Machine Learning and Molecular Modeling Strategy for the Identification of CNS-Active Acetylcholinesterase Inhibitors

Area of Science:

• Neuroscience
• Pharmacology
• Computational Chemistry

Background:

• Acetylcholinesterase (AChE) is a crucial target for treating neurological disorders.
• Developing novel AChE inhibitors with enhanced efficacy and pharmacokinetics presents a significant challenge.

Purpose of the Study:

• To identify potential novel acetylcholinesterase (AChE) inhibitors.
• To screen compounds for Blood-Brain Barrier (BBB) permeability for Central Nervous System (CNS) suitability.
• To evaluate the interaction profiles and stability of potential inhibitors.

Main Methods:

• Integrated computational (machine learning, molecular docking, simulations) and experimental approach.
• Machine learning model for predicting bioactivity from chemical libraries.
• In vitro biological evaluation of AChE inhibitory activity.

Main Results:

• Several compounds, including Z1498348710 and Z1824281875, showed moderate AChE inhibition (approx. 72-75% activity remaining).
• Other compounds exhibited moderate effects (82-86% activity remaining).
• Reference inhibitors (Donepezil, Neostigmine bromide) showed stronger inhibition (18-20% activity remaining).

Conclusions:

• Identified compounds possess moderate AChE inhibitory activity.
• These compounds show favorable predicted physicochemical and computational properties.
• The findings suggest these compounds are promising starting points for developing CNS-active AChE inhibitors.