AbFlow : End-to-end Paratope-Centric Antibody Design by Interaction Enhanced Flow Matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914311757103104 |
|---|---|
| author | Wang, Wenda Zhang, Yang Wei, Zhewei Huang, Wenbing |
| author_facet | Wang, Wenda Zhang, Yang Wei, Zhewei Huang, Wenbing |
| contents | Antigen-antibody binding is a critical process in the immune response. Although recent progress has advanced antibody design, current methods lack a generative framework for end-to-end modeling of full-atom antibody structures and struggle to fully exploit antigen-specific geometric information for optimizing local binding interfaces and global structures. To overcome these limitations, we introduce AbFlow, a flow-matching framework that leverages optimal transport to design full-atom antibodies end-to-end. AbFlow incorporates an extended velocity field network featuring an equivariant Surface Multi-channel Encoder, which uses surface-level antigen interaction data to refine the antibody structure, particularly the CDR-H3 region. Extensive experiments in paratoep-centric antibody design, multi-CDRs and full-atom antibody design, binding affinity optimization, and complex structure prediction show that AbFlow produces superior antigen-antibody complexes, especially at the contact interface, and markedly improves the binding affinity of generated antibodies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AbFlow : End-to-end Paratope-Centric Antibody Design by Interaction Enhanced Flow Matching Wang, Wenda Zhang, Yang Wei, Zhewei Huang, Wenbing Quantitative Methods Artificial Intelligence Computational Engineering, Finance, and Science Antigen-antibody binding is a critical process in the immune response. Although recent progress has advanced antibody design, current methods lack a generative framework for end-to-end modeling of full-atom antibody structures and struggle to fully exploit antigen-specific geometric information for optimizing local binding interfaces and global structures. To overcome these limitations, we introduce AbFlow, a flow-matching framework that leverages optimal transport to design full-atom antibodies end-to-end. AbFlow incorporates an extended velocity field network featuring an equivariant Surface Multi-channel Encoder, which uses surface-level antigen interaction data to refine the antibody structure, particularly the CDR-H3 region. Extensive experiments in paratoep-centric antibody design, multi-CDRs and full-atom antibody design, binding affinity optimization, and complex structure prediction show that AbFlow produces superior antigen-antibody complexes, especially at the contact interface, and markedly improves the binding affinity of generated antibodies. |
| title | AbFlow : End-to-end Paratope-Centric Antibody Design by Interaction Enhanced Flow Matching |
| topic | Quantitative Methods Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2602.07084 |