Generative methods for sampling transition paths in molecular dynamics

2022/05/05 by Tony Lelièvre, Lelièvre, Tony, Geneviève Robin +7 · 1 citation
Biochemistry, Genetics and Molecular Biology · Materials Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.48550/arxiv.2205.02818

openalex publication_date 2022/05/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Molecular systems often remain trapped for long times around some local minimum of the potential energy function, before switching to another one -- a behavior known as metastability. Simulating transition paths linking one metastable state to another one is difficult by direct numerical methods. In view of the promises of machine learning techniques, we explore in this work two approaches to more efficiently generate transition paths: sampling methods based on generative models such as variational autoencoders, and importance sampling methods based on reinforcement learning.

Cited by

• ProTDyn: a foundation Protein language model for Thermodynamics and Dynamics generation

Related

• Diffusion Methods for Generating Transition Paths
• Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional
• Generalized Flow Matching for Transition Dynamics Modeling
• The seeds of the future are in the present: A blind exploration of metastable states
• Computing Transition Pathways for the Study of Rare Events Using Deep Reinforcement Learning