May 19, 2026 ScienceOpening new paths in aging research ShareFew problems in medicine are more complex or consequential than aging. Its overlapping biological processes often determine how long people can live in good health. At Calico Life Sciences, head of AI/ML Matt Onsum and principal scientist Katherine Labbé are using Co‑Scientist to help connect scattered findings across the biology of aging and turn them into hypotheses worth testing.That is no small task, because the biology literature is full of mixed-quality findings, dead ends, and results that do not replicate. Onsum says Co-Scientist impressed Calico’s experts with its scientific discernment, helping cut through that noise to help them identify new ideas genuinely worth exploring.One example came from Calico’s work on the integrated stress response (ISR), a protective cellular mechanism that can also contribute to disease when persistently turned on. The Calico team used Co-Scientist to generate a novel yet plausible hypothesis about how the ISR is regulated by metabolism, which is known to change with age and in various diseases. Researchers also interacted with Co-Scientist to refine the experimental design to test the hypothesis and feed in new information as results emerged. The experiments led to new findings that have important implications for the role of ISR in health and disease and the team plans to publish the results.Slide 1 of 2What 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. 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. Dr Matt Onsum, Head of AI/ML Calico Life Sciences Related postsCo-Scientist: A multi-agent AI partner to accelerate researchMay 2026Science Learn more Uncovering repurposed medicines to fight liver fibrosisMay 2026Science Learn more Uniting biological toolkits for a new approach to ALSMay 2026Science Learn more Accelerating discovery of liver disease mechanismsMay 2026Science Learn more Finding the molecular switches behind new infectious diseasesMay 2026Science Learn more Fast-tracking genetic leads to reverse cellular agingMay 2026Science Learn more
Co-Scientist
Untangling the mysteries of aging
Related
ResearchLearning When to Trust via Selective Context Preference Optimization
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchmark that renders each reasoning item under four matched conditions (clean, misleading, correct-context, and irrelevant-context), together with SC2W, a paired metric counting how often a misle
Learning When to Trust via Selective Context Preference Optimization
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, tr...
ResearchTracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language model (LLM)-based approaches offer only partial automation with limited maintainability and evidence traceability. We developed the Nimblemind Multi-Agent System (nMAS), an evidence-linked, rubr