Recovering Hidden Degrees of Freedom Using Gaussian Processes

Abstract: Dimensionality reduction represents a crucial step in extracting meaningful insights from Molecular Dynamics (MD) simulations. Conventional approaches, including linear methods such as principal component analysis as well as various autoencoder architectures, typically operate under the assumption of independent and identically distributed data, disregarding the sequential nature of MD simulations. Here, we introduce a physics-informed representation learning framework that leverages Gaussian Processes combined with variational autoencoders to exploit the temporal dependencies inherent in MD data. Time-dependent kernel functions--such as the Mat\'ern kernel--directly impose impose the temporal correlation structure of the input coordinates onto a low-dimensional space, preserving Markovianity in the reduced representation while faithfully capturing the essential dynamics. Using a three-dimensional toy model, we demonstrate that this approach can successfully identify and separate dynamically distinct states that are geometrically indistinguishable due to hidden degrees of freedom. The resulting embedding features enhance metastability, facilitating the construction of Markov state models with smaller lag times and better convergence of implied timescales. This time-aware perspective provides a promising framework for understanding complex biomolecular systems, in which conventional collective variables may fail to capture the full dynamical picture.