Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Xiaoliang Shi, Zichen Wang, Runze Ma, Zhongyue Zhang, Shuangjia Zheng
• Venue: arXiv: q-bio.BM
• Published: 2026-07-22
• Collected: 2026-07-23
• URL: http://arxiv.org/abs/2607.20057v1
• PDF: https://arxiv.org/pdf/2607.20057v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers have developed a new model called AAMFM to improve the design of functional antibodies. This model learns unified representations of antibody sequences and structures, considering antigen context, which helps in understanding the interactions between antibodies and antigens. The researchers used a method called Cal-DPO for fine-tuning the model, aiming for functional relevance. Experiments showed that AAMFM outperforms existing methods for designing functional antibodies.

What the Document Says

• The study introduces AAMFM, an Antigen-specific Antibody Multimodal Foundation Model for functional antibody design.
• AAMFM learns unified representations of antibody sequences and structures conditioned on antigen context.
• Rich antigen information including geometric interfaces and epitope annotations are incorporated via a cross-modal adapter.
• Joint modeling of antibody-antigen interactions is enabled in a shared latent space.
• Calibrated Direct Preference Optimization (Cal-DPO) is used for fine-tuning AAMFM to align learning with binding-specific objectives.
• Experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design.

Key Concepts Mentioned

• Antibodies
• Antigen
• Epitope
• Latent space
• Calibrated Direct Preference Optimization (Cal-DPO)
• Functional antibody design

Claims Made by the Document

• AAMFM achieves state-of-the-art performance in functional antibody design.

Evidence Used

• Extensive experiments demonstrate that AAMFM achieves state-of-the-art performance in functional antibody design.

Methods / Approach

• AAMFM
• Cross-modal adapter
• Calibrated Direct Preference Optimization (Cal-DPO)

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The model's performance may be limited by the quality and quantity of data used for training and testing.

Open Questions

• What are the potential applications of AAMFM in antigen-specific antibody engineering?
• How does the model perform when dealing with complex or unusual antigens?

Notes for Future Q&A

May include interpretation. Labeled where it does.

It would be beneficial to consider the potential practical implications of this research for medicine and biotechnology.

Raw Abstract / Excerpt

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.