State Predictive Information Bottleneck

TL;DR

This paper introduces a deep learning method called State Predictive Information Bottleneck (SPIB) to learn reaction coordinates from high-dimensional molecular dynamics data, connecting AI techniques with traditional chemical physics insights.

Contribution

The paper presents a novel deep learning approach that learns physically interpretable reaction coordinates, related to the committor, and introduces a hyperparameter for controlling metastable state classification.

Findings

The learned reaction coordinate is analytically and numerically connected to the committor.

The hyperparameter controls the level of coarse-graining in metastable state classification.

SPIB accurately identifies transition states in benchmark systems.

Abstract

The ability to make sense of the massive amounts of high-dimensional data generated from molecular dynamics (MD) simulations is heavily dependent on the knowledge of a low dimensional manifold (parameterized by a reaction coordinate or RC) that typically distinguishes between relevant metastable states and which captures the relevant slow dynamics of interest. Methods based on machine learning and artificial intelligence have been proposed over the years to deal with learning such low-dimensional manifolds, but they are often criticized for a disconnect from more traditional and physically interpretable approaches. To deal with such concerns, in this work, we propose a deep learning based State Predictive Information Bottleneck (SPIB) approach to learn the RC from high dimensional molecular simulation trajectories. We demonstrate analytically and numerically how the RC learnt in this approach is deeply connected to the committor in chemical physics, and can be used to accurately identify transition states. A crucial hyperparameter in this approach is the time-delay, or how far into the future the algorithm should make predictions about. Through careful comparisons for benchmark systems, we demonstrate that this hyperparameter choice gives useful control over how coarse-grained we want the metastable state classification of the system to be. We thus believe that this work represents a step forward in systematic application of deep learning based ideas to molecular simulations in a way that bridges the gap between artificial intelligence and traditional chemical physics.