pipette
ESEspañol

Multiproperty optimization of therapeutic antibodies through sequence editing via large language model and reinforcement learning

Minyao Qiu, Zhiwei Wang, Xuan Liu, Hongzhun Wang, 华权高, Qin Shu, Shaoxiang Luo, Mengxi Niu, Feng Ma, Feng F. Huang, Yongkang Wang, Zhankun Xiong, Wen Zhang

Peer-reviewed journalReal-world use

In the authors' words

Discovering antibodies with multiple beneficial properties is essential for therapeutic drug development, but experimentally identified antibodies require further optimization. Joint optimization remains challenging because sequence space is vast, annotations are sparse and property tradeoffs are common. Herein, we propose AbOptimizer, a reinforcement learning framework for multiproperty antibody optimization through parallel multisite sequence editing. AbOptimizer identifies promising editing sites and edit actions, including ‘reservation’, ‘substitution’ and optional ‘insertion’ or ‘deletion’, before recommending mutations from protein language models, while surrogate evaluation and Pareto rewards shape policy training. We evaluate AbOptimizer on three therapeutic antibodies across multiproperty, data-limited and indel-inclusive optimization. In silico, AbOptimizer improves optimized properties and outperforms baseline methods. In vitro, selected variants show affinity-specificity co-optimization for emibetuzumab, improved affinity and specificity with largely maintained thermal stability for siltuximab, and indel-inclusive affinity optimization for trastuzumab. These results validate AbOptimizer as a practical framework for therapeutic antibody optimization. This study presents AbOptimizer, a computational framework that edits antibody sequences to improve multiple therapeutic properties. Tests on three antibodies show improved affinity, specificity and stability-related profiles.

Main resultThe abstract does not state a limitation.

Appeared: Wednesday, October 28. Nature Communications. Peer-reviewed journal.

DOI: 10.1038/s41467-026-78533-6