Flow Matching for Optimal Reaction Coordinates of Biomolecular System

Abstract

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.

For Supporting Information, please see https://pubs.acs.org/doi/full/10.1021/acs.jctc.4c01139

References in corpus (4)

• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• State Predictive Information Bottleneck
• Computing the Committor with the Committor: an Anatomy of the Transition State Ensemble
• Optimal Low-dimensional Approximation of Transfer Operators via Flow Matching: Computation and Error Analysis