ChatGPT Used to Create Personalized Dog Cancer Vaccine

Paul Conyngham, an Australian tech entrepreneur, used ChatGPT and AlphaFold to help design a personalized mRNA cancer vaccine for his dog, Rosie. The process involved converting biological tissue into data to identify specific mutations in a tumor and translating those findings into a targeted medical treatment.

Rosie, a rescue Staffordshire bull terrier cross, was diagnosed with a mast cell tumor (MCT), which is a common type of skin cancer in dogs. These tumors secrete histamines and can cause various systemic health issues. In Rosie’s case, the tumor on her leg grew to the size of a tennis ball, leading to a decline in her mobility.

Before turning to artificial intelligence, Rosie underwent standard-of-care treatments, including surgery and chemotherapy. These interventions were unsuccessful, and veterinarians informed Conyngham that the dog likely had only months to live.

The Technical Process and AI Integration

Conyngham, a data analyst with experience in machine learning but no formal background in biology, collaborated with scientists from the University of New South Wales to develop the treatment. The process began with the DNA sequencing of the tumor, a step for which Conyngham provided the funding.

The sequencing process read the DNA of the tumor—a chemical molecule acting as a biological instruction manual—and compared it to healthy cells. This comparison identified mutations, or spelling mistakes, in the cancer’s DNA that distinguished the tumor from healthy tissue.

We took her tumor, we sequenced the DNA, we converted it from tissue to data, and then we used that to search for the problem in her DNA, and then developed a cure based on that

Paul Conyngham

Once the DNA was converted into a data file listing the mutations, Conyngham used ChatGPT to assist in identifying the specific sequences and generating the RNA vaccine. The project also utilized AlphaFold, an AI system designed to predict protein structures, to aid in the design of the personalized vaccine.

mRNA and Neoantigens

The vaccine relied on mRNA technology and the identification of neoantigens. The process involves reading the genetic instructions inside a tumor and writing a new set of instructions via mRNA to enable the immune system to recognize and attack the cancer cells.

The speed of the transition from data analysis to a physical treatment was noted by medical professionals. Steven Hsesheng Lin, a radiation oncologist and physician-scientist at the MD Anderson Cancer Center, observed that the movement from concept to translation to the actual patient—in this case, an animal patient—is astounding.

The resulting personalized mRNA vaccine was generated and injected into Rosie shortly after the sequence was identified. This application demonstrates a use case where large language models and protein-folding AI are used to bridge the gap between genomic data and clinical application.