Transferable neural networks for enhanced sampling of protein dynamics

TL;DR

This paper introduces a transferable neural network approach using variational auto-encoders as collective variables for enhanced sampling in protein dynamics, enabling rapid analysis across related systems.

Contribution

The work presents a novel method that allows transfer of learned models for enhanced sampling from one protein system to related systems, improving efficiency.

Findings

Successfully described force field effects in alanine dipeptide.

Transferred models from WW domain to GTT mutant protein.

Enhanced sampling efficiency in related protein systems.

Abstract

Variational auto-encoder frameworks have demonstrated success in reducing complex nonlinear dynamics in molecular simulation to a single non-linear embedding. In this work, we illustrate how this non-linear latent embedding can be used as a collective variable for enhanced sampling, and present a simple modification that allows us to rapidly perform sampling in multiple related systems. We first demonstrate our method is able to describe the effects of force field changes in capped alanine dipeptide after learning a model using AMBER99. We further provide a simple extension to variational dynamics encoders that allows the model to be trained in a more efficient manner on larger systems by encoding the outputs of a linear transformation using time-structure based independent component analysis (tICA). Using this technique, we show how such a model trained for one protein, the WW domain, can efficiently be transferred to perform enhanced sampling on a related mutant protein, the GTT mutation. This method shows promise for its ability to rapidly sample related systems using a single transferable collective variable and is generally applicable to sets of related simulations, enabling us to probe the effects of variation in increasingly large systems of biophysical interest.