Generative Modeling of Molecular Dynamics Trajectories

TL;DR

This paper presents a generative modeling approach for molecular dynamics trajectories that enables diverse tasks like simulation, sampling, and design, demonstrating its effectiveness on peptide and protein data.

Contribution

It introduces a novel generative modeling framework conditioned on trajectory frames for flexible, multi-task surrogate modeling of molecular dynamics data.

Findings

Models can perform forward simulation and trajectory upsampling.

Generative models enable transition path sampling.

Approach produces realistic ensembles of protein structures.

Abstract

Molecular dynamics (MD) is a powerful technique for studying microscopic phenomena, but its computational cost has driven significant interest in the development of deep learning-based surrogate models. We introduce generative modeling of molecular trajectories as a paradigm for learning flexible multi-task surrogate models of MD from data. By conditioning on appropriately chosen frames of the trajectory, we show such generative models can be adapted to diverse tasks such as forward simulation, transition path sampling, and trajectory upsampling. By alternatively conditioning on part of the molecular system and inpainting the rest, we also demonstrate the first steps towards dynamics-conditioned molecular design. We validate the full set of these capabilities on tetrapeptide simulations and show that our model can produce reasonable ensembles of protein monomers. Altogether, our work illustrates how generative modeling can unlock value from MD data towards diverse downstream tasks that are not straightforward to address with existing methods or even MD itself. Code is available at https://github.com/bjing2016/mdgen.