I work on AI-enabled drug design, and on the scientific platforms that make those methods usable.
I am a postdoctoral researcher at the School of Chinese Medicine, Hong Kong Baptist University, working at the intersection of artificial intelligence, drug design, and scientific software. I received my Ph.D. in Computer Science from the National University of Defense Technology, where my work focused on molecular property prediction, molecular generation and optimization, and diffusion-based 3D lead generation and optimization.
My research emphasizes not only model performance, but also practical utility for biomedical discovery. Across publications, platforms, and collaborative research projects, I aim to turn advanced AI methods into usable infrastructure for medicinal chemistry, decision support, and real-world scientific workflows.
Beyond science, I am fascinated by the Yijing (The Book of Changes), an ancient Chinese philosophy that explores the dynamic balance of the universe. I see it as a timeless algorithm, offering insights into interconnectedness — whether decoding molecular structures or interpreting hexagrams, I enjoy uncovering hidden patterns and making sense of complexity.
5,396 citations · h-index 14 · 21 papers · platforms used in 100+ countries
📰News
- Started postdoctoral research at Hong Kong Baptist University
- Successfully defended Ph.D. dissertation
📚Selected publications
All🧬Research
- AI-enabled drug design Molecular property prediction, generative optimization, molecular docking, and large-scale virtual screening.
- Biomedical AI platforms Deployable scientific software and databases for ADMET, drug–drug interaction, and decision support.
- LLM-augmented scientific workflows Language-model agents for drug-discovery pipelines.
🚀Platforms
- DeepCYP End-to-end CYP450 pathway–site–product metabolism prediction.
- ADMETlab 3.0 ADMET prediction platform with API access and decision support.
- DDInter 2.0 Drug–drug, drug–food, and drug–disease interaction resource.
- ChemFH Screening for frequent false positives in chemical biology.
- OptADMET Substructure modification to improve ADMET properties of leads.
- DrugStudio One-stop platform for molecular modeling and scientific workflows; vNext moving to a problem-driven workbench.
- AIDD Brief Bilingual daily briefing on AI-driven drug discovery.
- AIDD Idea Atlas 100 citable research proposals on AI opportunities in drug discovery.