Now, biomedical engineers at Duke University have created a new platform—TuNa-AI—that pushes this paradigm even further. This AI-driven tool employs a hybrid kernel machine to design tunable nanoparticles specifically tailored for drug delivery. This cutting-edge system, developed by HDR, leverages some of the most advanced artificial intelligence (AI) techniques. It then automates these wet lab processes with software and hardware to perfect nanoparticle formation, advancing the field of biomedical engineering exponentially.
Under the leadership of Assistant Professor Daniel Reker, the team has had exceptional success. Intuitively, they proved that TuNa-AI increases the success rate of nanoparticle formation by 42.9% compared to traditional manual methods. The possibilities of this technology are enormous, especially in providing hard-to-reach therapies, like those required to treat leukemia.
Development and Functionality of TuNa-AI
TuNa-AI is a prime example of what’s possible when the most advanced AI meets smart, applied lab work. The platform uses an automated liquid handling system to systematically build a dataset of 1,275 unique formulations. These formulations are typically made up of several therapeutic molecules and excipients—nonactive substances that help improve the drug’s properties and absorption.
“This system allows us to systematically combine many different ingredients in numerous recipes,” said Zilu Zhang, a Ph.D. student in Reker’s lab who contributed significantly to TuNa-AI’s development. The AI uses millions of data points to predict what materials will work best under what conditions. It helps them optimize the selection of nanoparticles, so that they’re not just effective, but stable.
“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,” – Zilu Zhang
TuNa-AI’s ability to rapidly and iteratively optimize formulations will be integral to the development of nanoparticles capable of delivering these challenging-to-encapsulate therapies. This functionality is what distinguishes it from conventional methods, which have difficulty with stability and effectiveness in intricate treatments.
Enhancements in Drug Delivery
As a product, TuNa-AI is an incredible accomplishment. Most notably, its ability to successfully fabricate nanoparticles to deliver anti-cancer therapy for leukemia, a treatment commonly withstanding encapsulation obstacles. TuNa-AI made great strides this time around, enhancing the formulation of a second chemotherapy drug. Most importantly, it reduced the use of a potentially carcinogenic excipient by 75%.
This reduction not only increases safety, but maintains the drug’s efficacy and improves biodistribution in murine models. Reker believes that these novel technologies hold promise to enable a new paradigm of drug formulation and delivery.
“If we can identify the optimal mixture ratios, then we can form the particles and maintain their stability,” – Daniel Reker
The ability to improve upon current content as long as safety is not compromised is the second key advantage of this new technology. New research from Duke University underscores the importance of AI to provide insights in drug formulation. Using this innovation, researchers are developing safer, more effective targeted therapies for cancer and other diseases.
Future Implications and Research
The science behind TuNa-AI has been released in the journal ACS Nano, highlighting its impact in the scientific community. According to these results, this technology could significantly increase its utility outside of oncology. It has the potential to greatly impact other medical specialties that require sophisticated drug delivery systems.
Zhang emphasized the dual capabilities of TuNa-AI: “We showed that TuNa-AI can be used not only to identify new nanoparticles but also optimize existing materials to make them safer.” This flexibility demonstrates the novel potential for future developments in nanoparticle research. Additionally, it paves the way for developing therapies with new and improved safety profiles.
Development of TuNa-AI very quickly. Specifically, it holds the potential to invent more personalized medicine tactics by optimizing individual treatment for each patient’s unique biology using nanoparticle delivery systems.