Figure 3.

Performance of the 17-module classifier. (A). Classification performance of accumulated modules. The x axis represents the number of "genes" involved in the modules, including TFs, miRNAs, or genes, and the y axis represents the value of prediction accuracy(ACC) and Matthew correlation coefficient(MCC). Performance of classifiers whose number of "genes" within 300 are showed. One dot on a line represents addition of one more module. When the number of modules accumulated to 17, ACC overrides 90% and MCC overrides 80%. (B). Survival difference of the predicted non-metastatic and metastatic groups by the 17-module classifier. Kaplan-Meier estimation was calculated to plot the survival curve. Log-rank test was used to compare two survival distributions and generate the p value.

Zeng et al. BMC Genomics 2012 13(Suppl 8):S14   doi:10.1186/1471-2164-13-S8-S14