Search

Metabolic markers are the core of metabonomic surveys. Hence selection of differential metabolites is of great importance for either biological or clinical purpose. Here, a feature selection method was developed for complex metabonomic data set. As an effective tool for metabonomics data analysis, support vector machine (SVM) was employed as the basic classifier. To find out meaningful features effectively, support vector machine recursive feature elimination (SVM-RFE) was firstly applied. Then, genetic algorithm (GA) and random forest (RF) which consider the interaction among the metabolites and independent performance of each metabolite in all samples, respectively, were used to obtain more informative metabolic difference and avoid the risk of false positive. A data set from plasma metabonomics study of rat liver diseases developed from hepatitis, cirrhosis to hepatocellular carcinoma was applied for the validation of the method. Besides the good classification results for 3 kinds of liver diseases, 31 important metabolites including lysophosphatidylethanolamine (LPE) C16:0, palmitoylcarnitine, lysophosphatidylethanolamine (LPC) C18:0 were also selected for further studies. A better complementary effect of the three feature selection methods could be seen from the current results. The combinational method also represented more differential metabolites and provided more metabolic information for a 'global' understanding of diseases than any single method. Further more, this method is also suitable for other complex biological data sets. [ABSTRACT FROM AUTHOR]

Abstract: We applied the random forest method to discriminate among different kinds of cut tobacco. To overcome the influence of the descending resolution caused by column pollution and the subsequent deterioration of column efficacy at different testing times, we constructed combined peaks by summing the peaks over a specific elution time interval Δt. On constructing tree classifiers, both the original peaks and the combined peaks were considered. A data set of 75 samples from three grades of the same tobacco brand was used to evaluate our method. Two parameters of the random forest were optimized using out-of-bag error, and the relationship between Δt and classification rate was investigated. Experiments show that partial least squares discriminant analysis was not suitable because of the overfitting, and the random forest with the combined features performed more accurately than Naïve Bayes, support vector machines, bootstrap aggregating and the random forest using only its original features. [ABSTRACT FROM AUTHOR]