Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics

TL;DR

This paper introduces a novel learning-based framework called LED that significantly accelerates molecular simulations by capturing effective dynamics, enabling exploration of longer timescales in complex molecular systems.

Contribution

The paper presents a new probabilistic learning framework that extends equation-free methods to efficiently simulate molecular systems over much longer timescales.

Findings

Achieves up to 1000x speedup in simulations

Successfully models complex molecular systems like Trp Cage and alanine dipeptide

Provides explainable reduced-order representations of molecular dynamics

Abstract

Simulations are vital for understanding and predicting the evolution of complex molecular systems. However, despite advances in algorithms and special purpose hardware, accessing the timescales necessary to capture the structural evolution of bio-molecules remains a daunting task. In this work we present a novel framework to advance simulation timescales by up to three orders of magnitude, by learning the effective dynamics (LED) of molecular systems. LED augments the equation-free methodology by employing a probabilistic mapping between coarse and fine scales using mixture density network (MDN) autoencoders and evolves the non-Markovian latent dynamics using long short-term memory MDNs. We demonstrate the effectiveness of LED in the M\"ueller-Brown potential, the Trp Cage protein, and the alanine dipeptide. LED identifies explainable reduced-order representations and can generate, at any instant, the respective all-atom molecular trajectories. We believe that the proposed framework provides a dramatic increase to simulation capabilities and opens new horizons for the effective modeling of complex molecular systems.