Figure 4
From: Cancer module genes ranking using kernelized score functions
HumanNet network: precision and recall curves relative to different kernelized score functions using random walk kernels at 1, 2 and 3 steps. precisions, averaged across the 298 Cancer Modules, are computed through 5-fold cross-validation techniques repeated 5 times for different fixed recall levels ranging from 0.1 to 1. S AV stands for Average score, S NN for Nearest-neighbor score and S kNN for k-Nearest-neighbor score.