Variable selection for discriminating herbal medicines with chromatographic fingerprints.

When discriminating herbal medicines with pattern recognition based on chromatographic fingerprints, typically, the majority of variables/data points contain no discrimination information. In this paper, chemometric approaches concerning forward selection and key set factor analysis using principal component analysis (PCA), unweighted and weighted methods based on the inner- and outer-variances, Fisher coefficient from the between- and within-class variations were investigated to extract representative variables. The number of variables retained was determined based on the cumulative variance percent of principal components, the ratio of observations to variables and the factor indicative function (IND). In order to assess the methods for variable selection and criteria levels to determine the number of variables retained, the original and reduced datasets were compared with Procrustes analysis and a weighted measure of similarity. Moreover, the tri-variate plots of the first three PCA scores were used to visually examine the reduced datasets in low dimensional space. Herbal samples were finally discriminated by use of Bayes discrimination analysis with the reduced subsets. The case study for 79 herbal samples showed that, the methods of forward selection associating the variables with the loadings closest to 0 and key set factor analysis were preferable to determine the representative variables. Procrustes analysis and the weighted measure were not indicative to extract representative variables. High matching between the original and reduced datasets did not suggest high prediction accuracy. Visually examining the PC1-PC2-PC3 scores projection plots with the reduced subsets, not all the herb samples could be separated due to the complexity of chromatographic fingerprints.