Figure 3From: Entropy-based gene ranking without selection bias for the predictive classification of microarray dataSubfigure 3(a): Step 1: weight distribution with H ≤ H t ; Subfigure 3(b): Step 11: weight distribution with H > H t , and M ≤ M t ; Subfigure 3(c): Step 17: weight distribution with H > H t , and M > M t . Distribution of SVM weights at different steps of the E-RFE process (Tumor vs. metastases).Back to article page