Enhanced Diffusion Sampling: Efficient Rare Event Sampling and Free Energy Calculation with Diffusion Models

TL;DR

This paper introduces enhanced diffusion sampling methods that improve rare-event exploration in molecular dynamics, enabling fast, accurate free energy calculations while maintaining unbiased thermodynamic estimates.

Contribution

The authors develop a framework combining diffusion models with biased ensemble techniques and exact reweighting to efficiently sample rare events in molecular systems.

Findings

Achieved fast and accurate free energy estimates in protein folding.

Demonstrated scalability on GPU within hours per system.

Closed the rare-event sampling gap in diffusion-model-based methods.

Abstract

The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently, diffusion models such as BioEmu have emerged as powerful equilibrium samplers that generate independent samples from complex molecular distributions, eliminating the cost of sampling rare transition events. However, a sampling problem remains when computing observables that rely on states which are rare in equilibrium, for example folding free energies. Here, we introduce enhanced diffusion sampling, enabling efficient exploration of rare-event regions while preserving unbiased thermodynamic estimators. The key idea is to perform quantitatively accurate steering protocols to generate biased ensembles and subsequently recover equilibrium statistics via exact reweighting. We instantiate our framework in three algorithms: UmbrellaDiff (umbrella sampling with diffusion models), $\Delta$G-Diff (free-energy differences via tilted ensembles), and MetaDiff (a batchwise analogue for metadynamics). Across toy systems, protein folding landscapes and folding free energies, our methods achieve fast, accurate, and scalable estimation of equilibrium properties within GPU-minutes to hours per system -- closing the rare-event sampling gap that remained after the advent of diffusion-model equilibrium samplers.