Generative Coarse-Graining of Molecular Conformations

TL;DR

This paper introduces a generative model for accurate backmapping in molecular coarse-graining, leveraging equivariant networks to restore fine-grained structures from coarse representations with high realism.

Contribution

The paper presents a novel probabilistic, equivariant neural network model that improves backmapping accuracy in molecular simulations, addressing a key challenge in coarse-graining.

Findings

Outperforms existing methods in realistic structure recovery

Provides comprehensive benchmarks for evaluation

Effectively encodes FG uncertainties into invariant latent space

Abstract

Coarse-graining (CG) of molecular simulations simplifies the particle representation by grouping selected atoms into pseudo-beads and drastically accelerates simulation. However, such CG procedure induces information losses, which makes accurate backmapping, i.e., restoring fine-grained (FG) coordinates from CG coordinates, a long-standing challenge. Inspired by the recent progress in generative models and equivariant networks, we propose a novel model that rigorously embeds the vital probabilistic nature and geometric consistency requirements of the backmapping transformation. Our model encodes the FG uncertainties into an invariant latent space and decodes them back to FG geometries via equivariant convolutions. To standardize the evaluation of this domain, we provide three comprehensive benchmarks based on molecular dynamics trajectories. Experiments show that our approach always recovers more realistic structures and outperforms existing data-driven methods with a significant margin.