Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs

TL;DR

This paper introduces a method combining autoencoders and linear operators to predict future states of molecular systems efficiently, capturing both structural and physical dynamics from simulation data.

Contribution

It develops a pipeline for graph-structured representations and trains autoencoders with linear operators to improve molecular dynamics predictions.

Findings

Increasing autoencoder output dimensionality enhances prediction accuracy.

The approach isolates physical system characteristics during training.

Future states can be inferred without costly simulations.

Abstract

Molecular dynamics simulations produce data with complex nonlinear dynamics. If the timestep behavior of such a dynamic system can be represented by a linear operator, future states can be inferred directly without expensive simulations. The use of an autoencoder in combination with a physical timestep operator allows both the relevant structural characteristics of the molecular graphs and the underlying physics of the system to be isolated during the training process. In this work, we develop a pipeline for establishing graph-structured representations of time-series volumetric data from molecular dynamics simulations. We then train an autoencoder to find nonlinear mappings to a latent space where future timesteps can be predicted through application of a linear operator trained in tandem with the autoencoder. Increasing the dimensionality of the autoencoder output is shown to improve the accuracy of the physical timestep operator.