Invertible Coarse Graining with Physics-Informed Generative Artificial Intelligence

TL;DR

This paper introduces Cycle Coarse Graining (CCG), a unified physics-informed generative approach that enhances multiscale molecular modeling by enabling bidirectional information exchange between coarse and fine representations.

Contribution

The work develops a novel theory and methodology that simultaneously constructs coarse models and reconstructs fine details using deep generative models, linking two traditionally separate problems.

Findings

Enables efficient reconstruction of molecular details from coarse models.

Improves coarse-grained models with physics-informed feedback.

Facilitates free energy calculations without rare-event sampling.

Abstract

Multiscale molecular modeling is widely applied in scientific research of molecular properties over large time and length scales. Two specific challenges are commonly present in multiscale modeling, provided that information between the coarse and fine representations of molecules needs to be properly exchanged: One is to construct coarse grained models by passing information from the fine to coarse levels; the other is to restore finer molecular details given coarse grained configurations. Although these two problems are commonly addressed independently, in this work, we present a theory connecting them, and develop a methodology called Cycle Coarse Graining (CCG) to solve both problems in a unified manner. In CCG, reconstruction can be achieved via a tractable deep generative model, allowing retrieval of fine details from coarse-grained simulations. The reconstruction in turn delivers better coarse-grained models which are informed of the fine-grained physics, and enables calculation of the free energies in a rare-event-free manner. CCG thus provides a systematic way for multiscale molecular modeling, where the finer details of coarse-grained simulations can be efficiently retrieved, and the coarse-grained models can be improved consistently.