Transition Path Sampling with Boltzmann Generator-Based MCMC Moves

Abstract

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.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Plainer et al. "Transition Path Sampling with Boltzmann Generator-Based MCMC Moves." NeurIPS 2023 Workshops: GenBio, 2023.

Markdown

[Plainer et al. "Transition Path Sampling with Boltzmann Generator-Based MCMC Moves." NeurIPS 2023 Workshops: GenBio, 2023.](https://mlanthology.org/neuripsw/2023/plainer2023neuripsw-transition-a/)

BibTeX

@inproceedings{plainer2023neuripsw-transition-a,
  title     = {{Transition Path Sampling with Boltzmann Generator-Based MCMC Moves}},
  author    = {Plainer, Michael and Stark, Hannes and Bunne, Charlotte and Günnemann, Stephan},
  booktitle = {NeurIPS 2023 Workshops: GenBio},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/plainer2023neuripsw-transition-a/}
}