analiza aiqbench
This research introduces LF3DRoPE, a novel attention mechanism that integrates three-dimensional residue geometry directly into rotary position encoding for protein modeling. By treating spatial displacement as the primary positional signal rather than relying on sequence order alone, the method achieves state-of-the-art performance in predicting antibody-specific epitopes while maintaining SE(3) transformation invariance. This advancement demonstrates how incorporating explicit 3D structural priors can significantly enhance the accuracy of biological AI models beyond standard linear attention mechanisms.
Inter-Residue Geometry Attention for Antibody-Specific Epitope Prediction
arXiv:2608.01092v1 Announce Type: new 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.
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.
Artificial Intelligence (cs.AI)
arXiv:2608.01092 [cs.AI]
(or arXiv:2608.01092v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.01092 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 275 cuvinte
Subiecte conexe
EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
arXiv · 5 iun. 2026
How to build a cancer vaccine, and whether they will work this time
LessWrong · 8 iun. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
Attention Mean Fields Predict Average Representation Dynamics and Reveal Context-Specific Computation
arXiv · 16 sept. 2026