Vets gave his dog months to live — a man with no biology background built an AI vaccine to save her
With help from Australian scientists, he helped develop what researchers say is the first bespoke mRNA cancer vaccine created for a dog.
After his dog Rosie was diagnosed with aggressive cancer, Australian tech entrepreneur Paul Conyngham refused to accept that nothing more could be done. Despite surgery and chemotherapy, the tumors kept spreading, and Rosie’s health continued to decline.
Veterinarians told him the dog likely had only months left to live, but Conyngham wasn't one to give up. In fact, he went through a very unorthodox method to give Rosie a fighting chance. A report from March 16 expands further on this extraordinary event.
According to a report by The Australian shared by Fortune, Conyngham decided to approach the situation the same way he would tackle a complex engineering problem. Rather than accepting the prognosis, he began researching new treatment possibilities and eventually turned to artificial intelligence to help him explore options.
Conyngham is not a medical researcher, but he does have a strong technology background. He is an electrical and computing engineer who co-founded Core Intelligence Technologies and previously served as a director of the Data Science and AI Association of Australia.
"I went to ChatGPT and came up with a plan on how to do this," Conyngham explained. The AI suggested exploring immunotherapy and directed him to scientists at the University of New South Wales’ Ramaciotti Centre for Genomics. Conyngham reached out to the researchers and convinced them to help analyze Rosie’s tumor. He paid the university to sequence the tumor’s DNA so the underlying mutations could be studied in detail.
Speaking about the process during a television interview by TODAY, Conyngham explained how Rosie’s tumor was essentially converted into data that could be analyzed. "We took her tumor, we sequenced the DNA, we converted it from tissue to data," he said. AI tools played a major role in the next stage of the work.
Conyngham used AlphaFold, an AI system developed by Google’s DeepMind, to identify mutated proteins that could potentially be targeted with treatment. The analysis eventually pointed to an immunotherapy approach that appeared promising for Rosie.
However, the pharmaceutical company behind the drug declined to provide the treatment. With time running out, Conyngham turned to another group of researchers. Nanomedicine pioneer Professor Pall Thordarson, director of the University of New South Wales’ RNA Institute, stepped in and agreed to try designing a custom mRNA cancer vaccine tailored specifically to Rosie’s tumor.
Even for researchers who had worked with RNA technologies for years, the timeline was ambitious. "I was probably mainly just thinking this might take too long," he said.
But once Conyngham’s analysis identified the key genetic targets, the researchers developed a personalized mRNA vaccine in less than two months sing the tumor sequence data. "This is the first time a personalized cancer vaccine has been designed for a dog," Thordarson said.
mRNA-based cancer vaccines have shown measurable clinical results. In a mid-stage clinical trial involving a combination of Moderna’s personalized mRNA cancer vaccine, Intismeran autogene, plus the immunotherapy drug Keytruda for melanoma patients, the risk of cancer recurrence or death was reduced by 49% compared with Keytruda treatment alone at the five-year mark.
At the time the treatment began, her health had already started to decline significantly. Within weeks of the treatment, however, her condition began to improve. "Six weeks post-treatment, I was at the dog park when she spotted a rabbit and jumped the fence to chase it," Conyngham said.
While the vaccine has not eliminated the cancer entirely, researchers estimate that roughly three-quarters of the cancer burden has been pushed back by the treatment. "I’m under no illusion that this is a cure. But I do believe this treatment has bought Rosie significantly more time and quality of life," Conyngham said.
Thordarson believes Rosie’s case shows how rapidly treatments can be designed when genomic data, AI analysis, and mRNA technology are combined. For Conyngham, however, the project began with a much simpler motivation. Rosie had been his constant companion through difficult moments in his life.
When she was given a terminal diagnosis, he felt he owed it to her to try everything he could. "Rosie is my best mate," he said.
More on Scoop Upworthy
Tenant uses ChatGPT to uncover crucial evidence and win legal battle against greedy landlord
Share on Facebook
