AI-designed proteins outperform existing CAR T designs against BCMA tumors in mice
CAR T cell therapy, which involves genetically modifying a patient's own immune cells to fight cancer, is a technique that has shown great promise, especially against blood cancers. But currently, only about 4% of patients with advanced or metastatic cancer in the United States are candidates for CAR T therapy, and closer to 3% will actually benefit, according to one recent analysis.
A study conducted by Memorial Sloan Kettering Cancer Center (MSK) has found that AI-designed proteins outperform existing CAR T therapies against a specific cancer target in mice. CAR T cell therapy involves genetically modifying a patient's immune cells to target and destroy cancer cells. However, only a small percentage of advanced or metastatic cancer patients in the US currently benefit from this treatment.
The MSK lab led by computational biologist Caleb Lareau aims to improve CAR T therapies using generative AI to design better binders, proteins that recognize and bind to cancer cells. In a proof-of-concept study published in Nature Biomedical Engineering, the AI-driven approach significantly outperformed existing FDA-approved CAR T therapies targeting a protein called BCMA.
The study also sheds light on why AI models have struggled to design effective binders for the CD19 target and why CAR T cells can sometimes activate prematurely. The ultimate goal is to replace the traditional "guess and check" approach in the field with a more evidence-based understanding of why some cancer-targeting proteins work well and others fail. The AI-driven approach could also be used to develop personalized treatments for rare cancers.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
