Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Unsupervised reduction of random noise in complex data by a row-specific, sorted principal component-guided method

Figure 4

Optimization of the subset row number (A) and the repeat number (B). In treatment of simulated data matrices, the effect of different subset row number and different repeat number on noise reduction was investigated. Noise RMS ratios smaller than 1 indicate noise reduction. Each box and whiskers in the box plots shows the distribution of the noise RMS ratio values from 50 simulations. The parameters used for the simulated data sets were 30 large and 60 small signal blocks and a noise variance ratio of 0.01. The FDR used was 0.0316. In (A), the repeat number was 20. In (B), the subset row number was 180.

Back to article page