Enhancing Protein–Ligand Binding Affinity Predictions Using Neural Network Potentials
Francesc Sabanés Zariquiey, Raimondas Galvelis, Emilio Gallicchio, John D. Chodera, Thomas E. Markland, Gianni De Fabritiis
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 with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2.
Topics & Concepts
Artificial neural networkMolecular dynamicsLigand (biochemistry)Computer scienceBiological systemMolecular mechanicsChemistryStatistical physicsArtificial intelligenceComputational chemistryPhysicsBiologyBiochemistryReceptorProtein Structure and DynamicsComputational Drug Discovery MethodsMachine Learning in Materials Science