Figure 5

colon cancer prediction. Sensitivities (a) and specificities (b) (with standard deviations as error bars) estimated in colon cancer prediction from gene expression levels using 100 independent two-fold cross-validations and linear SVM classifier. Four sets of selected components were extracted by using LMMs (2a) and (2b) with control reference (c.r.) and disease reference (d.r.) samples respectively, where the overall number of components M has been set to 2 (red bars), 3 (green bars), 4 (blue bars) and 5 (magenta bars). Optimal values of the parameters λ and Δθwere used for each M. Increasing number of components M did not decrease prediction accuracy but did reduce the number of features (genes) in components used for classification (see Figure 6).