基于抗原信息的抗体生成模型，可精准设计靶向特定抗原的抗体。
Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design
- 融合抗体与抗原结构信息，通过跨模态适配器建模结合界面。
- 在多个数据集上实现当前最优功能抗体设计性能。
- 适合抗体药物研发人员，尤其关注抗原特异性设计场景。
抗体是免疫识别中关键的蛋白质，通过结合特定抗原分子发挥作用。尽管近期蛋白质语言模型在单链蛋白建模与生成方面取得进展，但在抗原特异性抗体设计中仍存在不足，因有效建模需显式捕捉抗体与抗原间的配对关系，尤其是在表位层面。为此，我们提出AAMFM——一种抗原特异性的抗体多模态基础模型，学习在抗原上下文条件下统一表示抗体序列与结构。AAMFM通过交叉模态适配器引入丰富的抗原信息，包括几何界面和表位注释，实现在共享潜在空间中联合建模抗体-抗原相互作用。为进一步引导模型向功能性目标对齐，我们采用校准直接偏好优化（Cal-DPO）进行微调，利用强结构先验提取的偏好信号。大量实验表明，AAMFM在功能抗体设计任务中达到当前最优表现，展现出抗原特异性抗体工程的巨大潜力。代码已开源：https://github.com/XL-S224/AAMFM。
原文摘要 · Abstract (English)
Antibodies are essential proteins that play a central role in immune recognition by binding specific antigen molecules. Although recent protein language models have enabled progress in single-chain protein modeling and generation, they often fall short in antigen-specific antibody design, where effective modeling requires explicit pairing between antibody and antigen, particularly at the epitope level. To address these limitations, we introduce AAMFM, an Antigen-specific Antibody Multimodal Foundation Model that learns unified representations of antibody sequences and structures conditioned on antigen context. AAMFM incorporates rich antigen information including geometric interfaces and epitope annotations via a cross-modal adapter, enabling joint modeling of antibody-antigen interactions in a shared latent space. To further guide the model toward functional relevance, we fine-tune AAMFM using Calibrated Direct Preference Optimization (Cal-DPO), leveraging preference signals extracted from a strong structural prior to align learning with binding-specific objectives. Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design, revealing its potential for antigen-specific antibody engineering. Our code is available at https://github.com/XL-S224/AAMFM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。