Tokyo: One of the most basic senses of animal species is the sense of smell. It helps in finding food, recognising attractiveness, and detecting danger.
Humans detect odorants using olfactory receptors found in olfactory nerve cells. These odorant sensory impressions have their molecular and physicochemical properties which enables us to tailor scents and generate the desired odor impression.
Current approaches can only predict olfactory perceptions based on odorant physicochemical properties. However, it cannot forecast sensing data, required for producing odors. To tackle this issue, scientists from Tokyo Institute of Technology (Tokyo Tech) have developed an innovative strategy to solve the inverse problem.
Instead of predicting the smell from molecular data, this method predicts molecular features based on the odor impression.
Professor Takamichi Nakamoto, the leader of the research effort by Tokyo Tech explains, “The method allows for the quick preparation of the predicted spectra of odor mixtures and can also predict the required mixing ratio, an important part of the recipe for new odor preparation. “For example, we show which molecules give the mass spectrum of apple flavor with enhanced ‘fruit’ and ‘sweet’ impressions.
“Our analysis method shows that combinations of either 59 or 60 molecules give the same mass spectrum as the one obtained from the specified odor impression. With this information, and the correct mixing ratio needed for a certain impression, we could theoretically prepare the desired scent,” highlights Prof. Nakamoto.
He further adds,” We used a machine-learning-based odor predictive model that we had previously developed to obtain the odor impression.” This is achieved using standard mass spectrum data and machine learning (ML) models.
This novel method described in this study can provide highly accurate predictions of the physicochemical properties of odor mixtures, as well as the mixing ratios required to prepare them, thereby opening the door to endless tailor-made fragrances.