Abstract:Computational antibody CDR design methods condition on antigen structure to generate binding loops, yet existing architectures conflate two fundamentally distinct sub-problems: identifying which CDR positions will contact the antigen, and selecting amino acids at those positions. This conflation forces models to learn contact reasoning implicitly through uniform message passing, diluting antigen signal across all positions equally. We introduce ConTact, a contact-then-act architecture that explicitly decomposes CDR design into three cascaded stages: learning surface complementarity fingerprints, predicting CDR-antigen contacts, and injecting contact-gated antigen features into the sequence head. A distance-biased cross-attention module encodes geometric priors favoring spatial neighbors, while a contact-weighted cross-entropy loss concentrates gradient signal on binding-critical positions. On CHIMERA-Bench dataset, ConTact achieves the best structural quality (7% RMSD improvement over the next-best baseline), best epitope awareness (10% F1 score over GNN baselines), and competitive sequence recovery (AAR 0.38) among several CDR-H3 design baselines.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.21600 [cs.LG] |
| (or arXiv:2605.21600v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21600 arXiv-issued DOI via DataCite |
From: Mansoor Ahmed [view email]
[v1]
Wed, 20 May 2026 18:04:32 UTC (77 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。