When Sydney-based tech entrepreneur Paul Conyngham learned that his eight-year-old staffy-shar pei mix, Rosie, had been given just months to live, he refused to accept that nothing more could be done. Instead, he opened his laptop and got to work.
According to sources, Rosie, a rescue dog who had been abandoned in bushland before Conyngham adopted her in 2019, was diagnosed with mast cell cancer in 2024. An initial round of chemotherapy and surgery slowed the progression but failed to reduce the tumors.
With conventional veterinary medicine running out of options, Conyngham turned to artificial intelligence to try to build something that had never existed before: a custom mRNA cancer vaccine designed specifically for his dog.
“She’s been with me through a whole bunch of really tough times, giving unconditional love,” Conyngham said during a recent interview. “She’s my best mate.”
The project began with a $3,000 investment in DNA sequencing. Conyngham collected samples from Rosie’s healthy cells and her tumor tissue, then used AI tools including ChatGPT and AlphaFold to comb through the genetic data and identify the mutations driving her cancer. He had no background in biology.
“I went to ChatGPT and came up with a plan on how to do this,” he explained. “The idea is you take the healthy DNA out of her blood and then you take the DNA out of her tumour and you sequence both of them to see exactly where the mutations have occurred.”
He put it in plain terms: “It’s like having the original engine of your car and then a version of the engine 300,000km down the road. You can compare them and see where there’s damage.”
Despite arriving as an outsider, Conyngham’s persistence opened doors at some of Australia’s most respected research institutions. Scientists at the Ramaciotti Centre for Genomics at the University of New South Wales agreed to help analyze the genomic data, though the initial inquiry raised eyebrows.
“We often get oddball queries, and this one was coming from a private individual looking to sequence his dog,” recalled Martin Smith from the centre.
What won them over was straightforward tenacity. “What really convinced them is I just kept going and providing results,” Conyngham said. Smith confirmed it: “Paul was relentless.”
The path was not without setbacks. The first targeted treatment Conyngham identified was a pharmaceutical immunotherapy d**g, but the manufacturer declined compassionate-use access, stopping the project in its tracks. “The wind went out of my sails,” he admitted.
Rather than accepting defeat, Conyngham pivoted. He connected with Pall Thordarson, director of the UNSW RNA Institute, and together they designed a custom mRNA vaccine. Conyngham ran an algorithm to determine the precise formulation and handed it over to the research team.
“He ran an algorithm to inform the design of the mRNA and sent it to us, and we made a little nanoparticle,” Thordarson explained.
Before a single dose could be administered, however, Conyngham had to navigate a significant regulatory process. “I had to do everything by the book because you can’t just willy-nilly create a vaccine in Australia,” he said.
A formal ethics approval was required, and Conyngham found a path through veterinary immunotherapy researcher Rachel Allavena at the University of Queensland, whose existing approved research program could accommodate Rosie’s treatment.
The vaccine was transported to Gatton, Queensland, where Rosie received her first injection in December, followed by a booster the following month. From the moment Conyngham submitted his sequence design to the RNA Institute, the turnaround to delivery took less than two months.
The response came within weeks. “In December she had low energy because the tumours were creating a huge burden for her,” Conyngham said. Then, six weeks post-treatment: “I was at the dog park when she spotted a rabbit and jumped the fence to chase it.”
Allavena, who administered the therapy, described the outcome with barely contained amazement. “Rosie’s cancer was really, really advanced but one tumour has shrunk quite a lot, probably halved,” she said. “It’s definitely working. When it happens that first time, it’s magical.”
For the researchers involved, the implications stretch well beyond one dog’s recovery. Smith was unambiguous about what the result means: “It was like holy c**p, it worked! It raises the question, if we can do this for a dog, why aren’t we rolling this out to all humans with cancer?”
Thordarson framed the project in even broader terms. “This is the first time a personalised cancer vaccine has been designed for a dog,” he said. “What Rosie is teaching us is that personalised medicine can be very effective, and done in a time-sensitive manner, with mRNA technology. It’s democratising the whole process.”
David Thomas, from the UNSW Centre for Molecular Oncology, pointed to something deeper in what Conyngham had accomplished. “The striking thing about this is the idea of citizen science, where a punter in the street, with a computer science background, can use their skills in the scientific process,” he said. “That’s a very impressive thing.”
Allavena was equally clear about where this stands in medical history: “This is the first time anyone’s ever done this therapy.”
Conyngham is careful not to overstate what has been achieved. “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,” he said.
He is already pursuing a second round of DNA sequencing to design a new vaccine targeting a tumor that did not respond to the first treatment. Rosie’s total care has now cost tens of thousands of dollars overall.
Global pharma companies including Moderna are already pursuing personalized cancer vaccines, but this work, he argues, proves it can be built and deployed domestically. “We can actually do this here, we don’t have to necessarily rely on foreign companies to help us do this,” he said in a television interview. “That means we can democratize this technology in Australia and we can also use it for other diseases possibly.” He pointed to neurological conditions as one potential frontier.
