Quantitation in multianalyte overlapping peaks from capillary electrophoresis runs using artificial neural networks

Abstract

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.