Deep Generative Markov State Models
This work addresses the challenge of inferring and predicting dynamics in complex systems like molecular dynamics, offering a novel approach for researchers in computational chemistry and biophysics.
The authors tackled the problem of modeling metastable dynamical systems and predicting trajectories by proposing DeepGenMSM, a deep generative framework that provides accurate long-time kinetics estimates and generates physically realistic structures, even in unseen regions of molecular configuration space.
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.