Class prediction using metabolomics data is increasingly important in studies aiming for early diagnosis, prognosis or treatment outcomes. MetaboAnalyst offers three powerful supervised classification methods—PLS-DA, random forest (22 ) and support vector machine (SVM). These methods have proved to be robust for high-dimensional data and are widely used for other ‘omics’ data analysis. In addition, they can also help prioritize features that contribute significantly to the performance. PLS-DA based feature selection and classification was previously discussed in the chemometrics path. Random forest uses an ensemble of classification trees, each of which is grown by random feature selection from a bootstrap sample at each branch. Class prediction is based on the majority vote of the ensemble. During tree construction, about one-third of the instances are left out of the bootstrap sample. This data is then used as test sample to obtain an unbiased estimate of the classification (OOB) error. Variable importance is evaluated by measuring the increase of the OOB error when it is permuted. Figure 2D shows the important features ranked by random forest. The SVM classification algorithm aims to find a nonlinear decision function in the input space by mapping the data into a higher dimensional feature space and separating it by means of a maximum margin hyperplane (23 ). MetaboAnalyst's SVM analysis is done through recursive feature selection and sample classification using a linear kernel (24 (link)). Features are selected based on their relative contribution in the classification using cross validation error rates. The least important features are eliminated in the subsequent steps. This process creates a series of SVM models. The features used by the best model are considered to be important and are ranked by their frequencies of being selected in the model.