Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.19395 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916632095358976 |
|---|---|
| author | Zhang, Xingyi Xie, Kun Huang, Ningqiao Liu, Wei Zhao, Peilin Wang, Sibo Zhao, Kangfei Jiang, Biaobin |
| author_facet | Zhang, Xingyi Xie, Kun Huang, Ningqiao Liu, Wei Zhao, Peilin Wang, Sibo Zhao, Kangfei Jiang, Biaobin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19395 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fast and Accurate Antibody Sequence Design via Structure Retrieval Zhang, Xingyi Xie, Kun Huang, Ningqiao Liu, Wei Zhao, Peilin Wang, Sibo Zhao, Kangfei Jiang, Biaobin Biomolecules Machine Learning 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. |
| title | Fast and Accurate Antibody Sequence Design via Structure Retrieval |
| topic | Biomolecules Machine Learning |
| url | https://arxiv.org/abs/2502.19395 |