Affiliation:
1. Microsoft Research AI4Science 1 , Beijing 100084, China
2. College of Chemistry and Molecular Engineering, Peking University 2 , Beijing 100871, China
3. Microsoft Research AI4Science 3 , Cambridge CB1 2FB, United Kingdom
Abstract
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.
Subject
Physical and Theoretical Chemistry,General Physics and Astronomy
Reference31 articles.
1. Generalized neural-network representation of high-dimensional potential-energy surfaces;Phys. Rev. Lett.,2007
2. Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics;Phys. Rev. Lett.,2018
3. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems;Bengio,2018
4. A.
Kabylda
, V.Vassilev-Galindo, S.Chmiela, I.Poltavsky, and A.Tkatchenko, “Towards linearly scaling and chemically accurate global machine learning force fields for large molecules,” arXiv:2209.03985 (2022).
5. Studies in molecular dynamics. I. General method;J. Chem. Phys.,1959
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献