Jingjie Zhang

Jingjie Zhang

Department of Computer Science and Engineering, The Chinese University of Hong Kong

Jingjie Zhang

About Me

I am a Ph.D. candidate at The Chinese University of Hong Kong (CUHK), starting in 2024. My research focuses on Artificial intelligence (AI) for drug design. I am particularly interested in AI for Post-translational modification (PTM). Previously, I completed my undergraduate studies at Shandong University (SDU), where I developed a strong foundation in computer science and bioinformatics.

Education

  • Ph.D. in Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), 2024–2028 (Expected)
  • B.Sc. in College of Software Engineering, Shandong University (SDU), 2020–2024

Research

SAGEPhos: SAGE Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection

Jingjie Zhang, Hanqun Cao, Zijun Gao, Xiaorui Wang, Chunbin Gu

  • Description: SAGEPhos is a structure-aware framework for phosphorylation site prediction that modifies protein inputs using auxiliary modalities at two levels (Bio-Coupled and Bio-Augmented fusion).
  • Note: This paper has been accepted at ICLR 2025.
  • Paper: arxiv
  • Code: GitHub Repository

Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks

Yu Wang, Chao Pang, Yuzhe Wang, Junru Jin, Jingjie Zhang, Xiangxiang Zeng, Ran Su, Quan Zou & Leyi Wei

  • Description: RetroExplainer is a novel deep learning-based approach that formulates retrosynthesis as a molecular assembly process, utilizing a multi-sense graph transformer, structure-aware contrastive learning, and dynamic multi-task learning to achieve state-of-the-art performance across 12 benchmark datasets with enhanced interpretability.
  • Note: This paper has been accepted at Nature Communications.
  • Code: GitHub Repository

MolCAP: Molecular Chemical reActivity Pretraining and prompted-finetuning enhanced molecular representation learning

Yu Wang, Jingjie Zhang, Junru Jin, Leyi Wei

  • Description: MolCAP is a graph-pretraining Transformer leveraging chemical reactivity knowledge and prompted fine-tuning, outperforming traditional molecular pretraining frameworks across 13 biomedical datasets.
  • Note: This paper has been accepted at Computers in Biology and Medicine.
  • Code: GitHub Repository

Honors

  • 🏆 Shandong University President’s Award (山东大学2023年度校长奖) (Dec 2023)
  • 🏅 National Scholarship (Oct 2022, Oct 2021)

Contact