OpenAI teamed up with PerturbAI and Scripps Research to deploy thousands of AI agents that analyzed biological data from millions of mouse cells. According to OpenAI, the agents ran on GPT-Rosalind and worked through a whole-brain CRISPR atlas, which maps how gene changes affect different cell types in the mouse brain.
The full analysis took 32 minutes. Each agent took on a single gene perturbation, analyzed how the cells responded, and searched the scientific literature for explanations. The team estimates that doing the same analysis by hand would take anywhere from several months to a year.
Among other findings, the agents turned up unexpected differences between two disease-related genes and a possible link between cholesterol regulation and neurodegeneration. In blind comparisons, human experts preferred the distributed agents' reports over those from a single agent 75 percent of the time. The resulting "Reasoning Atlas" is available on GitHub, and the accompanying paper is out on bioRxiv.
OpenAI says these leads should help researchers decide which mechanisms to test in the lab first.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.