Opening new paths in aging research – Google DeepMind and Calico use Co‑Scientist to generate hypotheses
Opening new paths in aging research – Google DeepMind and Calico use Co‑Scientist to generate hypotheses
Opening new paths in aging research
TL;DR
Google DeepMind announced that Calico Life Sciences used its Co‑Scientist multi‑agent AI system to generate and test a novel hypothesis about the integrated stress response in aging, showing how AI can accelerate biomedical discovery.
What Co‑Scientist is and how Calico applied it
Co‑Scientist helps researchers connect scattered findings and turn them into hypotheses worth testing. At Calico Life Sciences, head of AI/ML Matt Onsum and principal scientist Katherine Labbé employed Co‑Scientist to sift through the noisy biology literature on aging and identify promising ideas.
Generating a hypothesis on the integrated stress response
The team focused on the integrated stress response (ISR), a protective cellular mechanism that can contribute to disease when chronically activated. Using Co‑Scientist, they produced a novel yet plausible hypothesis describing how the ISR is regulated by metabolism, which changes with age and in various diseases.
Refining the experiment and obtaining results
Researchers interacted with Co‑Scientist to shape the experimental design to test the hypothesis, feeding in new data as results emerged. The ensuing experiments yielded new findings that have important implications for the role of ISR in health and disease, and the team intends to publish these results.
Expert perspectives on the collaboration
"What I found both exciting and surprising about using Co-Scientist is how much it thinks like a scientist. It really works naturally with how a scientist already thinks and behaves."\n> — Dr Katherine Labbé, Principal Scientist, Calico Life Sciences
"Seeing how Co-Scientist helps us integrate all the information we have around us to better untangle the mysteries of aging — that's about as big of a moonshot as I can think of."\n> — Dr Matt Onsum, Head of AI/ML, Calico Life Sciences
Implications for aging research
The use of Co‑Scientist demonstrates that AI can cut through low‑quality and non‑reproducible literature to surface testable ideas, thereby accelerating the pace of discovery in complex fields such as aging biology. The ISR‑metabolism hypothesis exemplifies how AI‑generated insights can lead to concrete experimental work and future publications.
Related DeepMind announcements
The blog post links to other May 2026 Science updates, including the Co‑Scientist announcement itself and studies on repurposed medicines for liver fibrosis, ALS toolkits, liver disease mechanisms, infectious disease switches, and genetic leads for reversing cellular aging.