Transferable neural networks for enhanced sampling of protein dynamics
This work addresses the challenge of probing protein variations in biophysical simulations, though it appears incremental as it builds on existing variational auto-encoder frameworks with modifications for transferability.
The authors tackled the problem of efficiently sampling protein dynamics across related systems by developing a transferable neural network method that uses a non-linear latent embedding as a collective variable for enhanced sampling, demonstrating its ability to rapidly sample mutant proteins like the GTT mutation after training on the WW domain.
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.