CHAPEL HILL, N.C., Sept. 15, 2026 - UNC Lineberger Comprehensive Cancer Center has received $40 million from the OpenAI Foundation, the non-profit parent organization that governs the for-profit company OpenAI Group PBC, to generate data that could make personalized cancer vaccines more effective.
Cancer vaccines are emerging as a promising frontier in cancer medicine but designing them effectively remains a challenge. Immunologist Benjamin Vincent, MD, and computational biologist Alex Rubinsteyn, PhD, are gathering clinical data to train AI models that can identify stronger cancer-cell targets and guide the development of more precise, personalized vaccines.
Alex Rubinsteyn, PhD
"Personalized cancer vaccines are finally starting to show signs of clinical efficacy, but many fail in the development process because they are too arbitrary," said Rubinsteyn, who is an expert in machine learning and computational medicine at the UNC School of Medicine. "Our goal is to help the world design personalized and more effective cancer vaccines, using the power of rich data and artificial intelligence."
The announcement comes as the OpenAI Foundation launches its second science program, Public Data for Health. The initiative supports high-quality, open-access scientific datasets that researchers and AI tools worldwide can use to advance life science and disease research for the public good.
"AI has enormous potential to help researchers design better cancer treatments, but that progress depends on having the right biological data to learn from," said Jacob Trefethen, Head of Life Sciences and Curing Diseases at the OpenAI Foundation. "UNC's work will generate data that researchers don't have at the scale they need today and make those findings broadly available so scientists around the world can build on them. By giving the broader scientific community a stronger foundation to work from, we hope to open up new possibilities for cancer research and ultimately help more patients benefit from advances that once felt out of reach."
Cancer vaccines are designed using tumor cells and immune cells derived from a patient. Proteins on the surface of tumors are of particular interest to researchers, as they act much like a red flag in a bull fighting ring. Vaccines can be used to train the immune response to recognize these red flags and create a highly coordinated attack on cancer cells.
Benjamin Vincent, MD
But performing such a task for any given cancer patient - each with their own specific cancer type and immune responses - requires complex scientific machinery, time, and, of course, data analysis. Vincent and Rubinsteyn aim to expedite this process by analyzing hundreds of de-identified tumor tissue and immune cells from three biobanks.
These data will be used to train improved AI-based methods for selecting tumor antigens for inclusion in personalized vaccine therapies. In parallel, researchers will compare multiple vaccine formulations in clinical trials for their ability to raise tumor-specific immune responses in triple-negative breast cancer.
"Selecting tumor antigens that are actually good targets, and understanding the relative potency of vaccine formulations for personalized therapy, are big problems in the field which our work will address," said Vincent, who is a member of the Immunology and Immunotherapy Research Program at UNC Lineberger Comprehensive Cancer Center.
If successful, the research could set the foundation for future vaccine candidates and speed up the rate at which personalized cancer vaccines can get into the hands of oncologists.
