Grappa -- A Machine Learned Molecular Mechanics Force Field
This work addresses the need for more accurate force fields in biomolecular simulations, enabling simulations closer to chemical accuracy without increased computational cost, though it is incremental as it builds on existing machine learning and molecular mechanics methods.
The authors tackled the challenge of creating accurate yet computationally efficient force fields for molecular dynamics simulations by developing Grappa, a machine learning framework that predicts molecular mechanics parameters from molecular graphs, achieving state-of-the-art accuracy for small molecules, peptides, RNA, and radicals while maintaining the same computational efficiency as established force fields.
Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted the tension between computational efficiency and accuracy of force fields, but they are still several orders of magnitude more expensive than established molecular mechanics (MM) force fields. Here, we propose Grappa, a machine learning framework to predict MM parameters from the molecular graph, employing a graph attentional neural network and a transformer with symmetry-preserving positional encoding. The resulting Grappa force field outperformstabulated and machine-learned MM force fields in terms of accuracy at the same computational efficiency and can be used in existing Molecular Dynamics (MD) engines like GROMACS and OpenMM. It predicts energies and forces of small molecules, peptides, RNA and - showcasing its extensibility to uncharted regions of chemical space - radicals at state-of-the-art MM accuracy. We demonstrate Grappa's transferability to macromolecules in MD simulations from a small fast folding protein up to a whole virus particle. Our force field sets the stage for biomolecular simulations closer to chemical accuracy, but with the same computational cost as established protein force fields.