Published:Journal of Chromatographic Science,
ISSN 0021-9665Volume
39, Number 10, October 2001, pp. 145-150
Quantitation in Multianalyte Overlapping Peaks from Capillary
Electrophoresis Runs Using Artificial Neural Networks
S. Sentellas, J. Saurina*, S. Hernández-Cassou, M.T.
Galceran, and L. Puignou
Department of Analytical Chemistry, University of Barcelona, Diagonal 647,
E-08028, Barcelona, Spain
The potentiality of artificial neural networks
for multicomponent analysis in unresolved peaks from capillary electrophoresis
(CE) is evaluated. The system chosen consists of mixtures of three ebrotidine
metabolites, which cannot be successfully separated by CE. Data selected for
analysis consist of UV spectra taken at the maximum of the CE peak. The most
dissimilar analyte, in terms of spectral differences, is accurately quantitated
in any type of mixture with an overall prediction error of 5%. Because of the
strong interference of the two most overlapped compounds, a preliminary procedure
for spectral data filtering based on principal component analysis is performed
to improve their quantitation.
Reproduction
of editorial content of this journal is prohibited without publisher’s
permission.
This
article is available in its entirety by fax for $4.00 per
page.
Visa or MasterCard 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.
