By Michael Peel,Aanu Adeoye
Publication Date: 2026-01-12 15:00:00
Unlock the Editor’s Digest for free
Roula Khalaf, Editor of the FT, selects her favourite stories in this weekly newsletter.
An international team including researchers from Nvidia and Microsoft has used AI on a biological trove of more than a million species to generate potential new gene editing and drug therapies to combat deadly diseases.
The AI models, known as Eden, use evolutionary information from mainly microbe specimens compiled globally by the UK company Basecamp Research that have never before appeared in public databases.
The initiative is a milestone in increasing efforts to use AI to learn from evolution about the nature and origin of diseases. Researchers have been trying to overcome data shortages and technical limitations that have held back the development of gene therapies.
“What we’re mapping here is organisms all over the planet [and] how they’ve evolved,” said John Finn, Basecamp’s chief scientific officer, adding that he hoped the approach could be used to target thousands of untreatable cancers and genetic conditions.
“Where machine learning models come into this is picking out these very, very hidden relationships between all these different species and 4bn years of evolution,” he said.
The Eden models designed potential new therapies after learning from a dataset that included more than 10bn novel genes from more than 1.03mn species added over the past several years….
