QuantumBind-RBFE: Accurate Relative Binding Free Energy Calculations Using Neural Network Potentials
This work addresses accuracy limitations in drug discovery for pharmaceutical researchers, representing an incremental improvement over existing neural network potential methods.
The authors tackled the problem of inaccurate protein-ligand binding affinity predictions in drug discovery by validating relative binding free energy calculations using neural network potentials, achieving improved accuracy and correlation compared to existing methods like GAFF2 and ANI2-x, with simulations running at 2 fs timesteps for significant speed gains.
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.