Candidate treatment for dry age-related macular degeneration
The Robin system automated hypothesis generation, experiment design and data analysis, identifying a novel candidate treatment for dry AMD.
- Lab
- FutureHouse
- Model
- Robin (multi-agent)
- Field
- Biology
- Date
- 2025-05-01
Sources
Original work
Media coverage
What was found
Presented as an end-to-end automated discovery loop with humans executing the physical experiments. Robin proposed enhancing retinal pigment epithelium phagocytosis as a therapeutic strategy, then identified ripasudil and KL001 as candidates and confirmed in vitro efficacy for both. It went on to propose and analyse a follow-up RNA sequencing experiment, which showed upregulation of ABCA1, a lipid efflux pump and a possible novel target in its own right. Published in Nature in May 2026.
Novelty check
Ripasudil is a clinically used Rho kinase inhibitor; the paper states that to the authors' knowledge it had never previously been proposed for the treatment of dry age-related macular degeneration, and the peer-reviewed version carries that claim. The ABCA1 mechanism emerged from the system's own follow-up experiment rather than from the prior literature. What is new is the repurposing hypothesis and its in vitro support, not a new compound.
Caveats and known objections
Peer reviewed, which is the right grade for an empirical claim of this kind, but in vitro efficacy is a long way from a treatment: a candidate is many years and several trial phases from the clinic. Verification of the biology is the journal's, not an independent replication. Autonomy stays ai-led rather than autonomous: the paper describes the approach as semi-autonomous, and humans executed every physical experiment, though all hypotheses, experimental directions, data analyses and main-text figures were produced by Robin.
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
- RegradedUpgraded from claimed to peer reviewed: the work was published in Nature (655, 497-505) on 19 May 2026, which also supplies the primary source the entry previously lacked. source ↗
- AddedEntered the registry graded Peer reviewed and AI-led.
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-led for autonomy. What these mean.
Cite this entry
whataifound.org. (2025). Candidate treatment for dry age-related macular degeneration. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2025-robin-macularBibTeX
@misc{whataifound-futurehouse-2025-macular,
title = {Candidate treatment for dry age-related macular degeneration},
author = {{whataifound.org}},
year = {2025},
howpublished = {whataifound.org: A Registry of AI Scientific and Mathematical Discoveries},
note = {Result by FutureHouse. Verification: Peer reviewed. Autonomy: AI-led.},
url = {https://whataifound.org/finding/2025-robin-macular}
}