Alzheimer's disease affects millions, but the genes driving it are still being uncovered. Now, researchers have used a clever AI approach to find clues hidden in brain cell data that standard methods overlooked.
The team applied a hybrid statistical framework, powered by ChatGPT-4o, to single-cell RNA sequencing data from the ROSMAP study—a large collection of brain tissue samples. This AI-assisted method identified genes linked to Alzheimer's that were previously undetected, including those involved in gamma-secretase pathways, which are known to play a role in the disease.
It's important to note that this is an early, methodological study—not a clinical trial. The results come from a single dataset and have only been validated through simulations, not in other groups. So while the findings are promising, they are not yet ready for the clinic.
Still, this work shows how AI can help researchers sift through massive genetic data to find new targets for understanding and potentially treating Alzheimer's. More studies are needed to confirm these results in other populations.