Deep Generative Markov State Models

Abstract

We propose a deep generative Markov State Model (DeepGenMSM) learning framework for inference of metastable dynamical systems and prediction of trajectories. After unsupervised training on time series data, the model contains (i) a probabilistic encoder that maps from high-dimensional configuration space to a small-sized vector indicating the membership to metastable (long-lived) states, (ii) a Markov chain that governs the transitions between metastable states and facilitates analysis of the long-time dynamics, and (iii) a generative part that samples the conditional distribution of configurations in the next time step. The model can be operated in a recursive fashion to generate trajectories to predict the system evolution from a defined starting state and propose new configurations. The DeepGenMSM is demonstrated to provide accurate estimates of the long-time kinetics and generate valid distributions for molecular dynamics (MD) benchmark systems. Remarkably, we show that DeepGenMSMs are able to make long time-steps in molecular configuration space and generate physically realistic structures in regions that were not seen in training data.

Cited by in corpus (8)

• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
• Deep learning Markov and Koopman models with physical constraints
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Deeptime: a Python library for machine learning dynamical models from time series data
• Machine Learning of coarse-grained Molecular Dynamics Force Fields
• Physics-aware, probabilistic model order reduction with guaranteed stability
• Kernel Embedding based Variational Approach for Low-dimensional Approximation of Dynamical Systems