Transition Path Sampling with Boltzmann Generator-based MCMC Moves
This work addresses a bottleneck in computational chemistry for applications like catalyst design and drug discovery by providing a more efficient sampling approach, though it appears incremental as it builds on existing MCMC and normalizing flow techniques.
The paper tackles the problem of sampling transition paths between molecular states by proposing a method that operates in the latent space of a normalizing flow, eliminating the need for time-intensive molecular dynamics simulations, and demonstrates its application on alanine dipeptide with exact sampling via Metropolis-Hastings criteria.
Sampling all possible transition paths between two 3D states of a molecular system has various applications ranging from catalyst design to drug discovery. Current approaches to sample transition paths use Markov chain Monte Carlo and rely on time-intensive molecular dynamics simulations to find new paths. Our approach operates in the latent space of a normalizing flow that maps from the molecule's Boltzmann distribution to a Gaussian, where we propose new paths without requiring molecular simulations. Using alanine dipeptide, we explore Metropolis-Hastings acceptance criteria in the latent space for exact sampling and investigate different latent proposal mechanisms.