Skip to content
View original post on X: Rohan Paul
Published
Pick75/100

OpenAI and partners split a mouse brain atlas across 1,946 AI agents

AIOpenAI, PerturbAI and Scripps Research had 1,946 GPT-Rosalind-5.5 agents analyze a whole-brain mouse CRISPR atlas in 32 minutes. The agents matched or refined 48 of 55 published findings the expression data could support, and blinded PhD reviewers preferred their reports 75% of the time.

AIWhy it matters.

The source shows a concrete method of splitting one large biology dataset among many agents, with specific results and reviewer preferences for readers to weigh.

Rohan PaulVerified on X
@rohanpaul_ai
View on X

OpenAI showed that AI agents can handle the slowest step in modern biology, making sense of huge experiments.

By splitting a huge brain experiment among 1,946 AI agents, OpenAI got in 32 minutes what it estimates would take people months: a ranked list of leads for new brain-disease research.

So biology labs can now produce experiments far bigger than their own experts can fully interpret

OpenAI, PerturbAI and Scripps Research had 1,946 GPT-Rosalind-5.5 agents interpret a whole-brain mouse CRISPR atlas in 32 minutes.

Each agent analyzed a single knockout’s effects and searched the literature, without seeing the atlas paper, which appeared after the model’s December 2025 knowledge cutoff.

They still matched or refined 48 of the 55 published findings the expression data could support.

The main advance is the method: split 1 giant analysis into nearly 2K small ones, 1 gene per agent, and run them all at once. A single agent given 893 genes cited just 11 papers, while the split-up agents cited 711 times as many, and blinded PhD reviewers preferred their reports 75% of the time.

OpenAI@OpenAI
GPT-Rosalind surfaced a new lead for drug discovery: could restoring cholesterol transport protect neurons from degeneration? DCTN1 is a gene linked to Perry syndrome, a rare neurodegenerative disorder. In mouse-brain data, disrupting it increased expression of genes involved in making cholesterol. GPT-Rosalind suggested a possible explanation: cholesterol may not be reaching where neurons need it. That gives scientists a specific mechanism to test and, if confirmed, a direction for developing new treatments for neurodegenerative disorders. With @perturbai_tx and @scrippsresearch, a team of thousands of GPT-Rosalind agents worked in parallel, connecting gene-expression results from millions of mouse brain cells with scientific literature in just 32 minutes. We’re now expanding this collaboration to identify new drug targets. https://openai.com/index/scaling-ai-research-for-complex-biological-data/
View quoted post on X
Source details

Rohan Paul · x.comPublished · added here

Original title: OpenAI showed that AI agents can handle the slowest step in modern biology, making sense of huge experiments.

Topics

OpenAI / ChatGPTAI agentsReasoningPapers & research