Reproduce “Robin: A multi-agent system for automating scientific discovery” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ali Essam Ghareeb, Benjamin Chang, Ludovico Mitchener, Angela Yiu, Caralyn J. Szostkiewicz, Jon M. Laurent, Muhammed T. Razzak, Andrew D. White and 2 more
Robin connects literature synthesis, hypothesis generation, researcher-run experiments, and AI analysis into an iterative workflow for dry age-related macular degeneration. It proposed testing retinal pigment epithelium phagocytosis and refined candidates using assay feedback. In ARPE-19 cells, Finch ranked ripasudil highest, estimating 7.5-fold versus DMSO, while human reanalysis found 1.75-fold; dose and time-course tests remain needed.
Key insights
- ROCK inhibitors like ripasudil can enhance RPE cell phagocytosis, suggesting therapeutic potential for dAMD
- Automated RNA-seq analysis revealed ABCA1 upregulation as a novel molecular target
- Multi-agent systems can effectively automate multiple stages of scientific discovery process
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.