Skip to main contentSkip to article

• View PDF

Cell

Available online 4 November 2025

Under a Creative Commons license

Open access

Highlights

• •

A protein language model was fine-tuned for antigen-specific antibody generation

• •

Antibody-antigen sequence database was constructed using public databases and LIBRA-seq

• •

Antibody design was experimentally validated against RSV-A, SARS-CoV-2, and H5N1

• •

Generated antibodies showed diverse binding specificities, neutralization, and epitopes

Summary

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.

Keywords

antibody design

language modeling

monoclonal antibody

viruses

biologics

machine learning

artificial intelligence

© 2025 The Authors. Published by Elsevier Inc.