Biomedical research produces a flood of information that no scientist can realistically absorb. At the University of Edinburgh, bioengineer Filippo Menolascina is using Co-Scientist to comb the literature for overlooked links and generate new hypotheses.

His team focused on a common liver disease called metabolic dysfunction‑associated steatohepatitis (MASH). Developing treatments is challenging because MASH involves intertwined biological processes, including liver inflammation and metabolism, meaning single‑target drugs fall short. That pushes researchers toward combination treatments, but the number of potential drug pairings is overwhelming.

Faced with that combinatorial explosion, Menolascina used Co‑Scientist to narrow the search. In his hands, Co‑Scientist synthesised evidence across liver biology and pharmacology, highlighted mechanisms worth focusing on, and flagged candidate combination therapies that his team could test.

In one emblematic case, Co‑Scientist tackled a live, practical question: Why does the drug resmetirom – a recently approved treatment prescribed for a specific stage of MASH – only help a narrow slice of those eligible patients? The system produced a hypothesis pinpointing the NLRP3 inflammasome as the specific molecular bridge coupling inflammation and metabolism in the disease — a connection never previously pulled together into a single, actionable explanation. The hypothesis, later experimentally verified, could pave the way for targeted dual-therapies.