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.
Released AIDD Brief (brief.minddanceai.com), a bilingual (EN/ZH) daily briefing site covering AI-driven drug discovery, with automated paper fetching, LLM-powered scoring, and curated digests.
Visit →Joined the School of Chinese Medicine, Hong Kong Baptist University, as a postdoctoral researcher.
Defended the dissertation "Research on Key Technologies for Deep Learning-based Small Molecule Drug Design" at the National University of Defense Technology.
Presented at the CAST Young Scientific Talent Pilot Program in Hunan and exchanged ideas with fellow early-career researchers.
News →Co-first authored paper published in Chemical Science (RSC), systematically decoding the boundaries and failure modes of deep learning-based molecular docking.
Paper →Selected for the inaugural doctoral-student track of the CAST Youth Talent Support Program.
ADMETlab 3.0 is the second updated version of the web server that provides a comprehensive and efficient platform for evaluating ADMET-related parameters as well as physicochemical properties and medicinal chemistry…
Lead optimization is a crucial step in drug discovery, aiming to design potential drug candidates from biologically active hits. During lead optimization, active hits undergo modifications to achieve a balance between…
Structure-based molecular docking, a cornerstone of computational drug design, is undergoing a paradigm shift fueled by deep learning (DL) innovations. However, the rapid proliferation of DL-driven docking methods…
Molecular property prediction, generative optimization, molecular docking, and large-scale virtual screening.
Deployable, one-stop scientific platforms for biomedicine and decision support.
Large language model agents for drug-discovery workflows.
10+ open-source platforms · 5.5M+ visits from 100+ countries · 5 software copyrights
A one-stop intelligent drug design platform for molecular modeling and scientific workflows.
WeChat official account sharing research notes, ideas, and updates on AI for drug discovery.
Scan to follow on WeChat