PLS regression-based chemometric modeling of odorant properties of diverse chemical constituents of black tea and coffee

Abstract

Tea and coffee are the most attractive non-alcoholic beverages used worldwide due to the odorant properties of diverse components present in these beverages. The aim of this work is to investigate the key structural features which regulate the odorant properties of constituents present in black tea and coffee using regression-based chemometric models. We have also investigated the key structural properties which create the odor difference between tea and coffee. We have employed different variable selection strategies to extract the most relevant variables prior to development of final partial least squares (PLS) models. The models were extensively validated using different validation metrics, and the results justify the reliability and usefulness of the developed predictive PLS models. The best PLS model captured the necessary structural information on relative hydrophobic surface area, heteroatoms with higher number of multiple bonds, hydrogen atoms connected to C³(sp³)/C²(sp²)/C³(sp²)/C³(sp) fragments, electron-richness, C-O atom pairs at the topological distance 10 and surface weighted charged partial negative surface areas for explaining the odorant properties of the constituents present in black tea. On the other hand, C-S atom pairs at the topological distance 1, C-C atom pairs at the topological distance 5, donor atoms like N and O for hydrogen bonds, hydrogen atoms connected to C³(sp³)/C²(sp²)/C³(sp²)/C³(sp) fragments and R-CX-X fragments (where, R represents any group linked through carbon and X represents any heteroatom (O, N, S, P, Se, and halogens)) are the key structural components captured by the PLS model developed from the constituents present in coffee. The developed models can thus be successfully utilized for in silico prediction of odorant properties of diverse classes of compounds and exploration of the structural information which creates the odor difference between black tea and coffee.

Fig. 1. Schematic representation of the steps involved in the development of final PLS models.

Fig. 2. The PLS model developed from the constituents present in black tea: (A) the scatter plot of the observed and the predicted values of odorant property [log(1/OT)] for the final PLS model. The dashed line indicates the best fit line based on test set compounds and the solid line indicates the best fit line based on the training set compounds. (B) The PLS score plot of the training set compounds using the developed PLS model. (C) The loading plot of the model descriptors and dependent variable (log(1/OT)).

Fig. 3. The PLS model developed from the constituents present in coffee: (A) the scatter plot of the observed and the predicted values of odorant property [log(1/OT)] for the final PLS model. The dashed line indicates the best fit line based on test set compounds and the solid line indicates the best fit line based on the training set compounds. (B) The PLS score plot of the training set compounds using the developed PLS model. (C) The loading plot of the model descriptors and dependent variable (log(1/OT)).