QuantumBind-RBFE: Accurate Relative Binding Free Energy Calculations Using Neural Network Potentials

TL;DR

This paper introduces a neural network potential-based method, QuantumBind-RBFE, for more accurate and faster protein-ligand binding affinity predictions, demonstrating improved accuracy and efficiency over traditional force fields.

Contribution

The work presents a novel neural network potential model, AceFF 1.0, that enhances the accuracy and speed of relative binding free energy calculations for diverse drug-like molecules.

Findings

Improved accuracy and correlation in binding affinity predictions compared to traditional force fields.

NNP simulations run at 2 fs timestep, doubling previous speed capabilities.

Code and models are publicly available for research use.

Abstract

Accurate prediction of protein-ligand binding affinities is crucial in drug discovery, particularly during hit-to-lead and lead optimization phases, however, limitations in ligand force fields continue to impact prediction accuracy. In this work, we validate relative binding free energy (RBFE) accuracy using neural network potentials (NNPs) for the ligands. We utilize a novel NNP model, AceFF 1.0, based on the TensorNet architecture for small molecules that broadens the applicability to diverse drug-like compounds, including all important chemical elements and supporting charged molecules. Using established benchmarks, we show overall improved accuracy and correlation in binding affinity predictions compared with GAFF2 for molecular mechanics and ANI2-x for NNPs. Slightly less accuracy but comparable correlations with OPLS4. We also show that we can run the NNP simulations at 2 fs timestep, at least two times larger than previous NNP models, providing significant speed gains. The results show promise for further evolutions of free energy calculations using NNPs while demonstrating its practical use already with the current generation. The code and NNP model are publicly available for research use.