eCite Digital Repository

Performance comparison of partial least squares-related variable selection methods for quantitative structure retention relationships modelling of retention times in reversed-phase liquid chromatography

Citation

Talebi, M and Schuster, G and Shellie, RA and Szucs, R and Haddad, PR, Performance comparison of partial least squares-related variable selection methods for quantitative structure retention relationships modelling of retention times in reversed-phase liquid chromatography, Journal of Chromatography A, 1424 pp. 69-76. ISSN 0021-9673 (2015) [Refereed Article]

Copyright Statement

Copyright 2015 Elsevier B.V.

DOI: doi:10.1016/j.chroma.2015.10.099

Abstract

The relative performance of six multivariate data analysis methods derived from or combined with partial least squares (PLS) has been compared in the context of quantitative structure–retention relationships (QSRR). These methods include, GA (genetic algorithm)-PLS, Monte Carlo uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), iteratively retaining informative variables (IRIV), variable iterative space shrinkage approach (VISSA) and PLS with automated backward selection of predictors (autoPLS). A set of 825 molecular descriptors was computed for 86 suspected sports doping compounds and used for predicting their gradient retention times in reversed-phase liquid chromatography (RPLC). The correlation between molecular descriptors selected by each technique and the retention time was established using the PLS method. All models derived from a selected subset of descriptors outperformed the reference PLS model derived from all descriptors, with very small demands of computational time and effort. A performance comparison indicated great diversity of these methods in selecting the most relevant molecular descriptors, ranging from 28 for CARS to 263 for MC-UVE. While VISSA provided the lowest degree of over-fitting for the training set, CARS demonstrated the best compromise between the prediction accuracy and the number of selected descriptors, with the prediction error of as low as 46 s for the external test set. Only ten descriptors were found to be common for all models, with the characteristics of these descriptors being representative of the retention mechanism in RPLC.

Item Details

Item Type:Refereed Article
Keywords:QSRR, partial least squares (PLS), genetic algorithm (GA), molecular descriptors, RPLC, retention time prediction
Research Division:Chemical Sciences
Research Group:Analytical Chemistry
Research Field:Separation Science
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in the Chemical Sciences
Author:Talebi, M (Dr Mohammad Talebi)
Author:Schuster, G (Dr Georg Schuster)
Author:Shellie, RA (Associate Professor Robert Shellie)
Author:Haddad, PR (Professor Paul Haddad)
ID Code:105914
Year Published:2015
Web of Science® Times Cited:7
Deposited By:Austn Centre for Research in Separation Science
Deposited On:2016-01-20
Last Modified:2016-05-17
Downloads:0

Repository Staff Only: item control page