Skip to main content

Table 2 The detailed predictions on the Embryonal dataset. Embryonal dataset: LOOCV result of the Disc-GS-KNN classifier by setting 100 gene clusters to select 45 genes. 36 out of the 42 predictions were correct (in bold).

From: Selecting dissimilar genes for multi-class classification, an application in cancer subtyping

# Samples M CRE S MG N
Medulloblastomas (M) 10 9   1   
CNS, renal and extrarenal rhabdoid (CRE) 10 1 9    
Supratentorial PNETs (S) 8 2   6   
Malignant glioma (MG) 10   1   9  
Normal (N) 4    1   3