Searching for AChE inhibitors from natural compounds by using machine learning and atomistic simulations

Area of Science:

• Computational Chemistry
• Pharmacology
• Drug Discovery

Background:

• Alzheimer's disease (AD) poses a significant health challenge, with acetylcholinesterase (AChE) identified as a key therapeutic target.
• Developing novel AChE inhibitors is crucial for effective AD treatment strategies.
• Natural compounds offer a rich source of potential therapeutic agents.

Purpose of the Study:

• To develop and validate a computational approach for identifying natural compounds with AChE inhibitory activity.
• To screen the VIETHERB database for potential AChE inhibitors using machine learning and atomistic simulations.
• To assess the binding affinity of identified compounds to AChE.

Main Methods:

• A machine learning (ML) model was trained to predict ligand-binding affinity to AChE.
• The ML model was used to screen the VIETHERB natural compound database.
• Atomistic simulations, including molecular docking and steered molecular dynamics, were employed to validate ML predictions.

Main Results:

• The combined ML and atomistic simulation approach demonstrated good agreement.
• Twenty natural compounds were identified as potential AChE inhibitors.
• Four compounds, including geranylgeranyl diphosphate and farnesyl diphosphate, exhibited highly potent sub-nanomolar affinities.

Conclusions:

• The integrated computational strategy effectively identifies promising AChE inhibitors from natural sources.
• The identified potent inhibitors warrant further investigation for Alzheimer's disease therapeutic development.
• This study highlights the potential of natural products in drug discovery for neurodegenerative diseases.