Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Signature Evaluation Tool (SET): a Java-based tool to evaluate and visualize the sample discrimination abilities of gene expression signatures

Figure 4

Error rate distribution analysis for signatures related to breast cancer metastasis. (A) Using 295 breast cancer samples (published by van de Vijver et al.), SET can reduce the gene number from 70 to 49 without losing prediction power (error rate 0.325 and 0.315, respectively). (B) For 151 samples with lymph-node-negative pathology status, the top 12 genes had a similar discrimination power to that of 70 genes (error rate 0.272 and 0.291, respectively; p value < 0.001). (C) For 144 samples with lymph-node-positive pathology status, the top 8 genes had a similar discrimination power to that of 70 genes (error rate 0.319 and 0.396, respectively; p value < 0.001).

Back to article page