Stanford ran a virtual biotech company staffed by 37,000 ai agents that worked through 50,000…
stanford ran a virtual biotech company staffed by 37,000 ai agents that worked through 50,000 clinical trials in under a week and flagged a signal: drugs targeting switch-like genes were 40 percent more likely to advance. the system also designed a lung cancer therapy that merck independently built and the fda later gave breakthrough designation.
the agents found the correlation, the humans had to prove it was real.
Context
A Stanford Medicine news page describes a virtual biotech company staffed by 37,000 AI agents. It says drugs targeting switch-like genes were 40% more likely to advance from phase 1 to phase 2, also 48% more likely to reach market and 32% fewer adverse events as written there, and that a private, well-established pharmaceutical company independently arrived at the same antibody-drug conjugate strategy against B7-H3 and then received FDA breakthrough therapy designation. The page says a paper was published on 17 September 2026 in Science, with Zou as senior author and Zhang as lead author.
This note is written from the Stanford institutional report only. The Science paper was not read, and a February 2026 bioRxiv preprint was seen in a snippet only. The note's 50,000 clinical trials in under a week was not found in the text searched, so it is unverified. The Stanford page does not name the pharmaceutical company, and naming it, such as Merck, has no supporting evidence on that page. The research claims are the team's own.
Related work
- Preprint (bioRxiv, 23 Feb 2026) ↗Snippet only.
Watch next
- The Science paper's own text.
Sources
- Virtual biotech company (Stanford Medicine news, Sep 2026)med.stanford.edu
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 22:02 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →