Motional representation; the ability to predict odor characters using molecular vibrations
This work addresses the challenge of odor prediction in chemistry and sensory science, offering incremental insights into molecular motional features beyond structural shapes.
The study tackled the problem of predicting odor characters from molecular structure by exploring molecular vibrations as explanatory variables, finding that CNN-based and logistic regression models using vibrational parameters achieved predictability comparable to traditional fingerprint-based methods.
The prediction of odor characters is still impossible based on the odorant molecular structure. We designed a CNN-based regressor for computed parameters in molecular vibrations (CNN\_vib), in order to investigate the ability to predict odor characters of molecular vibrations. In this study, we explored following three approaches for the predictability; (i) CNN with molecular vibrational parameters, (ii) logistic regression based on vibrational spectra, and (iii) logistic regression with molecular fingerprint(FP). Our investigation demonstrates that both (i) and (ii) provide predictablity, and also that the vibrations as an explanatory variable (i and ii) and logistic regression with fingerprints (iii) show nearly identical tendencies. The predictabilities of (i) and (ii), depending on odor descriptors, are comparable to those of (iii). Our research shows that odor is predictable by odorant molecular vibration as well as their shapes alone. Our findings provide insight into the representation of molecular motional features beyond molecular structures.