To make sense of this baffling chemistry, researchers have turned to the computational might of artificial intelligence. Now one team has trained a type of AI known as a graph neural network to predict what a compound will smell like to a person—rose, medicinal, earthy, and so on—based on the chemical features of odor molecules. The computer model assessed new scents as reliably as humans, the researchers report in a new draft paper posted to the preprint repository bioRxiv.

— Read more in AI Predicts What Chemicals Will Smell like to a Human at Scientific American.

A Scottish woman named Joy Milne made headlines in 2015 for an unusual talent: her ability to sniff out people afflicted with Parkinson’s disease, a progressive neurodegenerative illness that is estimated to affect nearly a million people in the U.S. alone. Since then a group of scientists in the U.K. has been working with Milne to pinpoint the molecules that give Parkinson’s its distinct olfactory signature. The team has now zeroed in on a set of molecules specific to the disease—and has created a simple skin-swab-based test to detect them.

— Read more in A Supersmeller Can Detect the Scent of Parkinson’s, Leading to an Experimental Test for the Illness at Scientific American.

And that presents quite the neuroscientific mystery: how can each randomly located, odor-detecting cell in the nose manage to send signals to just one specific glomerulus within the olfactory bulb? This feat is akin to, say, 50 friends who are originally separated in random places in a city making their way to the same apartment without initially having the address. Somehow they inherently all know where to go.

— Read more in Mental Landscapes: The Neural Cartography of Smell at Columbia's Zuckerman Institute.