Fast and Accurate Antibody Sequence Design via Structure Retrieval

TL;DR

Igseek introduces a structure-retrieval method using graph neural networks to improve antibody CDR sequence inference, outperforming existing inverse folding techniques in accuracy and efficiency.

Contribution

This paper presents Igseek, a novel retrieval-based framework that leverages structural similarity and sequence motifs for antibody CDR design, addressing limitations of traditional inverse folding methods.

Findings

Igseek outperforms state-of-the-art methods in sequence recovery.

Igseek is highly efficient in structural retrieval.

Effective for both antibody and T-Cell Receptor design.

Abstract

Recent advancements in protein design have leveraged diffusion models to generate structural scaffolds, followed by a process known as protein inverse folding, which involves sequence inference on these scaffolds. However, these methodologies face significant challenges when applied to hyper-variable structures such as antibody Complementarity-Determining Regions (CDRs), where sequence inference frequently results in non-functional sequences due to hallucinations. Distinguished from prevailing protein inverse folding approaches, this paper introduces Igseek, a novel structure-retrieval framework that infers CDR sequences by retrieving similar structures from a natural antibody database. Specifically, Igseek employs a simple yet effective multi-channel equivariant graph neural network to generate high-quality geometric representations of CDR backbone structures. Subsequently, it aligns sequences of structurally similar CDRs and utilizes structurally conserved sequence motifs to enhance inference accuracy. Our experiments demonstrate that Igseek not only proves to be highly efficient in structural retrieval but also outperforms state-of-the-art approaches in sequence recovery for both antibodies and T-Cell Receptors, offering a new retrieval-based perspective for therapeutic protein design.