Antivirals for monkeypox virus: Proposing an effective machine/deep learning framework

Area of Science:

• Virology
• Computational Biology
• Drug Discovery

Background:

• Monkeypox virus (MPXV) poses a significant public health threat with no specific approved antiviral treatments.
• Drug repurposing, aided by computational methods, offers a cost-effective strategy for identifying treatments for emerging viral diseases.

Purpose of the Study:

• To develop and apply a computational framework for predicting effective antiviral drugs against MPXV.
• To leverage machine learning and deep learning for identifying potential MPXV therapeutics through drug repurposing.

Main Methods:

• Generation of a novel virus-antiviral dataset for MPXV.
• Application of machine learning and deep learning models for antiviral prediction.
• In silico drug screening using molecular docking studies on homology-modeled and validated MPXV target proteins.

Main Results:

• The computational framework successfully predicted several potential antiviral drugs for MPXV.
• Docking studies validated the efficacy of the predicted drugs against MPXV targets.
• Tilorone, Valacyclovir, Ribavirin, Favipiravir, and Baloxavir marboxil were identified as promising candidates for MPXV treatment.

Conclusions:

• This study presents the first application of deep learning methods for MPXV antiviral prediction.
• The identified drugs represent viable options for further investigation and potential clinical use against MPXV infections.