Linear and nonlinear quantitative structure linear retention indices relationship models for essential oils

Abstract

Genetic algorithm and multiple linear regression (GA-MLR), partial least square (GA-PLS) and
kernel PLS (GA-KPLS) techniques were used to investigate the correlation between linear retention
indices (LRI) and descriptors for 101 diverse compounds in essential oils of six Stachys species
which obtained by gas chromatography/electron impact mass spectrum (GC-EIMS). The correlation
coefficient LGO-CV (Q2
) between experimental and predicted LRI for training and test sets by GAMLR, GA-PLS and GA-KPLS was 0.936, 0.942 and 0.967 (for 80 compounds), 0.860, 0.871 and
0.919 (for 21 compounds), respectively. This indicates that GA-KPLS can be used as an alternative
modeling tool for quantitative structure–retention relationship (QSRR) studies.