AI co-scientist hypotheses on antimicrobial resistance and liver fibrosis
A multi-agent system generated hypotheses that were subsequently validated experimentally in the lab.
- Lab
- Model
- AI Co-Scientist (Gemini 2.0 multi-agent)
- Field
- Biology
- Date
- 2025-02-19
What was found
The system proposed mechanisms in antimicrobial resistance and liver fibrosis that wet-lab work then supported. Notable as one of the earliest cases of an AI-generated hypothesis surviving experimental test rather than just sounding plausible. The peer-reviewed version, published in Nature in May 2026, covers three biomedical applications together: drug repurposing, novel-target discovery and explaining mechanisms of antimicrobial resistance. It adds drug-repurposing candidates and synergistic combination therapies for acute myeloid leukaemia that were then validated in vitro.
Novelty check
The AMR mechanism proposed had already been established experimentally, but not published, by the paper's own senior authors at Imperial College London, who posed the question to the system because they knew the answer: the published Cell version states that its top-ranked hypothesis matched their confirmed mechanism, in which capsid-forming phage-inducible chromosomal islands hijack diverse phage tails. That makes the AMR result a test of rediscovery against a held-out answer rather than a new mechanism, which complicates the novelty claim.
Caveats and known objections
Hypothesis generation with human-run validation, not autonomous discovery. Peer review confirms the work, not that every hypothesis in it was unprecedented, and the novelty question above is untouched by publication. Independent replication outside the collaborating labs is limited. Graded conservatively.
Nobody outside the lab has checked this yet.
Reading the primary source closely enough to say whether it supports the claim counts as a check, and you are credited on the entry.
Or on GitHub: submit a check challenge the grade send a correction or send a pull request
Flag this for triage
Signals order the review queue and nothing else. They are never published, and they never move a grade: that takes a citation.
History of this entry
- CorrectedCited the peer-reviewed Cell version of the antimicrobial resistance study and corrected the novelty check: the human group that had already found the mechanism was the paper's own authors. No grade moved. source ↗
- RegradedUpgraded from author verified to peer reviewed: the work was published in Nature (655, 487-496) on 19 May 2026, covering drug repurposing, novel-target discovery and antimicrobial resistance mechanisms together. source ↗
- AddedEntered the registry graded Peer reviewed and AI-assisted.
Entries are never deleted. A grade that does not hold up is downgraded on the record, with the reason beside it.
Graded peer reviewed for verification and ai-assisted for autonomy. What these mean.
Cite this entry
whataifound.org. (2025). AI co-scientist hypotheses on antimicrobial resistance and liver fibrosis. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2025-02-ai-coscientist-amrBibTeX
@misc{whataifound-google-2025-amr,
title = {AI co-scientist hypotheses on antimicrobial resistance and liver fibrosis},
author = {{whataifound.org}},
year = {2025},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by Google. Verification: Peer reviewed. Autonomy: AI-assisted.},
url = {https://whataifound.org/finding/2025-02-ai-coscientist-amr}
}