A new artificial intelligence system is capable of analyzing the molecular make-up of a compound and then predicting how it will smell. According to the researchers, the descriptions the AI generates are similar in language and often more precise than humans. Eventually, the scientists from Google Research and the spinoff start-up Osmo believe the system could deepen our understanding of how the brain processes odors. It could also lead to the design of new kinds of scents for commercial products. From Nature:
To explore the association between a chemical's structure and its odour, [neurobiologist Alexander] Wiltschko and his team at Osmo designed a type of artificial intelligence (AI) system called a neural network that can assign one or more of 55 descriptive words, such as fishy or winey, to an odorant. The team directed the AI to describe the aroma of roughly 5,000 odorants. The AI also analysed each odorant's chemical structure to determine the relationship between structure and aroma.
The system identified around 250 correlations between specific patterns in a chemical's structure with a particular smell. The researchers combined these correlations into a principal odour map (POM) that the AI could consult when asked to predict a new molecule's scent[…]
The AI's guess tended to be very close to the average response given by the humans — often closer than any individual's guess.
Here's the paper describing the research: "A principal odor map unifies diverse tasks in olfactory perception" (Science)