Efficient interatomic descriptors for accurate machine learning force fields of extended molecules

Machine learning force fields (MLFFs) are gradually evolving towards enabling molecular dynamics simulations of molecules and materials with ab initio accuracy but at a small fraction of the computational cost. However, several challenges remain to be addressed to enable predictive MLFF simulations of realistic molecules, including: (1) developing efficient descriptors for non-local interatomic interactions, which are essential to capture long-range molecular fluctuations, and (2) reducing the dimensionality of the descriptors to enhance the applicability and interpretability of MLFFs. Here we propose an automatized approach to substantially reduce the number of interatomic descriptor features while preserving the accuracy and increasing the efficiency of MLFFs. To simultaneously address the two stated challenges, we illustrate our approach on the example of the global GDML MLFF. We found that non-local features (atoms separated by as far as 15 angstrom in studied systems) are crucial to retain the overall accuracy of the MLFF for peptides, DNA base pairs, fatty acids, and supramolecular complexes. Interestingly, the number of required non-local features in the reduced descriptors becomes comparable to the number of local interatomic features (those below 5 angstrom). These results pave the way to constructing global molecular MLFFs whose cost increases linearly, instead of quadratically, with system size.

Automated summary

Machine learning force fields (MLFFs) are being optimized to enable molecular dynamics simulations with ab initio accuracy but at a fraction of the computational cost. Challenges remain in developing efficient descriptors for non-local interatomic interactions and reducing dimensionality of descriptors for enhanced applicability and interpretability. An automatized approach is proposed to reduce interatomic descriptor features while maintaining accuracy and efficiency of MLFFs. The results show the importance of non-local features in preserving overall accuracy and reducing the required features to a comparable number with local interatomic features.