Enhancing protein-ligand binding affinity predictions using neural network potentials
Enhancing protein-ligand binding affinity predictions using neural network potentials
Citació
- Sabanés Zariquiey F, Galvelis R, Gallicchio E, Chodera JD, Markland TE, De Fabritiis G. Enhancing protein-ligand binding affinity predictions using neural network potentials. J Chem Inf Model. 2024 Mar 11;64(5):1481-5. DOI: 10.1021/acs.jcim.3c02031
Enllaç permanent
Descripció
Resum
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 with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2.