VAMPnets: Deep learning of molecular kinetics

TL;DR

VAMPnets is a deep learning framework that automates the analysis of molecular dynamics data to accurately model biomolecular kinetics and conformational states in an end-to-end manner.

Contribution

It introduces VAMPnets, a neural network-based approach that streamlines and improves the modeling of molecular kinetics from simulation data.

Findings

Performs as well or better than existing Markov models

Provides interpretable kinetic models with few states

Enables end-to-end analysis of molecular dynamics data

Abstract

There is an increasing demand for computing the relevant structures, equilibria and long-timescale kinetics of biomolecular processes, such as protein-drug binding, from high-throughput molecular dynamics simulations. Current methods employ transformation of simulated coordinates into structural features, dimension reduction, clustering the dimension-reduced data, and estimation of a Markov state model or related model of the interconversion rates between molecular structures. This handcrafted approach demands a substantial amount of modeling expertise, as poor decisions at any step will lead to large modeling errors. Here we employ the variational approach for Markov processes (VAMP) to develop a deep learning framework for molecular kinetics using neural networks, dubbed VAMPnets. A VAMPnet encodes the entire mapping from molecular coordinates to Markov states, thus combining the whole data processing pipeline in a single end-to-end framework. Our method performs equally or better than state-of-the art Markov modeling methods and provides easily interpretable few-state kinetic models.