AI-Designed mRNA Vaccine Shrinks Dog's Cancer Tumour by Seventy-Five Percent

A Tech Entrepreneur's Race Against Time

When Paul Conyngham's rescue dog Rosie was diagnosed with mast cell cancer in twenty twenty-four, conventional treatments failed to stop the disease. Surgery, chemotherapy, and immunotherapy slowed the progression but couldn't shrink the tumours growing on her leg. Veterinarians gave the Staffordshire Bull Terrier-Shar Pei cross between one and six months to live.

From Data Science to DNA Sequencing

Conyngham, who runs a Sydney consultancy and has seventeen years of experience in machine learning, turned to the tools he knew best. He used ChatGPT as a research assistant to map out an entire treatment pipeline: sequence Rosie's tumour DNA, compare it against her healthy cells, identify the mutations driving the cancer, and design a vaccine targeting those specific neoantigens. He then employed Google DeepMind's AlphaFold to model the three-dimensional structures of proteins encoded by the tumour mutations, combining it with his own machine learning algorithms for neoantigen selection.

University Collaboration Brings the Vaccine to Life

The project drew in established research institutions. UNSW's Ramaciotti Centre for Genomics collaborated on the genomic analysis, while Pall Thordarson, director of the UNSW RNA Institute, produced the bespoke mRNA vaccine from Conyngham's data in less than two months. A veterinary researcher at the University of Queensland, who held ethical approvals for experimental treatments, administered the first injection in December twenty twenty-five, followed by a booster.

Dramatic Results and Cautious Optimism

Within roughly a month, Rosie's largest tumour had shrunk by up to seventy-five percent. Scientists involved have stressed that this remains a single case and controlled trials are needed before broader conclusions can be drawn. Conyngham is now sequencing a second tumour that did not respond to the initial vaccine to understand why it proved resistant.

Implications for Human Medicine

The case arrives as pharmaceutical companies are running large-scale Phase Three trials on the same concept for human patients. Thordarson framed the significance plainly: personalised medicine can be highly effective and delivered in a time-sensitive manner using mRNA technology, and what works for dogs could ultimately help humans too.