🤖 AI Summary
This work addresses the challenge of modeling local directional relationships among amino acids in protein 3D structure representation. We propose an SO(3)-equivariant graph neural network (GNN) that, for the first time, generalizes GNN edge weights from scalars to 3D vectors—explicitly encoding intra-residue dihedral angles and inter-residue spatial orientations. By integrating SO(3) group representation theory with vector-aware message passing, the model preserves global backbone topology while accurately enforcing geometric orientation constraints. Evaluated on protein structure classification, fold recognition, and binding site prediction, it achieves state-of-the-art performance across all tasks. The architecture significantly enhances sensitivity to and generalization over rotation-equivariant geometric features. This work establishes a novel paradigm for equivariant geometric deep learning in structural biology.
📝 Abstract
By folding into particular 3D structures, proteins play a key role in living beings. To learn meaningful representation from a protein structure for downstream tasks, not only the global backbone topology but the local fine-grained orientational relations between amino acids should also be considered. In this work, we propose the Orientation-Aware Graph Neural Networks (OAGNNs) to better sense the geometric characteristics in protein structure (e.g. inner-residue torsion angles, inter-residue orientations). Extending a single weight from a scalar to a 3D vector, we construct a rich set of geometric-meaningful operations to process both the classical and SO(3) representations of a given structure. To plug our designed perceptron unit into existing Graph Neural Networks, we further introduce an equivariant message passing paradigm, showing superior versatility in maintaining SO(3)-equivariance at the global scale. Experiments have shown that our OAGNNs have a remarkable ability to sense geometric orientational features compared to classical networks. OAGNNs have also achieved state-of-the-art performance on various computational biology applications related to protein 3D structures. The code is available at https://github.com/Ced3-han/OAGNN/tree/main.
