Enhancing Diffusion-Based Sampling with Molecular Collective Variables

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nam, Juno, Máté, Bálint, Toshev, Artur P., Kaniselvan, Manasa, Gómez-Bombarelli, Rafael, Chen, Ricky T. Q., Wood, Brandon, Liu, Guan-Horng, Miller, Benjamin Kurt
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911452142501888
author Nam, Juno
Máté, Bálint
Toshev, Artur P.
Kaniselvan, Manasa
Gómez-Bombarelli, Rafael
Chen, Ricky T. Q.
Wood, Brandon
Liu, Guan-Horng
Miller, Benjamin Kurt
author_facet Nam, Juno
Máté, Bálint
Toshev, Artur P.
Kaniselvan, Manasa
Gómez-Bombarelli, Rafael
Chen, Ricky T. Q.
Wood, Brandon
Liu, Guan-Horng
Miller, Benjamin Kurt
contents Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone, without training data. Yet, they remain impractical for molecular sampling because they are often slower than molecular dynamics and miss thermodynamically relevant modes. Inspired by enhanced sampling, we encourage exploration by introducing a sequential bias along bespoke, information-rich, low-dimensional projections of atomic coordinates known as collective variables (CVs). We introduce a repulsive potential centered on the CVs from recent samples, which pushes future samples towards novel CV regions and effectively increases the temperature in the projected space. Our resulting method improves efficiency, mode discovery, enables the estimation of free energy differences, and retains independent sampling from the approximate Boltzmann distribution via reweighting by the bias. On standard peptide conformational sampling benchmarks, the method recovers diverse conformational states and accurate free energy profiles. We are the first to demonstrate reactive sampling using a diffusion-based sampler, capturing bond breaking and formation with universal interatomic potentials at near-first-principles accuracy. The approach resolves reactive energy landscapes at a fraction of the wall-clock time of standard sampling methods, advancing diffusion-based sampling towards practical use in molecular sciences.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11923
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Diffusion-Based Sampling with Molecular Collective Variables
Nam, Juno
Máté, Bálint
Toshev, Artur P.
Kaniselvan, Manasa
Gómez-Bombarelli, Rafael
Chen, Ricky T. Q.
Wood, Brandon
Liu, Guan-Horng
Miller, Benjamin Kurt
Chemical Physics
Materials Science
Machine Learning
Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone, without training data. Yet, they remain impractical for molecular sampling because they are often slower than molecular dynamics and miss thermodynamically relevant modes. Inspired by enhanced sampling, we encourage exploration by introducing a sequential bias along bespoke, information-rich, low-dimensional projections of atomic coordinates known as collective variables (CVs). We introduce a repulsive potential centered on the CVs from recent samples, which pushes future samples towards novel CV regions and effectively increases the temperature in the projected space. Our resulting method improves efficiency, mode discovery, enables the estimation of free energy differences, and retains independent sampling from the approximate Boltzmann distribution via reweighting by the bias. On standard peptide conformational sampling benchmarks, the method recovers diverse conformational states and accurate free energy profiles. We are the first to demonstrate reactive sampling using a diffusion-based sampler, capturing bond breaking and formation with universal interatomic potentials at near-first-principles accuracy. The approach resolves reactive energy landscapes at a fraction of the wall-clock time of standard sampling methods, advancing diffusion-based sampling towards practical use in molecular sciences.
title Enhancing Diffusion-Based Sampling with Molecular Collective Variables
topic Chemical Physics
Materials Science
Machine Learning
url https://arxiv.org/abs/2510.11923