An Iterative Framework for Generative Backmapping of Coarse Grained Proteins

TL;DR

This paper presents an iterative, neural network-based framework for improving the accuracy and efficiency of backmapping coarse-grained protein models to detailed atomistic structures, addressing key challenges in the field.

Contribution

It introduces a novel iterative approach using conditional VAEs and graph neural networks for more accurate and stable backmapping of large biomolecules.

Findings

Enhanced accuracy in protein backmapping

Improved training stability and efficiency

Effective for ultra-coarse protein representations

Abstract

The techniques of data-driven backmapping from coarse-grained (CG) to fine-grained (FG) representation often struggle with accuracy, unstable training, and physical realism, especially when applied to complex systems such as proteins. In this work, we introduce a novel iterative framework by using conditional Variational Autoencoders and graph-based neural networks, specifically designed to tackle the challenges associated with such large-scale biomolecules. Our method enables stepwise refinement from CG beads to full atomistic details. We outline the theory of iterative generative backmapping and demonstrate via numerical experiments the advantages of multistep schemes by applying them to proteins of vastly different structures with very coarse representations. This multistep approach not only improves the accuracy of reconstructions but also makes the training process more computationally efficient for proteins with ultra-CG representations.