Machine learning kinetics from molecular dynamics data
physics.comp-ph, cond-mat.stat-mech, cs.LG, physics.chem-ph, physics.data-an
Submitted: 2026-09-15
Updated: 2026-09-15
Comments: 24 pages, 5 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Most molecular transitions occur on timescales far beyond direct molecular dynamics simulations.
Terminology
Abstract
Most molecular transitions occur on timescales far beyond direct molecular dynamics simulations. The committor, the probability that a configuration reaches a product state before a reactant state, is a central kinetic statistic, providing a mechanism-independent reaction coordinate and a foundation for transition path theory and the calculation of rates. This review surveys modern approaches for estimating the committor and related kinetic statistics from molecular simulations, with an emphasis on self-supervised methods that learn solutions of their defining dynamical equations rather than relying on labeled shooting data. We develop a common operator viewpoint connecting generator-based partial differential equations, variational principles, Markov state models, dynamical Galerkin approximation, and neural networks. Empirical and theoretical evidence points to the efficiency of these methods. We provide theoretical and practical guidance for realizing their full potential in applications, including strategies for treating non-Markovian effects and for sampling. We conclude by identifying opportunities for further research, including connections to reinforcement learning and generative modeling.
Sources
- An Introduction To Langer's Theory
- Markov state models revisited: Principles and algorithms for unbiased observables
- Fast operator learning for mapping correlations
- Approximating committor functions: Objective functions and training data sampling
- Let's Stalk About Membranes: Committor-Based Enhanced Sampling of Stalk Formation
- Rare Event Analysis via Stochastic Optimal Control
- Designing losses for data-free training of normalizing flows on Boltzmann distributions
- Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional
- Composing diffusion priors with explicit physical context via generative Gibbs sampling
- Quantum statistics from classical simulations via generative Gibbs sampling
Related papers
- Learning Spectral-Like Mesh-Free Discretisations
- Breaking the Exascale Barrier for the Electronic Structure Problem in Ab-Initio Molecular Dynamics
- Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations
- Metal-Insulator Transition of Solid Hydrogen by the Antisymmetric Shadow Wave Function
- Resonating Valence Bond Quantum Monte Carlo: Application to the ozone molecule
- Quantifying Gibbs measures of disordered crystals up to the solid-liquid phase transition