Using big data for good

MIT Technology Review

by Whitney Bauck

February 24, 2026

AI-Generated Deep Dive Summary

A photogenic Russian Blue cat named Petra has become the world’s most sequenced feline, thanks to her rescuer Charlie Lieu, a data expert and cofounder of Darwin’s Ark, a nonprofit focused on pet genetics. Since its launch in 2018, Darwin’s Ark has gathered genetic and behavioral data from over 67,000 cats and dogs, enabling researchers to study health issues like cancer, behavior traits, and inherited trainability. This innovative approach combines DNA analysis with detailed owner surveys about pets’ habits and personalities, creating a rich dataset that bridges genetics and real-world observations. Lieu’s motivation stems from her experience in the Human Genome Project and her personal connection to cancer—her mother died of the disease, and she herself has had tumors removed. She realized how challenging it is to study complex diseases in humans due to privacy concerns and participation hurdles. By focusing on pets, who are often more accessible for data collection, Darwin’s Ark bypasses these obstacles while still contributing valuable insights into genetics and health. The project has already yielded significant findings, such as the discovery that only 9% of dog behavior can be predicted by breed, debunking common stereotypes. Lieu explains how this model could inspire similar approaches in human medicine, using AI to process vast amounts of genetic and behavioral data at scale. By leveraging pet owners’ enthusiasm for sharing their pets’ stories, Darwin’s Ark has created a unique platform that democratizes science while advancing cutting-edge research. For readers interested in AI, this story highlights the potential of big data and community-driven research to tackle complex scientific challenges. The approach not only accelerates discovery but also demonstrates how AI tools can analyze massive datasets to uncover patterns and correlations that might otherwise remain hidden. By focusing on pets, Darwin’s Ark has found a novel way to gather high-quality data while fostering public engagement with science—a model that could inspire similar innovations in other fields. In an era where big data is transforming nearly every industry, the work of Darwin’s Ark shows how technology can be harnessed for meaningful scientific progress. By bridging genetics and behavior through citizen science, Lieu and her team have created a scalable platform that could serve as a blueprint for future research initiatives. Their story not only advances our understanding of pet health but also opens new avenues for AI-driven insights into human diseases and behaviors.

Verticals

aitechscience

Originally published on MIT Technology Review on 2/24/2026