Skip to main content

Table 1 Frequency counts of samples in each class for marker pairs.

From: TSG: a new algorithm for binary and multi-class cancer classification and informative genes selection


Ei < Ej



Class C 1

f 11ij

f 21ij

n 1 = f 11ij +f 21ij

Class C M

f 1Mij

f 2Mij

n M = f 1Mij +f 2Mij


T 1 = Σ m = 1 M f 1 m i j

T 2 = Σ m = 1 M f 2 m i j


  1. The E i and E j represent the population of expression values for markers i and j respectively.
  2. The ni are the total number of samples in class Ci, i = 1,..., M.