Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions
This addresses a central challenge in molecular modeling for researchers needing atomistic accuracy from accelerated simulations, though it is incremental as it builds on existing generative strategies.
The paper tackles the problem of recovering fine-grained atomistic details from coarse-grained molecular models, introducing split-flows as a flow-based method that enables accurate conditional sampling and, for the first time, tractable computation of mapping entropies to quantify information loss.
By reducing resolution, coarse-grained models greatly accelerate molecular simulations, unlocking access to long-timescale phenomena, though at the expense of microscopic information. Recovering this fine-grained detail is essential for tasks that depend on atomistic accuracy, making backmapping a central challenge in molecular modeling. We introduce split-flows, a novel flow-based approach that reinterprets backmapping as a continuous-time measure transport across resolutions. Unlike existing generative strategies, split-flows establish a direct probabilistic link between resolutions, enabling expressive conditional sampling of atomistic structures and -- for the first time -- a tractable route to computing mapping entropies, an information-theoretic measure of the irreducible detail lost in coarse-graining. We demonstrate these capabilities on diverse molecular systems, including chignolin, a lipid bilayer, and alanine dipeptide, highlighting split-flows as a principled framework for accurate backmapping and systematic evaluation of coarse-grained models.