Partial least squares discriminate analysis (PLS-DA) [20] is a
partial least squares regression aimed at predicting one (or several)
binary responses(s) y from a set of variables in X. Thus, PLS-DA
needs the class-variable of the objects and produced scores that
not only retain maximal variances of the original variables but also
are correlated with the class-variable. PLS-DA implements a compromise
between the usual discriminant analysis and a discriminant
analysis on the significant principal components of the
descriptor variables.