PCA plot of the different sample classes.

<p>The principal component analysis was performed on all samples, and on the top 50 microRNAs with the highest standard deviation. The normalized log ratio values have been used for the analysis. The features have been shifted to be zero centered, (i.e. the mean value across samples is shifted to 0) and scaled to have unit variance (i.e. the variance across samples is scaled to 1) before the analysis. Samples C2-C5, C7 & C13 correspond to the control group of patients, whereas sample codes beginning with S correspond to the 2 subsets of the study group, designated and colored separately as in <a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0123522#pone.0123522.g002" target="_blank">Fig 2</a>.