Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks

Abstract

Molecular dynamics simulations are a cornerstone in science, allowing to investigate from the system's thermodynamics to analyse intricate molecular interactions. In general, to create extended molecular trajectories can be a computationally expensive process, for example, when running $ab-initio$ simulations. Hence, repeating such calculations to either obtain more accurate thermodynamics or to get a higher resolution in the dynamics generated by a fine-grained quantum interaction can be time- and computationally-consuming. In this work, we explore different machine learning (ML) methodologies to increase the resolution of molecular dynamics trajectories on-demand within a post-processing step. As a proof of concept, we analyse the performance of bi-directional neural networks such as neural ODEs, Hamiltonian networks, recurrent neural networks and LSTMs, as well as the uni-directional variants as a reference, for molecular dynamics simulations (here: the MD17 dataset). We have found that Bi-LSTMs are the best performing models; by utilizing the local time-symmetry of thermostated trajectories they can even learn long-range correlations and display high robustness to noisy dynamics across molecular complexity. Our models can reach accuracies of up to 10${}^{-4}$ angstroms in trajectory interpolation, while faithfully reconstructing several full cycles of unseen intricate high-frequency molecular vibrations, rendering the comparison between the learned and reference trajectories indistinguishable. The results reported in this work can serve (1) as a baseline for larger systems, as well as (2) for the construction of better MD integrators.

arXiv comment13 pages, 8 figures, research article

References in corpus (20)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• SchNet - a deep learning architecture for molecules and materials
• Machine Learning Force Fields
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Physics-inspired structural representations for molecules and materials
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Deep Potential: a general representation of a many-body potential energy surface
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• TorchMD: A deep learning framework for molecular simulations
• Efficient nonparametric $n$-body force fields from machine learning
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Learning Molecular Dynamics with Simple Language Model built upon Long Short-Term Memory Neural Network
• Graph Neural Networks Accelerated Molecular Dynamics
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Building machine learning force fields for nanoclusters

Cited by in corpus (4)

• Fewest-Switches Surface Hopping with Long Short-Term Memory Networks
• Energy-conserving molecular dynamics is not energy conserving
• Four-Dimensional-Spacetime Atomistic Artificial Intelligence Models
• Building Robust Machine Learning Models for Small Chemical Science Data: The Case of Shear Viscosity