Data based predictive models for odor perception

Abstract

Machine learning and data analytics are being increasingly used for quantitative structure property relation (QSPR) applications in the chemical domain where the traditional Edisonian approach towards knowledge-discovery have not been fruitful. The perception of odorant stimuli is one such application as olfaction is the least understood among all the other senses. In this study, we employ machine learning based algorithms and data analytics to address the efficacy of using a data-driven approach to predict the perceptual attributes of an odorant namely the odorant characters (OC) of “sweet” and “musky”. We first analyze a psychophysical dataset containing perceptual ratings of 55 subjects to reveal patterns in the ratings given by subjects. We then use the data to train several machine learning algorithms such as random forest, gradient boosting and support vector machine for prediction of the odor characters and report the structural features correlating well with the odor characters based on the optimal model. Furthermore, we analyze the impact of the data quality on the performance of the models by comparing the semantic descriptors generally associated with a given odorant to its perception by majority of the subjects. The study presents a methodology for developing models for odor perception and provides insights on the perception of odorants by untrained human subjects and the effect of the inherent bias in the perception data on the model performance. The models and methodology developed here could be used for predicting odor characters of new odorants.

KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks

“…Based on this dataset, Chacko et al used machine learning to predict these perceptual characteristics from an odor molecule based on its structural properties. We applied our models to the same dataset, and we found that our KCNet models outperform the other data-driven approaches, such as XGBoost, that were used by Chacko et al [14].…”

“…Chacko et al [14] focused on a specialized form of the odorant perception task where odors could be classified by the presence or absence of two particular subjective properties referred to as Sweet and Musky. They used a psychophysical dataset including odor perception ratings of 55 human subjects.…”

Bitter Taste and Olfactory Receptors: Beyond Chemical Sensing in the Tongue and the Nose

“…As in the case of bitter tastants, machine learning approaches have also been developed for odorants (Lötsch et al 2019 ). These algorithms aim at predicting either new ligand-receptor pairs (Liu et al 2011 ; Audouze et al 2014 ; Bushdid et al 2018 ; Caballero-Vidal et al 2020 ; Cong et al 2020 ) or smells (Keller et al 2017 ; Poivet et al 2018 ; Nozaki and Nakamoto 2018 ; Chacko et al 2020 ; Sharma et al 2021 ), based on chemical features of the odorants.…”

A machine learning based analysis to probe the relationship between odorant structure and olfactory behaviour inC. elegans

“…With research on vision being aided by machine learning approaches, there is now an interest in applying computational techniques to olfaction research as well, both in human and animal studies. There have been efforts to construct an odorant chemical space and connect it to the resulting subjective experience of smell [20] through deep learning [21, 22] and supervised machine learning [23] approaches using data from human subjects. Alternatively, there is also an interest in learning the organisation of olfactory systems to make better deep and machine learning algorithms as opposed to the pre-existing ones that derive inspiration from the organisation of visual processing systems.…”