Quantitative structure-retention relationships analysis of retention index of essential oils

Genetic algorithm and multiple linear regression (GA-MLR), partial least square (GA-PLS), kernel PLS (GA-KPLS) and Levenberg-Marquardt artificial neural network (L-M ANN) techniques were used to investigate the correlation between retention index (RI) and descriptors for 116 diverse compounds in ess...

Full description

Saved in:
Bibliographic Details
Published in:Química Nova 2011, Vol.34 (2), p.242-249
Main Authors: Noorizadeh, Hadi, Farmany, Abbas, Noorizadeh, Mehrab
Format: Article
Language:English
Subjects:
CHEMISTRY, MULTIDISCIPLINARY
essential oils
genetic algorithm-kernel partial least squares
Levenberg-Marquardt artificial neural network
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Genetic algorithm and multiple linear regression (GA-MLR), partial least square (GA-PLS), kernel PLS (GA-KPLS) and Levenberg-Marquardt artificial neural network (L-M ANN) techniques were used to investigate the correlation between retention index (RI) and descriptors for 116 diverse compounds in essential oils of six Stachys species. The correlation coefficient LGO-CV (Q²) between experimental and predicted RI for test set by GA-MLR, GA-PLS, GA-KPLS and L-M ANN was 0.886, 0.912, 0.937 and 0.964, respectively. This is the first research on the QSRR of the essential oil compounds against the RI using the GA-KPLS and L-M ANN.
ISSN:0100-4042
1678-7064
DOI:10.1590/S0100-40422011000200014