Biomedical engineers at Duke University have developed a groundbreaking artificial intelligence platform that addresses a critical bottleneck in pharmaceutical development: optimizing nanoparticle formulations for drug delivery. The TuNa-AI (Tunable Nanoparticle platform guided by AI) system combines automated laboratory techniques with machine learning to design more effective and safer drug delivery vehicles.
The research, published September 14 in ACS Nano, represents a significant advancement in addressing the challenges of delivering difficult-to-encapsulate therapeutics to their target locations in the body.
Addressing Current AI Limitations in Drug Formulation
Existing AI platforms in drug development face a fundamental limitation: they can either recommend what materials to use or determine optimal quantities, but not both simultaneously. This constraint significantly impacts the effectiveness of nanoparticle design.
"When you're creating a nanoparticle, how well it works doesn't just depend on the recipe, but also on the quantity of the various ingredients, including both the active drug and inactive materials," explained Zilu Zhang, a PhD student in the lab of Daniel Reker, assistant professor of biomedical engineering. "Existing AI platforms can only handle one or the other, which limits their overall effectiveness."
The challenge extends beyond ingredient optimization. More complex AI platforms require massive datasets for effective training, while simpler approaches struggle to differentiate between similar materials, creating a significant gap in the drug development pipeline.
Revolutionary Platform Design and Performance
To overcome these limitations, the Duke team developed TuNa-AI using an automated liquid handling platform that systematically created 1,275 distinct formulations. Each formulation combined different therapeutic molecules with excipients—nonactive substances like coloring agents, preservatives, and other molecules that improve a drug's physical properties and absorption.
"By using robotics, we were able to combine many different ingredients in many different recipes very systematically," Zhang noted. "Our AI model was then able to look at that data for how different materials perform under different conditions and extrapolate that knowledge to select an optimized nanoparticle."
The results demonstrated the platform's superior performance, achieving a 42.9% increase in successful nanoparticle formation compared to standard approaches.
Clinical Applications and Proof of Concept
The research team validated their platform through two significant case studies that highlight its clinical potential. In the first proof of concept, TuNa-AI successfully formulated nanoparticles that more effectively encapsulated venetoclax, a chemotherapy drug used to treat leukemia. The resulting nanoparticles showed improved solubility and were significantly more effective at halting leukemia cell growth in laboratory tests compared to the non-encapsulated drug alone.
The second case study demonstrated the platform's ability to enhance drug safety. The AI-guided system reduced the use of a potentially carcinogenic excipient by 75% in a second chemotherapy drug's formulation while preserving the drug's efficacy and improving its biodistribution in mouse models.
"We showed that TuNa-AI can be used not only to identify new nanoparticles but also optimize existing materials to make them safer," Zhang emphasized.
Future Applications and Collaborative Efforts
The implications of this breakthrough extend far beyond the initial proof-of-concept studies. The team is actively expanding their platform to process other types of biomaterials for various therapeutic and diagnostic applications. They are collaborating with researchers and physicians both inside and outside of Duke University to apply this technology to drug delivery challenges in difficult-to-treat diseases.
"This platform is a big foundational step for designing and optimizing nanoparticles for therapeutic applications," said Reker. "Now, we're excited to look ahead and treat diseases by making existing and new therapies more effective and safer."
The research addresses a critical need in pharmaceutical development, where finding the right therapeutic molecule represents only half the challenge. The ability to deliver that molecule to the right location safely and effectively has remained a significant hurdle in translating promising drug candidates into successful treatments.
The study was supported by the National Institute of Health NIGMS Grant (R35GM151255), the Duke University Shared Materials Instrumentation Facility (SMIF), and the North Carolina Research Triangle Nanotechnology Network (RTNN), which receives support from the National Science Foundation as part of the National Nanotechnology Coordinated Infrastructure.
