Automatic scent creation by cheminformatics method

Abstract

The sense of smell is fundamental for various aspects of human existence including the flavor perception, environmental awareness, and emotional impact. However, unlike other senses, it has not been digitized. Its digitalization faces challenges such as the lack of reliable odor sensing technology or the precise scent delivery through olfactory displays. Its subjective nature and context dependence add complexity to the process. Moreover, the method of converting odors to digital information remains unclear. This work focuses on one of the most challenging aspects of digital olfaction: automatic scent creation. We propose a method that automatically creates a desired odor profile with the addition of one specific odor descriptor. It is based on a deep neural network that predicts odor descriptors from the multidimensional sensing data, such as mass spectra and an odor reproduction technique using odor components. The results demonstrate that the proposed method can successfully create a scent with the desired odor profile and that its performance depends on the accuracy of the underlying odor predicting method. This opens up the possibility of automatic scent creation, allowing for the presentation of scents with specific odor profiles with an olfactory display.

Keywords: Cheminformatics; Deep neural network; Digital olfaction; Mass spectrometry; Odor prediction; Odor reproduction.

Fig. 1

Scheme depicting the procedure. In panel (a) the general scheme of the algorithm is shown. In panel (b) the algorithm’s different parts are detailed where represents the combination of odor components that make up the created scent and is the cost function to show the degree of matching. In panel (c) is the odor profile prediction algorithm and in panel (d) the odor component calculation.

Fig. 2

Odor Descriptors in the database. (a) Odor Descriptor frequency in the database (b) Distribution of the number of Odor Descriptors in each Essential Oils.

Fig. 3

Balance accuracy of every odor descriptor. The blue bars correspond to odor descriptors with balance accuracy above 0.5 and red below 0.5. The “All” odor descriptor is in black.

Fig. 4

Errors on the search algorithm when searching the odor descriptors of the odor components. (a) The odor component mixture obtained (b) errors on the odor descriptors obtained.