Preprocessing of HPLC Trace Impurity Patterns by Wavelet Packets for Pharmaceutical Fingerprinting Using Artificial Neural Networks

Abstract

The immediate objective of this research program is to evaluate several computer-based classifiers as potential tools for pharmaceutical fingerprinting based on analysis of HPLC trace organic impurity patterns. In the present study, wavelet packets (WPs) are investigated for use as a preprocessor of the chromatographic data taken from commercial samples of L-tryptophan (LT) to extract input data appropriate for classifying the samples according to manufacturer using artificial neural networks (ANNs) and the standard classifiers KNN and SIMCA. Using the Haar function, WP decompositions for levels L = 0-10 were generated for the trace impurity patterns of 253 chromatograms corresponding to LT samples that had been produced by six commercial manufacturers. Input sets of N = 20, 30, 40, and 50 inputs were constructed, each one consisting of the first N/2 WP coefficents and corresponding positions from the overall best level (L = 2). The number of hidden nodes in the ANNs was also varied to optimize performance. Optimal ANN performance based on percent correct classifications of test set data was achieved by ANN-30-30-6 (97%) and ANN-20-10-6 (94%), where the integers refer to the numbers of input, hidden, and output nodes, respectively. This performance equals or exceeds that obtained previously (Welsh, W.J.; et al.Anal.Chem. 1996, 68, 3473) using 46 inputs from a so-called Window preprocessor (93%). KNN performance with 20 inputs (97%) or 30 inputs (90%) from the WP preprocessor also exceeded that obtained from the Window preprocessor (85%), while SIMCA performance with 20 inputs (86%) or 30 inputs (82%) from the WP preprocessor was slightly inferior to that obtained from the Window preprocessor (87%). These results indicate that, at least for the ANN and KNN classifiers considered here, the WP preprocessor can yield superior performance and with fewer inputs compared to the Window preprocessor.

Improvements in pentosan polysulfate sodium quality assurance using fingerprint electropherograms

“…All relevant changes in the PPS structure could also be modeled by the computational easy KNN algorithm. This algorithm tries to classify objects even if they are far away from the training data, which must be taken into account while analyzing KNN results [34]. SIMCA is a powerful algorithm if a sufficient amount of principal components can be used for the calculation of the class model.…”

Fingerprint analysis of Flos Lonicerae japonicae using binary HPLC profiling

“…Chemical pattern recognition methods have been employed for definition of the class of herbal medicines (Collantes et al, 1997;Luo et al, 1993). The classification of Flos Lonicerae japonicae derived from six species was carried out using hierarchical clustering analysis in our study.…”

Quality control of herbal medicines

“…Thus, the chemical pattern recognition methods, such as K-nearest neighbors (KNN) [190,192] and soft independent modeling of class analogy (SIMCA) [193], etc. should be taken into consideration for reasonable definition of the class of the herbal medicine [194][195][196]. In fact, several researchers in China had worked on the concepts of using chemical analytical and chromatographical fingerprinting to measure the consistency of raw Chinese medicinal herbs and composite formula with the application of fuzzy clustering analysis of HPLC pattern in the early 1990s [225].…”