Scientists from the Tokyo Institute of Technology have introduced a machine learning model for predicting sensing data to produce desired odor or fragrance
The researchers developed an approach of machine learning model analyzing sensing data i.e. the mass spectra of odor mixtures. The linear combination of the mass spectra of single components is used for the above analysis. This process enables for quick preparation of the predicted spectra of odor mixtures, it can also predict the required mixing ratio that is very essential for the recipe of new odor preparation.”We used a machine-learning-based odor predictive model that we had previously developed to obtain the odor impression. Then we predicted the mass spectrum from odor impression inversely based on the previously developed forward model,” explains Professor Takamichi Nakamoto, the leader of the research effort by Tokyo Tech. The findings have been published in PLoS One.
The methods available presently can only predict olfactory impressions from the physiochemical attributes of odorants which are not useful in creating smells. Hence, researchers developed the novel approach of predicting molecular features based on odor impression instead of inverse, i.e., predicting the smell from molecular data. “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.
Smell has been the most essential type of sensation to animals and humans to trace food, water, or detect danger. Humans have olfactory receptors for smell sensation that are processed by olfactory nerve cells. The industries can benefit from using the above prediction model to generate different types of odors and fragrances in manufacturing their products to attract customers. This approach furnishes highly accurate predictions of the physiochemical properties of odor mixtures with mixing ratios to prepare them, allowing us to produce our desired fragrances and odors.
Click here for the Published Research Paper
