Researchers have made significant strides in precision cancer treatment through the development of an AI platform designed to customize protein components and enhance the immune system's ability to combat cancer. This innovative method, published in the journal Science, marks a groundbreaking advancement by demonstrating the capability to design proteins computationally for redirecting immune cells to target cancer cells via pMHC molecules. This advancement has the potential to reduce the time required to identify effective cancer treatment molecules from years to just weeks.
The platform, developed by a collaborative team from the Technical University of Denmark (DTU) and the Scripps Research Institute, addresses a key challenge in cancer immunotherapy: generating targeted treatments that spare healthy tissue. Traditional approaches involve identifying specific T-cell receptors that can be used for treatment, a process that is often time-consuming. The new AI-driven method creates molecular "keys" that can quickly target cancer cells.
In their study, researchers focused on the cancer target NY-ESO-1, which is prevalent in various cancers. They successfully designed a minibinder that effectively guided T cells to attack cancer cells in laboratory settings. Additionally, the researchers applied this method to create binders for a cancer target in a metastatic melanoma patient, demonstrating its adaptability for personalized immunotherapy.
A pivotal aspect of this innovation is a 'virtual safety check' utilized by the researchers to screen designed minibinders against pMHC molecules found on healthy cells, which helps mitigate potential side effects prior to experimental testing.
Looking ahead, it is estimated that it may take up to five years before this method is ready for clinical trials in humans. Once implemented, it will involve modifying patients' immune cells to carry the AI-designed minibinders, enabling these cells to seek and destroy cancer cells more effectively.