Repurposing of Anti-Infectives for the Management of Onchocerciasis Using Machine Learning and Protein Docking...

Area of Science:

• Drug discovery and computational chemistry
• Infectious diseases and parasitology
• Machine learning in pharmacology

Background:

• Neglected tropical diseases (NTDs), like onchocerciasis, face slow drug development due to limited financial incentives.
• Current onchocerciasis treatments rely on ivermectin and moxidectin.
• Novel anti-infective strategies are crucial for combating onchocerciasis.

Purpose of the Study:

• To computationally identify existing anti-infective agents for repurposing or as lead compounds against onchocerciasis.
• To explore the potential of machine learning and molecular docking for drug discovery in NTDs.
• To validate computational predictions through molecular docking against a known drug target.

Main Methods:

• Evaluated 58 anti-infective agents using exploratory data analysis and machine learning (ML) models.
• Utilized molecular docking simulations against the glutamate-gated chloride channel, a target for onchocerciasis drugs.
• Assessed binding affinities and interactions of top predicted compounds compared to native ligands and known drugs.

Main Results:

• Machine learning models predicted 14 out of 58 agents as potentially effective for onchocerciasis.
• Molecular docking revealed high binding affinities for cridanimod (-7.8 kcal/mol), diminazene (-7.2 kcal/mol), and vandetanib (-7.1 kcal/mol).
• These top candidates exhibited binding interactions similar to established onchocerciasis agents like ivermectin.

Conclusions:

• Cridanimod, diminazene, and vandetanib demonstrate significant potential as new therapeutic candidates for onchocerciasis.
• This study validates a computational approach for discovering drugs against neglected tropical diseases.
• The findings pave the way for developing novel treatments to manage onchocerciasis.