Inter-Residue Geometry Attention for Antibody-Specific Epitope Prediction

2026-08-02

AI Summary

Current methods for antibody–antigen epitope prediction struggle to effectively model the three-dimensional spatial complementarity between complementarity-determining regions (CDRs) and antigens. This work proposes Local-Frame 3D Rotary Position Encoding (LF3DRoPE), which constructs local coordinate frames based on the protein backbone to embed inter-residue 3D geometric relationships into rotary position encodings in an SE(3)-invariant manner, integrated within a geometry-aware attention mechanism. Evaluated on the AsEP benchmark, the method achieves state-of-the-art performance in terms of Matthews Correlation Coefficient (MCC). Ablation studies and mutational ranking results further demonstrate its ability to accurately capture structural compatibility between antibodies and antigens.

Abstract

Antibody-specific epitope prediction aims to identify which antigen residues are recognized by a given antibody, a task that depends on the three-dimensional complementarity between antibody CDRs and the antigen surface. Existing methods usually leverage PLM embeddings and inject structure through additional graph, surface, or point-cloud encoders, where the positional mechanism inside attention remains largely tied to one-dimensional sequence order. For proteins, the analogue of a token offset is not only sequence separation, but also the three-dimensional displacement between residues after folding. This raises a question, can folded residue geometry serve as the positional mechanism of attention itself? We propose Local-Frame 3D Rotary Position Encoding (LF3DRoPE), which expresses inter-residue displacements in backbone-defined local frames and injects them directly into rotary attention. This design preserves continuous directional geometry while ensuring invariance to global $\mathrm{SE}(3)$ transformations. On the AsEP benchmark, LF3DRoPE achieves state-of-the-art $\mathrm{MCC}$ on both ratio and epitope-group splits. Ablations and rigid transformation tests show that local three-dimensional geometry provides information beyond sequence-order attention while preserving invariance to arbitrary global coordinate systems. Mutation ranking results further indicate that LF3DRoPE captures antigen-specific structural compatibility.

Problem

• antibody-specific epitope prediction
• inter-residue geometry
• 3D structure
• positional encoding
• protein-protein interaction

Innovation

• 3D rotary position encoding
• antibody-specific epitope prediction
• inter-residue geometry
• SE(3) invariance
• local-frame representation