# Variational Selection of Features for Molecular Kinetics

arXiv: https://arxiv.org/abs/1811.11714 · HTML: https://mlsanity.com/paper/1811.11714/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Deeptime: a Python library for machine learning dynamical models from time series data](https://mlsanity.com/paper/2110.15013/) (2021)
- [Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy](https://mlsanity.com/paper/2201.02867/) (2022)
- [GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomolecules](https://mlsanity.com/paper/2201.04609/) (2022)
- [Reaction coordinate flows for model reduction of molecular kinetics](https://mlsanity.com/paper/2309.05878/) (2023)
- [Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamics](https://mlsanity.com/paper/2409.19838/) (2024)
- [Improving Estimation of the Koopman Operator with Kolmogorov-Smirnov Indicator Functions](https://mlsanity.com/paper/2306.05945/) (2023)
- [Temporal Subspace Clustering for Molecular Dynamics Data](https://mlsanity.com/paper/2408.00056/) (2024)
- [Learning Topological Representations of Protein Structure and Dynamics](https://mlsanity.com/paper/2606.14737/) (2026)

## Abstract (arXiv)

The modeling of atomistic biomolecular simulations using kinetic models such as Markov state models (MSMs) has had many notable algorithmic advances in recent years. The variational principle has opened the door for a nearly fully automated toolkit for selecting models that predict the long-time kinetics from molecular dynamics simulations. However, one yet-unoptimized step of the pipeline involves choosing the features, or collective variables, from which the model should be constructed. In order to build intuitive models, these collective variables are often sought to be interpretable and familiar features, such as torsional angles or contact distances in a protein structure. However, previous approaches for evaluating the chosen features rely on constructing a full MSM, which in turn requires additional hyperparameters to be chosen, and hence leads to a computationally expensive framework. Here, we present a method to optimize the feature choice directly, without requiring the construction of the final kinetic model. We demonstrate our rigorous preprocessing algorithm on a canonical set of twelve fast-folding protein simulations, and show that our procedure leads to more efficient model selection.