Note: Variational Encoding of Protein Dynamics Benefits from Maximizing Latent Autocorrelation
This is an incremental improvement for researchers in computational biology and chemistry aiming to better analyze protein dynamics.
The paper tackles the problem of modeling biomolecular simulation data by proposing that maximizing latent autocorrelation in Variational Auto-Encoders helps identify slow processes, showing that the VDE framework with this loss outperforms related methods.
As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while inferring a reduced coordinate, which assists in finding slow processes as according to the variational approach to conformational dynamics. We additionally provide evidence that the VDE framework (Hernández et al., 2017), which uses this autocorrelation loss along with a time-lagged reconstruction loss, obtains a variationally optimized latent coordinate in comparison with related loss functions. We thus recommend leveraging the autocorrelation of the latent space while training neural network models of biomolecular simulation data to better represent slow processes.