Ian Quigley was employee #13 at pharmaceutical company AI Recursion until 2021, when he quit and turned the basement of his Utah home into a laboratory to develop AI models that enable to predict which proteins small-molecule drugs might target — a tool that he and co-founder Andrew Blevins lost during his time at Recursion.
When setting up the lab, Quigley ordered an Illumina DNA sequencer that the delivery guy had wanted to leave on his porch. Panicked by the idea, he picked it up in his Toyota Yaris, folding down the rear seats to place it next to his dog’s kennel.
In this basement lab, Quigley and his small team at Leash Bio produced about 133 million data sets of small molecules binding to protein targets. Earlier this year, they released this data as a training source in a competition to determine whether AI models that predict the interactions of small molecules with proteins actually learn anything about biology or were simply memorizing what they had seen before.
This article is reserved for STAT+ subscribers
Unlock this article – and get additional analysis of the technologies disrupting healthcare – by subscribing to STAT+.
Already have an account? Log in
See all packages
To read the rest of this story, subscribe to STAT+.
Subscribe