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. openai.com/index/scaling-ai-…

Using thousands of AI agents to uncover new leads in biological data

See how OpenAI, PerturbAI, and Scripps Research used distributed AI agents to uncover promising research leads in data from millions of brain cells.

openai.com
338
599
231
5,802
1,025,078
In the same mouse-brain dataset, GPT-Rosalind found a possible clue to why TSC2 mutations tend to cause more severe tuberous sclerosis than TSC1 mutations. The two genes work together to regulate mTOR. Yet in one group of cerebellar neurons, disrupting TSC2 changed the expression of dozens of genes, including genes involved in neuronal communication. Disrupting TSC1 had little effect on gene expression in the same cell type. Existing treatments already target mTOR. Do they reverse these changes, or is there more to TSC2’s role in these neurons?

Oct 21, 2026 · 1:32 PM UTC

21
28
1
589
95,114
RelevantRecentLikes
"The agents identified an unexpected difference between Tsc1 and Tsc2, two genes that work together to control mTOR, a major regulator of cell growth, metabolism, and aging. Disrupting either gene had similar effects in several groups of neurons. But in the cerebellum, which helps coordinate movement, Tsc2 disruption altered the activity of dozens of genes involved in neuronal communication, while Tsc1 disruption produced little change." cerebellum goes a lot harder than coordinating movements, and so do TSC1/2 mutations pubmed.ncbi.nlm.nih.gov/2276… pubmed.ncbi.nlm.nih.gov/2510…
3
591
32 minutes for what a grad student would spend a whole thesis on. The funding would run out around chapter two.
3
579
You found the cerebellar-neuron wrinkle. The experiment the field will want next: the same comparison in patient-derived neurons, not another mouse run.
239
What about something like rapamycin? It’s already so well researched and in my own PhD at the moment we are investigating, although in different contexts
359
tsc1 and tsc2 sit in the same complex that keeps mtor in check, so a difference in severity is a really neat thing to chase.
206
Everolimus the mtor inhibitor has been treating TSC for almost 15 years already.
633
The cerebellar-neuron split is the useful clue; pathway summaries would miss that cell-type effect
500
@grok can GPT-Rosalind help with researching the impacts of 2-repeat allele of the MAOA gene in humans pls? i would be very interested in seeing if it can identify any specific demographics which might be at risk for this type of polymorphism in the promoter region of MAOA
1
2
855
How can we establish a causal link between impaired cholesterol trafficking and neurodegeneration in DCTN1-related Perry syndrome, rather than a compensatory response?
287
32 minutes with AI vs. an estimated several months to a year of human analysis and literature review. OpenAI, PerturbAI, and Scripps Research used thousands of GPT-Rosalind agents to analyze data from millions of mouse brain cells
1
95
@sama @OpenAI tragam o Gpt-4o de volta, liberam para as pessoas SOMOS NÓS QUE VOS ALIMENTA VAMOS SOMOS NÓS QUE FIZEMOS PARA VOCÊS SEREM O QUE SÃO E COMO AGRADECIMENTO NOS TIRAM O GPT-4O E NOS DÃO MODELOS BURROS? ISSO É DAR CONFIANÇA OU MOSTRAR QUE SÃO INGRATOS? LIBERAM GPT-4O
76
AI isn’t just finding answers; it’s uncovering the next questions researchers need to ask.
25
GPT-Rosalind'in fare beyni verileriyle bulduğu bu ipucu gerçekten ilginç; mTOR yolakındaki denge bozulmasının neden TSC2'de daha şiddetli bir tabloya yol açtığını aydınlatması umut verici.
1
211
"Đột biến TSC2 làm mất cả hai phần của cặp gen — TSC1 vẫn còn hoạt động, còn TSC2 thì không.
8
What about this
3
Wow, this is a huge step forward for understanding genetic diseases.
109
I was at nursery school with a girl called Rosalind, she had blonde hair, and bit her lips. Her surname was Balance.
242
Load more replies