AI-Driven Drug Discovery and Precision Medicine Laboratory

Research

AI Agents for Drug Discovery

Medea paper: AI agent workflow for therapeutic discovery

We build AI agents that connect molecular design, property prediction, synthesis planning, and experimental feedback to accelerate lead discovery and validation.

Molecular AI & Chemistry

MolMap paper: molecular representation maps from descriptors and fingerprints

We develop AI models for reaction prediction, condition optimization, and retrosynthesis, combining large-scale chemical data with experimental validation to guide drug synthesis.

Multi-Omics & Precision Medicine

COMPASS paper: biological concepts and immunotherapy response prediction

We integrate multi-omics and clinical data to discover therapeutic targets and predict immunotherapy response, advancing precision diagnosis and treatment through clinical validation.

What We Work On

We combine AI, computational chemistry, and biomedical science to advance drug discovery, from molecular property prediction to lead optimization. With tools such as MolMap and Leadmaster, we develop AI agents and foundation models that connect molecular design, synthesis planning, and experimental feedback.

For precision oncology, we integrate multi-omics data to understand tumor heterogeneity and identify therapeutic targets, using approaches such as AggMap. Our COMPASS model predicts immunotherapy response across cancer types, with multi-center validation supporting its clinical translation.

News

  • COMPASS and ACANet accepted by Nature Medicine and Nature Communications, respectively.
  • FPPool, a knowledge-guided pooling framework connecting molecular fingerprints and graph neural networks, is on ChemRxiv.
  • Medea, an omics AI agent for automated therapeutic discovery, is posted on bioRxiv.
  • Dr. Shen joins Zhejiang University as Assistant Professor under the Hundred Talents Program.
All News →

Recent Publications

01 / 06
All Publications →