Figure 3
From: The application of network label propagation to rank biomarkers in genome-wide Alzheimer’s data
AUCs with 95% confidence intervals for four different feature ranking methods (chi square, SWRF, SLR, and LP) obtained from application of the k NN classifier on two LOAD datasets (TGen and ADRC) with two sets of SNPs (chromosome 19 only and genome-wide). The datasets used in the four panels are: A) TGen chromosome 19 only (3,652 SNPs); B) TGen genome-wide (234,665 SNPs); C) ADRC chromosome 19 only (13,087 SNPs); D) ADRC genome-wide (682,685 SNPs). The SLR method implicitly selects <500 features in each experiment.