforcement learning-guided GraphVAE (RL-GraphVAE) was employed for target-biased molecular generation. The generated compounds were prioritized through CardiotoxPred-based cardiotoxicity screening, molecular docking, triplicate molecular dynamics simulations, and chemical synthesis. Experimental evaluation identified D0209 as a lead molecule exhibiting a noncompetitive inhibition mechanism. Notably, compared with donepezil, D0209 showed ∼43-fold lower hERG channel inhibition, indicating an improved cardiac safety profile. Overall, this integrated computational and experimental workflow demonstrates the utility of generative modeling for the discovery of novel leads with improved predicted safety profiles, providing promising starting points for further optimization and biological evaluation. 2026-09-29T00:00:00Z Text Journal contribution 10.1021/acs.jcim.6c02233.s001 https://figshare.com/articles/journal_contribution/Generative_AI-Assisted_Molecular_Design_of_AChEIs/34025076 CC BY-NC 4.0