Enhancing Protein-Ligand Binding Affinity Predictions using Neural Network Potentials

TL;DR

This paper introduces a hybrid neural network potential combined with molecular mechanics to improve the accuracy of protein-ligand binding affinity predictions, demonstrating significant enhancements over traditional force fields.

Contribution

It presents a novel NNP/MM approach for more accurate binding affinity predictions and validates its effectiveness against benchmark datasets.

Findings

Significant improvement over conventional MM force fields

Enhanced accuracy in relative binding free energy calculations

Validated against established benchmarks

Abstract

This letter gives results on improving protein-ligand binding affinity predictions based on molecular dynamics simulations using machine learning potentials with a hybrid neural network potential and molecular mechanics methodology (NNP/MM). We compute relative binding free energies (RBFE) with the Alchemical Transfer Method (ATM) and validate its performance against established benchmarks and find significant enhancements compared to conventional MM force fields like GAFF2.