IgCraft: A versatile sequence generation framework for antibody discovery and engineering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916690472730624 |
|---|---|
| author | Greenig, Matthew Zhao, Haowen Radenkovic, Vladimir Ramon, Aubin Sormanni, Pietro |
| author_facet | Greenig, Matthew Zhao, Haowen Radenkovic, Vladimir Ramon, Aubin Sormanni, Pietro |
| contents | Designing antibody sequences to better resemble those observed in natural human repertoires is a key challenge in biologics development. We introduce IgCraft: a multi-purpose model for paired human antibody sequence generation, built on Bayesian Flow Networks. IgCraft presents one of the first unified generative modeling frameworks capable of addressing multiple antibody sequence design tasks with a single model, including unconditional sampling, sequence inpainting, inverse folding, and CDR motif scaffolding. Our approach achieves competitive results across the full spectrum of these tasks while constraining generation to the space of human antibody sequences, exhibiting particular strengths in CDR motif scaffolding (grafting) where we achieve state-of-the-art performance in terms of humanness and preservation of structural properties. By integrating previously separate tasks into a single scalable generative model, IgCraft provides a versatile platform for sampling human antibody sequences under a variety of contexts relevant to antibody discovery and engineering. Model code and weights are publicly available at https://github.com/mgreenig/IgCraft. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19821 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IgCraft: A versatile sequence generation framework for antibody discovery and engineering Greenig, Matthew Zhao, Haowen Radenkovic, Vladimir Ramon, Aubin Sormanni, Pietro Biomolecules Machine Learning Quantitative Methods Designing antibody sequences to better resemble those observed in natural human repertoires is a key challenge in biologics development. We introduce IgCraft: a multi-purpose model for paired human antibody sequence generation, built on Bayesian Flow Networks. IgCraft presents one of the first unified generative modeling frameworks capable of addressing multiple antibody sequence design tasks with a single model, including unconditional sampling, sequence inpainting, inverse folding, and CDR motif scaffolding. Our approach achieves competitive results across the full spectrum of these tasks while constraining generation to the space of human antibody sequences, exhibiting particular strengths in CDR motif scaffolding (grafting) where we achieve state-of-the-art performance in terms of humanness and preservation of structural properties. By integrating previously separate tasks into a single scalable generative model, IgCraft provides a versatile platform for sampling human antibody sequences under a variety of contexts relevant to antibody discovery and engineering. Model code and weights are publicly available at https://github.com/mgreenig/IgCraft. |
| title | IgCraft: A versatile sequence generation framework for antibody discovery and engineering |
| topic | Biomolecules Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2503.19821 |