2025年11月4日出版的《细胞》杂志发表了范德比尔特大学Ivelin S. Georgiev团队的最新成果，他们开发出使用大型语言模型生成抗原特异性成对链抗体。

在这项工作中，该课题组提出了MAGE（单克隆抗体生成器），这是一种基于序列的蛋白质语言模型（PLM），用于针对感兴趣的靶标生成成对的人类可变重链和轻链抗体序列。该课题组发现MAGE可以产生新的和多样化的抗体序列，具有实验验证的针对SARS-CoV-2、新兴禽流感H5N1和呼吸道合胞病毒A （RSV-A）的结合特异性。MAGE代表了一种一流的模型，能够在没有起始模板的情况下设计针对多个靶点的人类抗体。

据悉，传统的抗体发现过程受到低效率、高成本和低成功率的限制。最近，利用人工智能（AI）的方法已经被开发出来，以优化现有抗体并以与靶标无关的方式生成抗体序列。

附：英文原文

Title: Generation of antigen-specific paired-chain antibodies using large language models

Author: Perry T. Wasdin, Nicole V. Johnson, Alexis K. Janke, Sofia Held, Toma M. Marinov, Gwen Jordaan, Rebecca A. Gillespie, Léna Vandenabeele, Fani Pantouli, Olivia C. Powers, Matthew J. Vukovich, Clinton M. Holt, Jeongryeol Kim, Grant Hansman, Jennifer Logue, Helen Y. Chu, Sarah F. Andrews, Masaru Kanekiyo, Giuseppe A. Sautto, Ted M. Ross, Daniel J. Sheward, Jason S. McLellan, Alexandra A. Abu-Shmais, Ivelin S. Georgiev

Issue&Volume: 2025-11-04

Abstract: The traditional process of antibody discovery is limited by inefficiency, high costs, and low success rates. Recent approaches employing artificial intelligence (AI) have been developed to optimize existing antibodies and generate antibody sequences in a target-agnostic manner. In this work, we present MAGE (monoclonal antibody generator), a sequence-based protein language model (PLM) fine-tuned for the task of generating paired human variable heavy- and light-chain antibody sequences against targets of interest. We show that MAGE can generate novel and diverse antibody sequences with experimentally validated binding specificity against SARS-CoV-2, an emerging avian influenza H5N1, and respiratory syncytial virus A (RSV-A). MAGE represents a first-in-class model capable of designing human antibodies against multiple targets with no starting template.

DOI: 10.1016/j.cell.2025.10.006

Source: https://www.cell.com/cell/abstract/S0092-8674(25)01135-3