IgCraft: A versatile sequence generation framework for antibody discovery and engineering

2025-03-25

AI Summary

Antibody sequence design must simultaneously satisfy human-likeness and structural–functional constraints, yet existing methods lack unified support for multi-task generation. This paper introduces the first unified antibody generation framework based on Bayesian Flow Networks (BFNs), enabling integrated modeling of unconditional sampling, sequence inpainting, inverse folding, and CDR motif grafting. Notably, it is the first method to support joint generation of paired heavy and light chains under antibody-specific constraints. In CDR grafting, our approach achieves state-of-the-art performance, improving humanness scores by +12.3% and reducing backbone RMSD by 0.48 Å—demonstrating enhanced structural compatibility and naturalness. All model code and pre-trained weights are publicly released.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Diffusion Models for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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 github.com/mgreenig/IgCraft.

Problem

• Designing human-like antibody sequences for biologics development
• Unifying multiple antibody design tasks with one generative model
• Improving CDR motif scaffolding for humanness and structural integrity

Innovation

• Bayesian Flow Networks for antibody generation
• Unified model for multiple design tasks
• State-of-the-art CDR motif scaffolding