Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

TL;DR

Timewarp is a transferable acceleration method for molecular dynamics that learns to make large, time-coarsened steps using normalizing flows, enabling efficient sampling of long-timescale molecular processes across different systems.

Contribution

It introduces a transferable, learned acceleration technique using normalizing flows to enhance sampling efficiency in molecular dynamics simulations.

Findings

Timewarp generalizes to unseen small peptides at all-atom resolution.

It achieves significant wall-clock acceleration over standard MD.

The method effectively explores metastable states in molecular systems.

Abstract

Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{s}$). MD is often used to compute equilibrium properties, which requires sampling from an equilibrium distribution such as the Boltzmann distribution. However, many important processes, such as binding and folding, occur over timescales of milliseconds or beyond, and cannot be efficiently sampled with conventional MD. Furthermore, new MD simulations need to be performed for each molecular system studied. We present Timewarp, an enhanced sampling method which uses a normalising flow as a proposal distribution in a Markov chain Monte Carlo method targeting the Boltzmann distribution. The flow is trained offline on MD trajectories and learns to make large steps in time, simulating the molecular dynamics of $10^{5} - 10^{6}\:\textrm{fs}$. Crucially, Timewarp is transferable between molecular systems: once trained, we show that it generalises to unseen small peptides (2-4 amino acids) at all-atom resolution, exploring their metastable states and providing wall-clock acceleration of sampling compared to standard MD. Our method constitutes an important step towards general, transferable algorithms for accelerating MD.