Variational Selection of Features for Molecular Kinetics

by   Martin K. Scherer, et al.
Freie Universität Berlin

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.


page 5

page 7

page 10

page 11


VAMPnets: Deep learning of molecular kinetics

Here we develop a deep learning framework for molecular kinetics from mo...

Learning Geometrically Disentangled Representations of Protein Folding Simulations

Massive molecular simulations of drug-target proteins have been used as ...

Collective variable discovery in the age of machine learning: reality, hype and everything in between

Understanding kinetics and thermodynamics profile of biomolecules is nec...

Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations

Markov state models (MSMs) and Master equation models are popular approa...

Understanding recent deep-learning techniques for identifying collective variables of molecular dynamics

The dynamics of a high-dimensional metastable molecular system can often...

Understanding Protein Dynamics with L1-Regularized Reversible Hidden Markov Models

We present a machine learning framework for modeling protein dynamics. O...

Please sign up or login with your details

Forgot password? Click here to reset