Curie Brief
Turn on cookies to sign in
Signing in saves your progress to your Curie account. We can only do that with cookies on — turn them on to continue.
NewsA KAUST-led team has developed Unify, an AI tool that maps cell similarities across vastly different species — from humans to worms — spanning over 700 million years of evolution. Unlike traditional tools that rely on direct gene matching, Unify compares gene functions, uncovering biological connections that were previously invisible. The result: better insight into which animal study findings actually apply to human health.
Scientists have long used animal models to understand human biology, but it hasn't always been clear which discoveries translate across species. A team at King Abdullah University of Science & Technology (KAUST) is changing that with Unify, an AI tool published in Nature Communications that maps cell-type similarities across species separated by more than 700 million years of evolution.
Traditional comparison tools rely on direct, one-to-one gene matches — a method that breaks down as species diverge. Unify takes a smarter approach: instead of matching genes by name, it compares what those genes do. Using AI models trained on protein sequences and gene function descriptions, Unify groups genes with similar roles into "macrogenes," allowing it to recognize functionally equivalent cells even when their underlying genetics look nothing alike.
By the Numbers
Why it matters: Knowing which animal findings carry over to humans helps researchers focus their efforts more efficiently — potentially accelerating discoveries in immunology, neuroscience, and beyond. The KAUST team is already expanding Unify to incorporate gene regulation and tissue-position data for an even richer biological picture.
