Skip to main content

Table 5 Training and test error statistics with all possible subsets of six biomarkers

From: Discovering biomarkers from gene expression data for predicting cancer subgroups using neural networks and relational fuzzy clustering

  Training Error in % Test Error in %
Gene Removed Max. Min. Average Max. Min. Average
FGFR4 87.30 0 18.18 85.0 15.0 37.0
AF1Q 68.25 0 15.71 80.0 10.0 34.5
NAB2 87.30 0 20.24 85.0 15.0 37.25
CDH2 68.25 0 30.32 75.0 10.0 43.0
EHD1 68.25 0 20.56 75.0 10.0 32.75
LSP1 68.25 0 11.59 70.0 10.0 26.25
FVT1 68.25 0 10.40 75.0 0.0 20.5
  1. The maximum, minimum and the average training and test errors obtained using MLP networks with all possible subsets of size six genes (i.e., after removing one gene at a time from the set of identified marker genes). With each combination of 6 genes, the network was trained 20 times with different initializations and the statistics are computed based on the results of these 20 trials