We've published work in Advanced Functional Materials on heparin-folate nanoparticles (HF NPs) as a way to unlock heparin's anticancer potential without the bleeding risk that has always prevented clinical use. Heparin is best known as an anticoagulant, but it also has real immunomodulatory and anti-angiogenic activity through neutrophil activation, complement regulation, and VEGF neutralization. The problem has been that the doses needed to exploit those effects would cause dangerous bleeding, and chemically chopping heparin into low-molecular-weight forms only partly solves it.

We've published work in Bioorganic Chemistry applying our AI drug-design pipeline to a very different target, herbicide discovery. The molecule here is 4-hydroxyphenylpyruvate dioxygenase (HPPD), one of the few commercially successful modern herbicide targets, and the goal was to generate genuinely new inhibitor scaffolds rather than variations on the existing triketone chemistry. Data is what makes this hard. Generative AI models are usually trained on large pharmaceutical datasets, but specialized enzyme targets like HPPD have far fewer known active compounds, and agricultural molecules have to satisfy physicochemical requirements like solubility, foliar uptake, and systemic movement in plants that pull the useful chemical space away from where medicinal-chemistry-trained models are comfortable.

We've published work in Analytical Chemistry on a serum-based blood test for lung cancer that reads the full Raman spectrum of a patient's blood rather than chasing a single biomarker. The appeal of this "data-first" approach is that it needs no predetermined target and only 5 microliters of serum, but is limited by the high similarity in chemical composition between healthy and cancer serum, which leaves the disease-relevant differences buried in noise and in the natural biological variation from one patient to the next.

We've published work in Research (a Science Partner Journal) on a dual-modal "search-and-confirm" approach to glioblastoma surgery that pairs indocyanine green (ICG) fluorescence with label-free Raman spectroscopy. ICG is widely used to highlight tumor tissue intraoperatively, but it accumulates wherever vascular boundaries are disrupted, which leads to signal outside the tumor and a systematic overestimate of the tumor boundary, risking resection of healthy brain tissue. Raman spectroscopy reads molecular composition directly and matches the true margin, but it's too slow to survey an open surgical field point by point.

We've published work in Chemical & Biomedical Imaging covering our development of pemefolacianine (NY-07) to address a critical failure mode in fluorescence-guided surgery. Current FDA-approved probes generate false-positive rates of 25-68% because they accumulate in both tumor and inflammatory tissue, leading to unnecessary resections and surgical complications. NY-07, designed through ML optimization integrated with CADD modeling of antifolate drugs, achieved 8-fold selectivity for tumor over inflammatory tissue. The compound is currently being advanced through Phase II clinical trials by our industrial collaborator Nanjing Nuoyuan Medical Devices following IND approval from both FDA and NMPA.

We've demonstrated that treatment timing fundamentally determines therapeutic efficacy in combination cancer therapies. Published in Advanced Science, this work establishes that a 36-hour interval between siRNA delivery and photothermal treatment doubles tumor reduction compared to non-optimized protocols. This finding has immediate implications for how we schedule any gene silencing combination therapy.