Learning Biomolecular Motion: The Physics-Informed Machine Learning Paradigm
This addresses the biomolecular closure problem for computational chemistry and biophysics researchers, though it is a review of existing methods rather than presenting new incremental results.
The paper tackles the challenge of modeling biomolecular systems by integrating physics-informed machine learning (PIML) to improve accuracy, generalizability, and extrapolation beyond observed data, focusing on areas like long-timescale kinetics and free-energy estimation.
The convergence of statistical learning and molecular physics is transforming our approach to modeling biomolecular systems. Physics-informed machine learning (PIML) offers a systematic framework that integrates data-driven inference with physical constraints, resulting in models that are accurate, mechanistic, generalizable, and able to extrapolate beyond observed domains. This review surveys recent advances in physics-informed neural networks and operator learning, differentiable molecular simulation, and hybrid physics-ML potentials, with emphasis on long-timescale kinetics, rare events, and free-energy estimation. We frame these approaches as solutions to the "biomolecular closure problem", recovering unresolved interactions beyond classical force fields while preserving thermodynamic consistency and mechanistic interpretability. We examine theoretical foundations, tools and frameworks, computational trade-offs, and unresolved issues, including model expressiveness and stability. We outline prospective research avenues at the intersection of machine learning, statistical physics, and computational chemistry, contending that future advancements will depend on mechanistic inductive biases, and integrated differentiable physical learning frameworks for biomolecular simulation and discovery.