Prediction of Chiral Chromatographic Separations Using Combined Multivariate Regression and Neural Networks
- 1 October 1997
- journal article
- research article
- Published by American Chemical Society (ACS) in Analytical Chemistry
- Vol. 69 (19) , 3879-3883
- https://doi.org/10.1021/ac9702150
Abstract
A new method for the prediction and description of enantioselective separations on HPLC chiral stationary phases (CSPs) is described. Based on the combination of multivariate regression and neural networks, the method was successfully applied to the separation of a series of 29 aromatic acids and amides, chromatographed on three amylosic CSPs. Combinations of charge transfer, electrostatic, lipophilic, and dipole interactions, identified by multivariate regression, were found to describe retention and enantioselectivity, with highly predictive models being generated by the training of back-propagation neural networks.Keywords
This publication has 20 references indexed in Scilit:
- Neural networks: A new method for solving chemical problems or just a passing phase?Published by Elsevier ,2002
- Mechanistic investigation into the enantioselective separation of mexiletine and related compounds, chromatographed on an amylose tris(3,5-dimethylphenylcarbamate) chiral stationary phaseJournal of Chromatography A, 1996
- Separation of Benzodioxinic Isomers in LC. A Molecular Modeling Approach for the Choice of the Stationary PhaseJournal of Liquid Chromatography, 1995
- Enantiomeric resolution of sulfoxides on a DACH‐DNB chiral stationary phase: A quantitative structure–enantioselective retention relationship (QSERR) studyChirality, 1993
- Mechanism of retention of benzodiazepines in affinity, reversed-phase and adsorption high-performance liquid chromatography in view of quantitative structure retention relationshipsJournal of Chromatography A, 1992
- Counter-propagation neural networks in the modeling and prediction of Kovats indexes for substituted phenolsAnalytical Chemistry, 1992
- Estimating and representing hydrophobicity potentialJournal of Molecular Graphics, 1988
- Quantitative correlation between calculated molecular properties and retention of a series of structurally related racemates on cellulose triacetateJournal of the Chemical Society, Perkin Transactions 2, 1988
- Resolution of enantiomeric amides on a cellulose-based chiral stationary phaseJournal of Chromatography A, 1986
- Solvent-Accessible Surfaces of Proteins and Nucleic AcidsScience, 1983