De novo generation of SARS-CoV-2 antibody CDRH3 with a pre-trained generative large language model.

Autor: He H; AI Lab, Tencent, Shenzhen, 518052, China.; Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China., He B; AI Lab, Tencent, Shenzhen, 518052, China. hebinghb@gmail.com., Guan L; State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers and National Clinical Research Center for Digestive Diseases, Xijing Hospital of Digestive Diseases, Xi'an, China., Zhao Y; AI Lab, Tencent, Shenzhen, 518052, China., Jiang F; AI Lab, Tencent, Shenzhen, 518052, China., Chen G; Artificial Intelligence Medical Research Center, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China., Zhu Q; State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers and National Clinical Research Center for Digestive Diseases, Xijing Hospital of Digestive Diseases, Xi'an, China., Chen CY; AI for Science (AI4S)-Preferred Program, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, 518055, China. cy@pku.edu.cn.; State Key Laboratory of Chemical Oncogenomics, School of Chemical Biology and Biotechnology, Peking University Shenzhen Graduate School, Shenzhen, 518055, China. cy@pku.edu.cn.; Department of Medical Research, China Medical University Hospital, Taichung, 40447, Taiwan. cy@pku.edu.cn.; Department of Bioinformatics and Medical Engineering, Asia University, Taichung, 41354, Taiwan. cy@pku.edu.cn.; Guangdong L-Med Biotechnology Co. Ltd, Meizhou, 514699, Guangdong, China. cy@pku.edu.cn., Li T; State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers and National Clinical Research Center for Digestive Diseases, Xijing Hospital of Digestive Diseases, Xi'an, China. romaliting18@163.com., Yao J; AI Lab, Tencent, Shenzhen, 518052, China. jianhua.yao@gmail.com.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2024 Aug 10; Vol. 15 (1), pp. 6867. Date of Electronic Publication: 2024 Aug 10.
DOI: 10.1038/s41467-024-50903-y
Abstrakt: Artificial Intelligence (AI) techniques have made great advances in assisting antibody design. However, antibody design still heavily relies on isolating antigen-specific antibodies from serum, which is a resource-intensive and time-consuming process. To address this issue, we propose a Pre-trained Antibody generative large Language Model (PALM-H3) for the de novo generation of artificial antibodies heavy chain complementarity-determining region 3 (CDRH3) with desired antigen-binding specificity, reducing the reliance on natural antibodies. We also build a high-precision model antigen-antibody binder (A2binder) that pairs antigen epitope sequences with antibody sequences to predict binding specificity and affinity. PALM-H3-generated antibodies exhibit binding ability to SARS-CoV-2 antigens, including the emerging XBB variant, as confirmed through in-silico analysis and in-vitro assays. The in-vitro assays validate that PALM-H3-generated antibodies achieve high binding affinity and potent neutralization capability against spike proteins of SARS-CoV-2 wild-type, Alpha, Delta, and the emerging XBB variant. Meanwhile, A2binder demonstrates exceptional predictive performance on binding specificity for various epitopes and variants. Furthermore, by incorporating the attention mechanism inherent in the Roformer architecture into the PALM-H3 model, we improve its interpretability, providing crucial insights into the fundamental principles of antibody design.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: