Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions

2025-11-03

AI Summary

In molecular simulations, coarse-graining accelerates computation but sacrifices atomic-level detail; its inverse mapping—recovering atomistic configurations from coarse-grained (CG) structures—has long suffered from low fidelity and the absence of quantifiable information loss. This work introduces *split-flows*, a novel method that formulates cross-resolution inverse mapping as a continuous-time measure transport problem, establishing for the first time a direct probabilistic mapping between CG and atomistic scales. Leveraging flow-based generative modeling, split-flows enables high-fidelity, conditional sampling of atomistic structures and analytically derives the information entropy loss incurred during mapping—providing a computationally tractable theoretical framework for assessing information fidelity of CG models. Validated on chignolin, alanine dipeptide, and lipid bilayer systems, split-flows achieves significantly higher back-mapping accuracy than state-of-the-art methods and enables quantitative comparison of information loss across distinct CG representations.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

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.

Problem

• Recovering atomistic detail lost in coarse-grained molecular simulations
• Establishing probabilistic mapping between molecular resolution scales
• Quantifying information loss during coarse-graining through mapping entropies

Innovation

• Flow-based approach for continuous-time measure transport
• Direct probabilistic link enabling expressive conditional sampling
• Tractable computation of mapping entropies across resolutions