Estimating AChE inhibitors from MCE database by machine learning and atomistic calculations.

Area of Science:

• Computational chemistry
• Neuroscience
• Pharmacology

Background:

• Alzheimer's disease (AD) poses a significant challenge, with acetylcholinesterase (AChE) inhibition being a key therapeutic strategy.
• Developing novel AChE inhibitors is crucial for effective AD treatment and prevention.

Purpose of the Study:

• To identify and characterize novel acetylcholinesterase (AChE) inhibitors using computational methods.
• To validate the efficacy of potential inhibitors through molecular docking and dynamics simulations.

Main Methods:

• A machine learning (ML) model was trained to predict AChE inhibitory activity.
• Molecular docking and molecular dynamics simulations were performed to analyze ligand-AChE interactions.
• Compounds from the MedChemExpress (MCE) database were screened.

Main Results:

• The ML model successfully estimated the inhibitory potential of MCE compounds.
• Atomistic simulations confirmed the inhibitory capacity of selected compounds.
• Two specific compounds (PubChem IDs 130467298 and 132020434) were identified as potent AChE inhibitors.

Conclusions:

• Computational approaches, including ML and simulations, are effective in discovering drug candidates.
• The identified compounds demonstrate potential for Alzheimer's disease treatment by inhibiting AChE.
• Further investigation into these compounds could lead to new therapeutic strategies for AD.