MP-GCAN: a highly accurate classifier for $\alpha$-helical membrane proteins and $\beta$-barrel proteins

TL;DR

This paper introduces MP-GCAN, a graph neural network model that accurately classifies membrane proteins using 3D structural data, outperforming existing sequence-based and structure-confidence methods.

Contribution

The study presents a novel GNN-based classifier that integrates hierarchical structural features from 3D protein graphs, achieving high accuracy in membrane protein classification.

Findings

MP-GCAN achieves 96% accuracy in classification.

It significantly outperforms sequence-based models.

Structural features improve classification performance.

Abstract

Membrane protein classification is a fundamental task in structural bioinformatics, critical to understanding protein functions and accelerating drug discovery. In this study, we propose MP-GCAN, a novel graph-based classification model that leverages both spatial and sequential features of proteins. MP-GCAN combines GCN, GAT, and GIN layers to capture hierarchical structural representations from 3D protein graphs, constructed from high-resolution PDB files with $\alpha$-carbon coordinates and residue types. To evaluate performance, we curated a high-quality dataset of 500 membrane and 500 non-membrane proteins, and compared MP-GCAN with two baselines: a structure-confidence-based SGD classifier utilizing AlphaFold's pLDDT scores, and DeepTMHMM, a sequence-based deep learning model. Our experiments demonstrate that MP-GCAN significantly outperforms baselines, achieving an accuracy of 96% and strong F1-scores on both classes. The results highlight the importance of integrating pretrained GNN architectures with domain-specific structural data to enhance membrane protein classification.