Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional

Sanjeev Raja, Martin Sipka, Michael Psenka, Tobias Kreiman, Michal Pavelka, Aditi S. Krishnapriyan

Track: Machine learning: computational method and/or computational results

Nature Biotechnology: No

Keywords: transition path sampling, molecular dynamics, generative models, diffusion models, flow matching models

TL;DR: We repurpose generative models for transition path sampling via minimization of the Onsager-Machlup action functional.

Abstract: Transition path sampling (TPS), which involves finding probable paths connecting two points on an energy landscape, remains a challenge due to the complexity of real-world atomistic systems. Current machine learning approaches rely on expensive training procedures and under-utilize growing quantities of atomistic data, limiting scalability and generalization. In this work, we address TPS by interpreting candidate paths as trajectories sampled from stochastic dynamics induced by the learned score function of generative models, namely denoising diffusion and flow matching. Under these dynamics, finding high-likelihood transition paths becomes equivalent to minimizing the Onsager-Machlup (OM) action functional, enabling us to repurpose pre-trained generative models for TPS in a zero-shot fashion. We demonstrate our approach on several fast-folding proteins, where we obtain diverse, physically realistic transition pathways, as well as tetrapeptides, where we demonstrate successful TPS on systems not seen by the generative model during training. Our method can be easily incorporated into new generative models, making it practically relevant as models continue to scale and improve.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Sanjeev_Raja1

Format: Yes, the presenting author will definitely attend in person because they attending ICLR for other complementary reasons.

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Submission Number: 51