Improving machine learning force fields for molecular dynamics simulations with fine-grained force metrics

Machine learning force fields (MLFFs) have gained popularity in recent years as they provide a cost-effective alternative to ab initio molecular dynamics (MD) simulations. Despite a small error on the test set, MLFFs inherently suffer from generalization and robustness issues during MD simulations. To alleviate these issues, we propose global force metrics and fine-grained metrics from element and conformation aspects to systematically measure MLFFs for every atom and every conformation of molecules. We selected three state-of-the-art MLFFs (ET, NequIP, and ViSNet) and comprehensively evaluated on aspirin, Ac-Ala3-NHMe, and Chignolin MD datasets with the number of atoms ranging from 21 to 166. Driven by the trained MLFFs on these molecules, we performed MD simulations from different initial conformations, analyzed the relationship between the force metrics and the stability of simulation trajectories, and investigated the reason for collapsed simulations. Finally, the performance of MLFFs and the stability of MD simulations can be further improved guided by the proposed force metrics for model training, specifically training MLFF models with these force metrics as loss functions, fine-tuning by reweighting samples in the original dataset, and continued training by recruiting additional unexplored data.

Automated summary

Machine learning force fields (MLFFs) have become a cost-effective alternative to ab initio molecular dynamics (MD) simulations. However, they suffer from generalization and robustness issues. To address this, we proposed global force metrics and fine-grained metrics to systematically measure MLFFs. We evaluated three state-of-the-art MLFFs on different molecules and analyzed the relationship between force metrics and simulation stability.