Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Ziyang, Huang, Wenbing, Liu, Yang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909414679642112
author Yu, Ziyang
Huang, Wenbing
Liu, Yang
author_facet Yu, Ziyang
Huang, Wenbing
Liu, Yang
contents Molecular Dynamics (MD) is crucial in various fields such as materials science, chemistry, and pharmacology to name a few. Conventional MD software struggles with the balance between time cost and prediction accuracy, which restricts its wider application. Recently, data-driven approaches based on deep generative models have been devised for time-coarsened dynamics, which aim at learning dynamics of diverse molecular systems over a long timestep, enjoying both universality and efficiency. Nevertheless, most current methods are designed solely to learn from the data distribution regardless of the underlying Boltzmann distribution, and the physics priors such as energies and forces are constantly overlooked. In this work, we propose a conditional generative model called Force-guided Bridge Matching (FBM), which learns full-atom time-coarsened dynamics and targets the Boltzmann-constrained distribution. With the guidance of our delicately-designed intermediate force field, FBM leverages favourable physics priors into the generation process, giving rise to enhanced simulations. Experiments on two datasets consisting of peptides verify our superiority in terms of comprehensive metrics and demonstrate transferability to unseen systems.
format Preprint
id arxiv_https___arxiv_org_abs_2408_15126
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides
Yu, Ziyang
Huang, Wenbing
Liu, Yang
Chemical Physics
Machine Learning
Computational Physics
Biomolecules
Molecular Dynamics (MD) is crucial in various fields such as materials science, chemistry, and pharmacology to name a few. Conventional MD software struggles with the balance between time cost and prediction accuracy, which restricts its wider application. Recently, data-driven approaches based on deep generative models have been devised for time-coarsened dynamics, which aim at learning dynamics of diverse molecular systems over a long timestep, enjoying both universality and efficiency. Nevertheless, most current methods are designed solely to learn from the data distribution regardless of the underlying Boltzmann distribution, and the physics priors such as energies and forces are constantly overlooked. In this work, we propose a conditional generative model called Force-guided Bridge Matching (FBM), which learns full-atom time-coarsened dynamics and targets the Boltzmann-constrained distribution. With the guidance of our delicately-designed intermediate force field, FBM leverages favourable physics priors into the generation process, giving rise to enhanced simulations. Experiments on two datasets consisting of peptides verify our superiority in terms of comprehensive metrics and demonstrate transferability to unseen systems.
title Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides
topic Chemical Physics
Machine Learning
Computational Physics
Biomolecules
url https://arxiv.org/abs/2408.15126