Revealing the Atomistic Mechanism of Rare Events in Molecular Dynamics

TL;DR

The paper introduces AMORE-MD, a framework that interprets deep-learned reaction coordinates in molecular dynamics, revealing atomistic mechanisms of rare conformational transitions without prior knowledge.

Contribution

AMORE-MD connects deep learning reaction coordinates to atomistic mechanisms, enabling interpretable analysis of rare events in molecular dynamics simulations.

Findings

Successfully recovers known mechanisms in test systems

Provides chemically interpretable structural rearrangements

Enhances sampling of rare transition regions

Abstract

Interpretable reaction coordinates are essential for understanding rare conformational transitions in molecular dynamics. The Atomistic Mechanism Of Rare Events in Molecular Dynamics (AMORE-MD) framework enhances interpretability of deep-learned reaction coordinates by connecting them to atomistic mechanisms, without requiring any a priori knowledge of collective variables, pathways, or endpoints. Here, AMORE-MD employs the ISOKANN algorithm to learn a neural membership function $\chi$ representing the dominant slow process, from which transition pathways are reconstructed as minimum-energy paths aligned with the gradient of $\chi$, and atomic contributions are quantified through gradient-based sensitivity analysis. Iterative enhanced sampling further enriches transition regions and improves coverage of rare events enabling recovery of known mechanisms and chemically interpretable structural rearrangements at atomic resolution for the M\"uller-Brown potential, alanine dipeptide, and the elastin-derived hexapeptide VGVAPG.