Posts by Collection

portfolio

publications

UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge

Published in NeurIPS 2025, 2025

We introduce UniZyme, a unified protein cleavage site predictor that generalizes across diverse enzymes using a biochemically-informed model architecture with active-site knowledge of proteolytic enzymes.

Recommended citation: Chenao Li, Shuo Yan, Enyan Dai. (2025). "UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge." NeurIPS 2025.

Protap: General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications

Published in arXiv, 2025

Protap is a comprehensive benchmark comparing backbone architectures, pretraining strategies, and domain-specific models across diverse realistic downstream protein applications.

Recommended citation: Shuo Yan, Yuliang Yan, Bin Ma, Chenao Li, Haochun Tang, Jiahua Lu, Minhua Lin, Yuyuan Feng, Enyan Dai. (2025). "Protap: Benchmarking Protein Modeling on Realistic Applications." arXiv:2506.02052.

FlexRibbon: Joint Sequence and Structure Pretraining for Protein Modeling

Published in ICLR 2026, 2025

FlexRibbon is a pretrained protein model that jointly learns from amino acid sequences and 3D structures, achieving SOTA on 12 different tasks.

Recommended citation: Jianwei Zhu, Yu Shi, ..., Chenao Li, ..., Tao Qin. (2025). "FlexRibbon: Joint Sequence and Structure Pretraining for Protein Modeling." ICLR 2026.

TCRAD: An End-to-End Framework for Antigen-Targeted T Cell Receptor Design

Published in bioRxiv(Under review in Briefings in Bioinformatics), 2026

TCRAD is an end-to-end deep learning framework for de novo design of antigen-specific TCR CDR3β sequences, with experimental validation showing 17.2% of designed TCRs elicited antigen-induced activation.

Recommended citation: Chenao Li, Yaochi Guo, Xin Guan, Hui Chen, Yong Zhang, Pengyuan Yang, Jizhong Lou. (2026). "TCRAD: An End-to-End Framework for Antigen-Targeted T Cell Receptor Design." bioRxiv.

Chenao Li