😸 ChatGPT saved this dog's life

2026-03-05 · Source: The Neuron · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Emerging Technologies & Innovation · Depth: Intermediate, medium

Summary

A data engineer with no biology background successfully used AI tools, including ChatGPT and Google DeepMind's AlphaFold, to develop a personalized mRNA cancer vaccine for his dog, Rosie, who was diagnosed with deadly mast cell cancer in 2024. After traditional treatments failed, Paul Conyngham sequenced Rosie's DNA for $3,000, identified tumor mutations, and mapped proteins to drug targets using AlphaFold. He then collaborated with UNSW's RNA Institute to synthesize a custom mRNA vaccine based on his formula. Following the first injection in December, Rosie's tennis ball-sized tumor shrunk by half, and she resumed normal activities. This case is being hailed as a "citizen science" breakthrough, informing human cancer research and demonstrating the potential of AI tools in accelerating complex medical discoveries.

Key takeaway

For AI/ML Directors evaluating novel research methodologies, Rosie's case highlights that AI-powered citizen science can accelerate complex biological research, potentially compressing years of work into months. Your teams should explore integrating advanced AI tools like AlphaFold and structured LLM prompting into early-stage R&D to identify new pathways or validate hypotheses, even with limited domain expertise. This approach could significantly reduce discovery timelines and costs for your organization.

Key insights

AI tools enable non-experts to achieve significant scientific breakthroughs, exemplified by a personalized cancer vaccine for a dog.

Principles

• AI democratizes complex scientific research.
• Structured prompts enhance AI model reliability.

Method

The process involved DNA sequencing, AI-driven mutation identification and protein mapping (AlphaFold), and mRNA vaccine synthesis based on AI-generated formulas, demonstrating a novel "citizen science" approach.

In practice

• Use ChatGPT for initial research guidance.
• Employ AlphaFold for protein structure prediction.
• Structure prompts with clear sections and emphasis.

Topics

• AI in Medicine
• Large Language Models
• Prompt Engineering
• AI Ethics
• AlphaFold

Code references

• jina-ai/jina-grep-cli

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, Data Scientist, General Interest

Related on AIssential

• 🗞️ Techie uses ChatGPT and AlphaFold to build DIY mRNA cancer vaccine, saves dog — AI tools empower individuals without specialized training to conduct complex scientific research and develop novel solutions.
• The Dog That Hacked Cancer — AI tools can accelerate personalized medicine development, even for non-experts.
• Understanding cancer at a genetic level with AI — AI tools like AlphaFold are democratizing advanced biomedical research in resource-limited settings.
• Stanford researchers will discuss their agentic 'scientists' that are on course to reshape drug discovery at VB Transform 2026 — Agentic AI systems with hierarchical orchestration and continuous context can significantly improve the efficiency of complex, multi-stage processes like drug discovery.
• He won a Nobel here for AlphaFold. Then he left. - John Jumper — AlphaFold demonstrates that highly specialized, empirically-driven AI can solve long-standing scientific "holy grail" problems.
• Demis Hassabis On What AI Will Do Next — AI is evolving into a co-creative partner, poised to accelerate scientific discovery and revolutionize human health within decades.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Neuron.