Skip to main content
Figure 6 | BMC Bioinformatics

Figure 6

From: Integrative analysis of gene expression and copy number alterations using canonical correlation analysis

Figure 6

The effect of choosing extreme regularization values. Representation of the samples from the validation set by their coordinates in the first two pairs of features extracted from the tuning set using regularized dual CCA, with regularization parameters τ x = 0, τ y = 0 (left panel), and τ x = 1, τ y = 1 (right panel). The filled markers represent the coordinates in the features extracted from the copy number variables, and the open markers represent coordinates in the features extracted from the gene expression variables. Samples with different leukemia subtypes are shown with different colors. Without regularization (left panel) the extracted features, although being highly correlated (see Additional file 1: Supplementary Figure 2), do not encode any biological information and are not generalizable to extract correlated information from the validation set. With maximal regularization (right panel), the agreement between the extracted features is weak, although they contain a large part of the variance in the data sets.

Back to article page