Creating New Drug Delivery Techniques With AI

Duke researchers have developed a new AI-powered approach to nanoparticle drug delivery design, which performed well in lab tests with cancer drugs

Image
a rendering of a cell

AI helps speed up the process by proposing combinations of ingredients people haven’t thought of before, say the researchers. It’s like making a new recipe, and the team took these drug delivery recipes designed by its AI and had robots mix many options together in the lab to test them.

In a recently published paper, the researchers show how they were able to use this approach to create more efficient delivery systems for the drugs that are used for treating cancer.

In one example, the team created a new nanoparticle recipe for leukemia drug venetoclax. This formulation dissolved better and more effectively halted leukemia cell growth in the lab compared to venetoclax not packed into a nanoparticle.

In another example, the researchers wanted to improve an existing recipe for trametinib, a therapy for several cancers, including skin and lung cancers. Their AI helped them design a new formulation that reduced the use of a potentially toxic component by 75%, while improving how the drug was distributed in lab mice.

“This platform is a big foundational step for designing and optimizing nanoparticles for therapeutic applications,” said biomedical engineer and senior author Daniel Reker. “Now, we’re excited to look ahead and treat diseases by making existing and new therapies more effective and safer.”

Learn more about how federally-funded Duke Research Saves Lives in the full story from the Pratt School of Engineering.