A consideration for structure-taste correlations of perillartines using pattern-recognition techniques

Publisher Website
Google Scholar
Abstract
The relationships between molecular structure and taste quality (sweet or bitter) [to humans] or several perillartine derivatives were investigated using pattern-recognition techniques. For the classification of these compounds into 2 classes (sweet or bitter), a significant discriminant function was developed by the use of linear learning machine. All the compounds were assigned correctly to their observed taste classes by the function involving 3 parameters (1 hydrophobic and 2 steric). The K-L [Karhunen-Loeve] transformation technique was used for examination of classification results.