Robin was published in Nature today.
Robin is the first multi-agent system for discovery in biology that integrates novel hypothesis generation with experimental data analysis in one continuous workflow. In this study, our team applied Robin to dry age-related macular degeneration, a leading cause of irreversible sight loss with limited treatment options. The system proposed drug-repurposing hypotheses, which were then tested experimentally in the lab.
Robin developed the experimental strategy for therapeutic hypothesis generation, proposed follow-up experiments, and extracted actionable insights from the resulting data, including validation in primary human retinal pigment epithelium (RPE) stem cells.
Robin proposed a mechanism of enhancing RPE phagocytosis by modulating the cells’ circadian rhythm using an experimental drug, KL001, that has never before been used in humans or proposed for AMD. To our knowledge, this mechanism had not previously been proposed.
This work lays the foundation for how scientists can effectively leverage AI through AI-automated workflows. Agents working in parallel across a worlflow perform research tasks at a scale impossible for humans working alone. Beyond the benefits of higher throughput, they connect insights across disciplines, provide novel insights, and turn existing knowlegde into testable hypotheses.
Read the full paper in Nature.
