AntibodyDesignBFN: High-Fidelity Fixed-Backbone Antibody Design via Discrete Bayesian Flow Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hu, Yue, Tao, Feng, Wang, Junqing, Liu, YingChao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915811769188352
author Hu, Yue
Tao, Feng
Wang, Junqing
Liu, YingChao
author_facet Hu, Yue
Tao, Feng
Wang, Junqing
Liu, YingChao
contents The computational design of antibodies with high specificity and affinity is a cornerstone of modern therapeutic development. While deep generative models have demonstrated potential, they often struggle to balance high-fidelity geometric conditioning with the discrete nature of amino acid sequences. In this work, we present AntibodyDesignBFN, a novel framework for fixed-backbone antibody design based on Discrete Bayesian Flow Networks (BFN). Unlike standard diffusion models, BFNs operate on a continuous probability simplex, enabling a fully differentiable generative process that seamlessly integrates geometric gradients. By combining a lightweight Geometric Transformer with Invariant Point Attention (IPA) and a resource-efficient training strategy, our model establishes a new state-of-the-art. Evaluations on a rigorous 2025 temporal test set (43 complexes) demonstrate that AntibodyDesignBFN achieves an unprecedented Amino Acid Recovery(AAR) of 67.8%, significantly outperforming leading graph-based baselines. Furthermore, the model is highly efficient, enabling millisecond-scale inference on consumer-grade hardware. AntibodyDesignBFN thus offers a powerful, accessible, and mathematically robust framework for next generation antibody engineering. Code and model checkpoints are available at https://github.com/YueHuLab/AntibodyDesignBFN and https://huggingface.co/YueHuLab/AntibodyDesignBFN.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05605
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AntibodyDesignBFN: High-Fidelity Fixed-Backbone Antibody Design via Discrete Bayesian Flow Networks
Hu, Yue
Tao, Feng
Wang, Junqing
Liu, YingChao
Quantitative Methods
92C40, 68T07, 62F15
The computational design of antibodies with high specificity and affinity is a cornerstone of modern therapeutic development. While deep generative models have demonstrated potential, they often struggle to balance high-fidelity geometric conditioning with the discrete nature of amino acid sequences. In this work, we present AntibodyDesignBFN, a novel framework for fixed-backbone antibody design based on Discrete Bayesian Flow Networks (BFN). Unlike standard diffusion models, BFNs operate on a continuous probability simplex, enabling a fully differentiable generative process that seamlessly integrates geometric gradients. By combining a lightweight Geometric Transformer with Invariant Point Attention (IPA) and a resource-efficient training strategy, our model establishes a new state-of-the-art. Evaluations on a rigorous 2025 temporal test set (43 complexes) demonstrate that AntibodyDesignBFN achieves an unprecedented Amino Acid Recovery(AAR) of 67.8%, significantly outperforming leading graph-based baselines. Furthermore, the model is highly efficient, enabling millisecond-scale inference on consumer-grade hardware. AntibodyDesignBFN thus offers a powerful, accessible, and mathematically robust framework for next generation antibody engineering. Code and model checkpoints are available at https://github.com/YueHuLab/AntibodyDesignBFN and https://huggingface.co/YueHuLab/AntibodyDesignBFN.
title AntibodyDesignBFN: High-Fidelity Fixed-Backbone Antibody Design via Discrete Bayesian Flow Networks
topic Quantitative Methods
92C40, 68T07, 62F15
url https://arxiv.org/abs/2601.05605