# Characterizing metastable states with the help of machine learning

arXiv: https://arxiv.org/abs/2204.07391 · HTML: https://mlsanity.com/paper/2204.07391/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 47 references that are in the map.
- First posted on arXiv 15 Apr 2022.

## Builds on (most cited first, 3 of 3)

- [VAMPnets: Deep learning of molecular kinetics](https://mlsanity.com/paper/1710.06012/) (2017)
- [Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets](https://mlsanity.com/paper/1902.03336/) (2019)
- [Improving Sample and Feature Selection with Principal Covariates Regression](https://mlsanity.com/paper/2012.12253/) (2020)

## Built on by (most cited first, 5 of 5)

- [Learning invariant representations of time-homogeneous stochastic dynamical systems](https://mlsanity.com/paper/2307.09912/) (2023)
- [Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems](https://mlsanity.com/paper/2505.18671/) (2025)
- [Spectral Map for Slow Collective Variables, Markovian Dynamics, and Transition State Ensembles](https://mlsanity.com/paper/2409.06428/) (2024)
- [Machine Learning of Slow Collective Variables and Enhanced Sampling via Spatial Techniques](https://mlsanity.com/paper/2412.20868/) (2024)
- [Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination](https://mlsanity.com/paper/2605.24136/) (2026)

## Abstract (arXiv)

Present-day atomistic simulations generate long trajectories of ever more complex systems. Analyzing these data, discovering metastable states, and uncovering their nature is becoming increasingly challenging. In this paper, we first use the variational approach to conformation dynamics to discover the slowest dynamical modes of the simulations. This allows the different metastable states of the system to be located and organized hierarchically. The physical descriptors that characterize metastable states are discovered by means of a machine learning method. We show in the cases of two proteins, Chignolin and Bovine Pancreatic Trypsin Inhibitor, how such analysis can be effortlessly performed in a matter of seconds. Another strength of our approach is that it can be applied to the analysis of both unbiased and biased simulations.