We've developed a promising new tool that could make oral cancer surgery more precise. Our team created a specialized fluorescent dye called LP-S that lights up metastatic lymph nodes, making them easier for surgeons to identify and remove.
Right now, surgeons rely on a standard dye called ICG, but it's not very specific - it highlights everything, making it hard to tell which lymph nodes actually contain cancer cells. Our new dye is much more precise,  specifically binding to EGFR receptors, which are found in high concentrations on oral cancer cells.

When we tested LP-S in mouse models, the results were impressive. The dye produced clearer, longer-lasting fluorescence in cancerous lymph nodes compared to ICG, giving surgeons a much better view of what they're working with. This means they can more accurately remove the correct lymph nodes while leaving healthy tissue in place.

If this technology makes it through clinical testing, it could be a game-changer for oral cancer patients. Better lymph node mapping means more accurate cancer staging and ultimately better treatment outcomes.

                   

We've been working with our colleagues at IceKredit on an exciting project for the  First Global AI Drug Design Competition sponsored by Baidu and Tsinghua University to help identify potential COVID-19 treatments. Using advanced machine learning, we developed a model that can predict whether new compounds might be effective against SARS-CoV-2.

What makes our approach special is that it looks at molecules from multiple angles - both the fine details of their structure and their broader chemical fingerprints. This multi-scale view helps us make more accurate predictions about which compounds are worth testing in the lab.
This work builds on our recent publication in the Journal of Computer-Aided Molecular Design and shows how our computational methods can be applied to tackle urgent health challenges like the pandemic.

We've published new research in the Journal of Computer-Aided Molecular Design that could speed up the hunt for new medicines. Our team developed a hybrid AI model that's better at designing potential drug molecules than traditional computational methods.
Here's how it works: we combined two powerful AI approaches - one that generates new molecular structures and another that predicts how well those molecules will bind to their target protein. By linking these together with reinforcement learning, our system can efficiently explore vast chemical possibilities and focus on the most promising candidates.
When we tested this approach on DDR1 kinase (a protein involved in cancer), the results were impressive. Our hybrid model found molecules with much higher binding scores than conventional similarity-based methods. Even better, it discovered chemically diverse compounds that looked quite different from known inhibitors but still bound effectively to the target.
What makes this especially exciting is that our approach reduces one of the biggest limitations in AI drug discovery - the need for massive datasets. Instead of just making slight tweaks to existing drugs, our system can venture into unexplored chemical territory to find genuinely novel compounds.
While there's still more work ahead, this hybrid strategy could help researchers identify promising new treatments for diseases where current drugs aren't working well enough.

I'm excited to share that our collaborative work with Professor Hui Wei's team at NJU-BME has been recognized with the RSC Horizons Dalton Prize. This interdisciplinary project focused on advancing our understanding of nanozymes and their potential applications.
Nanozymes are artificial nanomaterials that can act like natural enzymes - they catalyze reactions just like the biological enzymes in our bodies, but they're engineered rather than evolved. The potential applications are pretty exciting: these synthetic catalysts could be used to treat cancer and inflammation, and they're even being explored for wearable medical devices.
Our research demonstrated that these designed nanozymes actually outperform natural enzymes in several key areas. The work also provided new insights into what factors control how effectively these artificial catalysts work - knowledge that will be crucial for designing even better nanozymes in the future.
This recognition highlights both the innovative science and the successful international collaboration that made this research possible. It's a great example of how interdisciplinary partnerships can lead to breakthroughs with real-world biomedical applications.