Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: Robust differential expression analysis by learning discriminant boundary in multi-dimensional space of statistical attributes

Fig. 3

Compares the true DEFs detected by different DC configurations. Four DC configurations (DCT, DCR, DCNB and DCT+R+NB) are compared under different sample sizes (x-axis) and different true DEF configurations: (a) G 400400 , (b) G 500500 , (c) G 600600 , and (d) G 10000 . The target FDR cutoff is 0.05. The y-axis indicates the relative differences (in parentage) of the average true DEFs detected by different DC configurations with respect to those detected by DCT+R+NB.The plots only display up to 20% relative difference. This figure clearly shows that DCT+R+NB outperformed the remaining DC configurations

Back to article page