Geometric Epitope and Paratope Prediction

TL;DR

This paper explores the use of geometric deep learning methods to improve the prediction of antibody-antigen binding sites, emphasizing the importance of 3D structural information and surface-based models for enhanced accuracy.

Contribution

It introduces a novel comparison of geometric deep learning approaches for epitope and paratope prediction, demonstrating the superiority of surface-based models and achieving state-of-the-art results.

Findings

Surface-based models outperform other methods

Incorporating 3D coordinates improves prediction accuracy

O-GEP achieves state-of-the-art performance

Abstract

Antibody-antigen interactions play a crucial role in identifying and neutralizing harmful foreign molecules. In this paper, we investigate the optimal representation for predicting the binding sites in the two molecules and emphasize the importance of geometric information. Specifically, we compare different geometric deep learning methods applied to proteins' inner (I-GEP) and outer (O-GEP) structures. We incorporate 3D coordinates and spectral geometric descriptors as input features to fully leverage the geometric information. Our research suggests that surface-based models are more efficient than other methods, and our O-GEP experiments have achieved state-of-the-art results with significant performance improvements.