De Novo Design of Antigen-Specific Antibodies Using Structural Constraint-Based Generative Language Model
Abstract
Despite significant advances in computational antibody design, the limited availability of high-quality binding data continues to constrain the exploration of diverse antibody syntax and uncharted evolutionary landscapes. To overcome these challenges, we developed PALM-PA (Pre-trained Antibody Generative Large Language Model–Preference Alignment), which integrates antibody linguistic patterns with structural constraints to explore novel sequence spaces. Experimental validation on influenza A hemagglutinin and programmed death-ligand 1 (PD-L1) demonstrated nanomolar binding affinities (30.2 nM and 1.29 nM, respectively), underscoring the feasibility of using structure-guided language models for the de novo design of antibodies.
Cite
Text
Jia et al. "De Novo Design of Antigen-Specific Antibodies Using Structural Constraint-Based Generative Language Model." ICLR 2025 Workshops: GEM, 2025.Markdown
[Jia et al. "De Novo Design of Antigen-Specific Antibodies Using Structural Constraint-Based Generative Language Model." ICLR 2025 Workshops: GEM, 2025.](https://mlanthology.org/iclrw/2025/jia2025iclrw-de/)BibTeX
@inproceedings{jia2025iclrw-de,
title = {{De Novo Design of Antigen-Specific Antibodies Using Structural Constraint-Based Generative Language Model}},
author = {Jia, Yuran and He, Bing and Lv, Tianxu and YangXiao, and Zhao, Tianyi and Yao, Jianhua},
booktitle = {ICLR 2025 Workshops: GEM},
year = {2025},
url = {https://mlanthology.org/iclrw/2025/jia2025iclrw-de/}
}