Robust Conditional Diffusion with Noisy Templates for Antibody Sequence–Structure Design
Preprint
Abstract
Antibodies specifically recognize antigens and play a central role in therapeutic discovery. Designing antibodies for a given antigen remains challenging because antigen–antibody complex data are limited, whereas the sequence and conformational spaces of complementarity-determining regions (CDRs) are large. Retrieved CDR templates from databases or candidate libraries can narrow the design space and improve controllability, but retrieval for novel antigens is often sparse and imperfect; treating retrieved templates as hard conditions can bias the denoising process and cause negative transfer. To address this problem, we propose Robust Conditional Diffusion with Noisy Templates for antibody sequence–structure design (NT-ABDiff), a joint diffusion framework that treats candidate CDR-only templates as optional and potentially unreliable conditions. NT-ABDiff uses reliability-aware template modulation to estimate the context-conditioned usefulness of each candidate and to adaptively reweight and fuse multiple templates during conditioning. We further train the model with mixed-quality and corrupted templates as conditional perturbation regularization, encouraging the denoiser to exploit informative templates while remaining stable when templates are uninformative. Experiments under controlled template shifts and a train-set retrieval evaluation show that NT-ABDiff improves CDR-H3 sequence recovery and structural accuracy over strong baselines, while retaining robustness to missing, mismatched, and corrupted templates. Under a stringent random-template CDR-H3 evaluation, NT-ABDiff improves amino-acid recovery (AAR) from 30.03% to 39.47% and reduces RMSD from 3.160 to 2.915 Å; with train-set retrieval candidates, it achieves 39.50% AAR and 2.76 Å RMSD. Code, processed splits, configuration files, and evaluation scripts are available at https://github.com/ShiDeng7rz/NT-ABDiff .Keywords
This publication has 25 references indexed in Scilit:
- A comprehensive overview of recent advances in generative models for antibodiesComputational and Structural Biotechnology Journal, 2024
- Computational and artificial intelligence-based methods for antibody developmentTrends in Pharmacological Sciences, 2023
- Deciphering the language of antibodies using self-supervised learningPatterns, 2022
- Antibody structure prediction using interpretable deep learningPatterns, 2021
- A compact vocabulary of paratope-epitope interactions enables predictability of antibody-antigen bindingCell Reports, 2021
- The H3 loop of antibodies shows unique structural characteristicsProteins: Structure, Function, and Bioinformatics, 2017
- AbDesign: An algorithm for combinatorial backbone design guided by natural conformations and sequencesProteins: Structure, Function, and Bioinformatics, 2015
- The Origin of CDR H3 Structural DiversityStructure, 2015
- Structure and function of immunoglobulinsJournal of Allergy and Clinical Immunology, 2010
- Canonical structures for the hypervariable regions of immunoglobulinsJournal of Molecular Biology, 1987