Flow Matching for Optimal Reaction Coordinates of Biomolecular System
This provides a more efficient method for analyzing biomolecular dynamics, which is important for computational biophysicists studying protein folding and molecular interactions.
The authors tackled the problem of identifying optimal reaction coordinates in biomolecular systems by developing FMRC, a deep learning algorithm that encodes dynamics into low-dimensional coordinates without explicitly learning transfer operators. They demonstrated FMRC's superiority over state-of-the-art methods in three complex biomolecular systems by evaluating Markov state model quality.
We present flow matching for reaction coordinates (FMRC), a novel deep learning algorithm designed to identify optimal reaction coordinates (RC) in biomolecular reversible dynamics. FMRC is based on the mathematical principles of lumpability and decomposability, which we reformulate into a conditional probability framework for efficient data-driven optimization using deep generative models. While FMRC does not explicitly learn the well-established transfer operator or its eigenfunctions, it can effectively encode the dynamics of leading eigenfunctions of the system transfer operator into its low-dimensional RC space. We further quantitatively compare its performance with several state-of-the-art algorithms by evaluating the quality of Markov state models (MSM) constructed in their respective RC spaces, demonstrating the superiority of FMRC in three increasingly complex biomolecular systems. In addition, we successfully demonstrated the efficacy of FMRC for bias deposition in the enhanced sampling of a simple model system. Finally, we discuss its potential applications in downstream applications such as enhanced sampling methods and MSM construction.