Fig. 2
From: Ensemble outlier detection and gene selection in triple-negative breast cancer data
Individuals’ distributions in the space spanned by the first two Principal Components. a symbols correspond to actual labels: circles, non-TNBC individuals; triangles, TNBC individuals; blue data points are influential observations; red data points are influential observations which are suspect regarding their HER2 label. b symbols correspond to predicted labels by the EM algorithm: circles, non-TNBC individuals; triangles, TNBC individuals; red data points are actual non-TNBC observations, for which at least one of the 3 TNBC-associated genes has an arguably high expression value