Figure 4

Measure of separation against the reduced number of genes at different k values. The sum of median distance measure as a function of genes and k parameter of CUR (different colors). The horizontal red line shows the baseline value when all the genes are used for PCA. Above 300 genes and k = 3 the CUR selected subsets give better separation than the original all-genes and the maximum separation performance is around k = 5 using 150 genes.