August 7, 2025

Integrating Physics-Based Simulations with Data-Driven Deep Learning Represents a Robust Strategy for Developing Inhibitors Targeting the Main Protease

Key Points

Core finding reveals a novel computational pipeline enhancing inhibitor optimization for the coronavirus main protease.
The approach combines prediction from deep learning and validation via free energy perturbation and molecular dynamics simulations.
Starting with a known inhibitor, the pipeline prioritized analogs that target specific binding subpockets efficiently.
This integration of physics-based methods with AI represents a significant advancement in antiviral drug development.

Abstract

The coronavirus main protease, essential for viral replication, is a well-validated antiviral target. Here, we present Deep-CovBoost, a computational pipeline integrating deep learning with free energy perturbation (FEP) simulations to guide the structure-based optimization of inhibitors targeting the coronavirus main protease. Starting from a reported noncovalent inhibitor, the pipeline generated and prioritized analogs using predictive modeling, followed by rigorous validation through FEP and molecular dynamics simulations. This approach led to the identification of optimized compounds (e.g., I3C-1, I3C-2, I3C-35) that enhance binding affinity by engaging the underexploited S4 and S5 subpockets. These results highlight the potential of combining physics-based and AI-driven approaches to accelerate lead optimization and antiviral design.

Integrating Physics-Based Simulations with Data-Driven Deep Learning Represents a Robust Strategy for Developing Inhibitors Targeting the Main Protease

Key Points

Abstract

Cite This Study