Encoding protein dynamic information in graph representation for functional residue identification

TL;DR

This paper introduces ProDAR, a graph neural network that incorporates protein dynamics via normal mode analysis, significantly improving functional residue identification and interpretability in protein structure-function prediction.

Contribution

The study presents a novel dynamics-informed graph neural network that enhances protein function prediction by integrating conformational flexibility data.

Findings

ProDAR outperforms static models in residue-level function annotation.

Dynamic information improves interpretability of protein function models.

The method effectively identifies residues with functional impact across diverse proteins.

Abstract

Recent advances in protein function prediction exploit graph-based deep learning approaches to correlate the structural and topological features of proteins with their molecular functions. However, proteins in vivo are not static but dynamic molecules that alter conformation for functional purposes. Here we apply normal mode analysis to native protein conformations and augment protein graphs by connecting edges between dynamically correlated residue pairs. In the multilabel function classification task, our method demonstrates a remarkable performance gain based on this dynamics-informed representation. The proposed graph neural network, ProDAR, increases the interpretability and generalizability of residue-level annotations and robustly reflects structural nuance in proteins. We elucidate the importance of dynamic information in graph representation by comparing class activation maps for hMTH1, nitrophorin, and SARS-CoV-2 receptor binding domain. Our model successfully learns the dynamic fingerprints of proteins and pinpoints the residues of functional impacts, with vast untapped potential for broad biotechnology and pharmaceutical applications.