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

2026-02-18

AI Summary

This work addresses the inefficient sampling of rare events—such as protein folding—in molecular dynamics, which severely hampers accurate computation of equilibrium thermodynamic quantities like free energy. The authors propose a diffusion model–based enhanced sampling framework that uniquely integrates concepts from umbrella sampling, free energy difference estimation, and metadynamics, yielding three novel algorithms: UmbrellaDiff, ΔG-Diff, and MetaDiff. These methods generate biased ensembles through controllable guidance and recover unbiased thermodynamic estimates via exact reweighting. Demonstrated on toy models, protein folding landscapes, and free energy calculations, the approach achieves high accuracy and efficiency, requiring only minutes to hours of GPU time to obtain equilibrium properties—thereby substantially narrowing the sampling gap for rare events.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Diffusion Models for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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), $Δ$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.

Problem

• rare-event sampling
• molecular dynamics
• free energy calculation
• equilibrium sampling
• biomolecular simulation

Innovation

• enhanced diffusion sampling
• diffusion models
• rare-event sampling
• free energy calculation
• exact reweighting