Published:Journal of Chromatographic Science,
ISSN 0021-9665 Volume
47, Number 5, May/June 2009, pp. 396-404
Quantitative Structure-Retention Relationship
Models for the Prediction of the Reversed-Phase HPLC Gradient
Retention Based on the Heuristic Method and Support Vector Machine
Hongying Du, Jie Wang, Xiaojun Yao, and Zhide
Hu
Department of Chemistry, Lanzhou University, Lanzhou 730000,
China
The heuristic method (HM) and support vector machine
(SVM) were used to construct quantitative structure–retention
relationship models by a series of compounds to predict the gradient
retention times of reversed-phase high-performance liquid chromatography
(HPLC) in three different columns. The aims of this investigation
were to predict the retention times of multifarious compounds,
to find the main properties of the three columns, and to indicate
the theory of separation procedures. In our method, we correlated
the retention times of many diverse structural analytes in three
columns (Symmetry C18, Chromolith, and SG-MIX) with their representative
molecular descriptors, calculated from the molecular structures
alone. HM was used to select the most important molecular descriptors
and build linear regression models. Furthermore, non-linear regression
models were built using the SVM method; the performance of the
SVM models were better than that of the HM models, and the prediction
results were in good agreement with the experimental values.
This paper could give some insights into the factors that were
likely to govern the gradient retention process of the three
investigated HPLC columns, which could theoretically supervise
the practical experiment.
Reproduction
of editorial content of this journal is prohibited without publisher’s
permission.
This
article is available in its entirety by fax for $40.00.
Visa, MasterCard & Amex accepted.
To
order electronicallyclick here or call: 847-647-2900 ext. 1323 or fax request to: 847-647-1155.
Please
indicate JCS volume and issue along with
page numbers.
For permission to reuse material from Journal of Chromatographic Science, please access www.copyright.com or contact the Copyright Clearance Center, Inc. (CCC), 222 Rosewood Drive, Danvers, MA 01923, 978-750-8400. CCC is a not-for-profit organization that provides licenses and registration for a variety of uses.
