Researchers have developed a groundbreaking AI platform that can design proteins within weeks to help T cells precisely target and eliminate cancer cells, significantly accelerating the timeline for developing new cancer treatments.
Researchers have developed an innovative AI-based platform that could transform precision cancer treatment, significantly reducing the time required to develop new therapeutic proteins.
The method, published in the journal Science, showcases the ability of artificial intelligence to design molecular “missiles” that arm T cells — a critical component of the immune system — to effectively target and destroy cancer cells. This advancement could cut the development time for new cancer treatment proteins from years to just a few weeks.
“We are essentially creating a new set of eyes for the immune system,” last author Timothy P. Jenkins, an associate professor at the Technical University of Denmark (DTU), said in a news release. “Current methods for individual cancer treatment are based on finding so-called T-cell receptors in the immune system of a patient or donor that can be used for treatment. This is a very time-consuming and challenging process. Our platform designs molecular keys to target cancer cells using the AI platform, and it does so at incredible speed, so that a new lead molecule can be ready within 4-6 weeks.”
The pioneering AI platform is the brainchild of a collaborative effort between researchers at DTU and the Scripps Research Institute in the United States. Their goal was to streamline one of the most pressing challenges in cancer immunotherapy: designing targeted treatments that precisely attack tumor cells without harming healthy tissue.
Normally, T cells detect cancer cells by recognizing specific protein fragments, or peptides, presented on the cell surface by molecules called peptide-major histocompatibility complexes (pMHCs). However, producing therapeutic proteins that leverage this natural process is notoriously slow and complex due to the variability in each patient’s T-cell receptors.
In the study, the platform’s efficacy was tested on a well-recognized cancer target called NY-ESO-1, prevalent in a variety of cancers. By designing minibinders that bound tightly to NY-ESO-1 pMHC molecules, the researchers created modified T cells termed ‘IMPAC-T’ cells, which successfully directed the T cells to kill cancer cells in lab experiments.
“It was incredibly exciting to take these minibinders, which were created entirely on a computer, and see them work so effectively in the laboratory,” added co-author Kristoffer Haurum Johansen, a postdoctoral researcher at DTU.
The research team also demonstrated the versatility of the platform by designing binders for a cancer target in a metastatic melanoma patient. This indicates the method’s potential for developing personalized immunotherapies against various cancer targets.
An essential innovation in this process was the development of a “virtual safety check.” Using AI, the researchers screened the designed minibinders against pMHC molecules on healthy cells to eliminate those that might cause adverse side effects. This preemptive measure aims to enhance the safety and effectiveness of the resulting treatments.
“Precision in cancer treatment is crucial. By predicting and ruling out cross-reactions already in the design phase, we were able to reduce the risk associated with the designed proteins and increase the likelihood of designing a safe and effective therapy,” added co-author Sine Reker Hadrup, a DTU professor.
While this technology is still in the experimental phase, Jenkins expects it could be ready for initial human clinical trials within five years. The treatment process will involve drawing blood from patients, modifying their T cells with the AI-designed minibinders in a lab, and then reinfusing the enhanced immune cells back into the patient. These modified T cells will act like precision-guided missiles, seeking out and eliminating cancer cells in the body.
Source: Technical University of Denmark