He had adopted Rosie, a Staffy–Shar Pei cross, from an animal shelter in 2019 (Image source: @TheRundownAI/X)
In a remarkable incident, an Australian techie used AI tools to help create an experimental vaccine that may help treat cancer in his pet dog.
According to reports, Paul Conyngham took help from several AI platforms such as ChatGPT and AlphaFold, developed by Google DeepMind, to design a personalised treatment after his dog was diagnosed with cancer.
Conyngham shared his emotional journey during an appearance on the Australian news program ‘Today’, saying, “When she was handed the sentence, I felt I had to do my part for her.”
He had adopted Rosie, a Staffy-Shar Pei cross, from an animal shelter in 2019. Five years later, the dog was diagnosed with cancer. Despite spending money on conventional treatments such as chemotherapy, the tumour did not respond to the therapy.
Conyngham then decided to explore a different approach with the help of AI. According to The Australian, he sequenced Rosie’s DNA to identify the underlying cause of the cancer and potentially design a targeted treatment.
He shared that he used ChatGPT to help develop a plan for the process. “I went to ChatGPT and came up with a plan on how to do this,” he told the publication.
🇦🇺An Australian tech founder with zero biology background sequenced his dog’s tumor DNA, then used ChatGPT and AlphaFold to design a custom mRNA cancer vaccine.
A month later, the tumors shrank by half.
And this is just the start of AI medicine.pic.twitter.com/af7HlfJhgK
— Mario Nawfal (@MarioNawfal) March 15, 2026
Conyngham already had a strong background in AI technologies, with 17 years of experience working in machine learning and data analysis. He then reached out to the University of New South Wales’s Ramaciotti Centre for Genomics to obtain the genomic data, which carried out the sequencing for about $3,000 (approximately Rs 2 lakh), the report stated.
After receiving the results, Conyngham compared Rosie’s healthy DNA with the DNA from the tumour to identify genetic mutations responsible for the cancer.
Explaining the process, he said, “It’s like having the original engine of your car and then a version of the engine 3,00,000 km down the road – you can compare them and see where there’s damage.”
He then used AlphaFold to analyse protein structures linked to the identified mutations. This step helped determine which drugs or treatments could potentially target the tumour. Following this, Conyngham reached out to researchers at the university to develop a customised mRNA vaccine for Rosie.
An mRNA vaccine works by delivering synthetic messenger RNA into cells, prompting the body to produce a harmless protein that triggers an immune response against the disease, the report added.
However, developing the treatment came with regulatory challenges. Conyngham said obtaining ethical approval to conduct a drug trial on Rosie took months. “It took me three months, putting two hours aside every single night just typing up this 100-page document,” he said.
According to the report, Rosie received her first injection in December, followed by booster doses. Since beginning the treatment, the tumour has reportedly shrunk significantly, although the cancer had already reached an advanced stage.
Despite the encouraging results, Conyngham remains cautious about calling it a cure. “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 is currently working on developing a second vaccine to target another tumour. “There’s actually a chance that for some cancers, we can change it from being a terminal sentence to a manageable disease,” he said.