Skip to main content

Table 1 Designation of training set and test set in our experiments

From: Finding minimum gene subsets with heuristic breadth-first search algorithm for robust tumor classification

Datasets Usages m* n* k Platform
Prostate102 Tr** 102 12,600 2 Affy HU95A V2
Prostate34 Te** 34 12,626 2 Affy U95A
DLBCL77 Tr 77 7,129 2 Affy HU6800
DLBCL21 Te 21 12,581 2 Affy HU95AV2
Leukemia72 Tr 72 7,129 2 Affy HU6800
Leukemia52 Te 52 12,582 2 AffyHGU95a
Colon Tr 42 2000 2 AffyHUM6000
Te 20
ALL Tr 148 12626 6 Affy HGU95AV2
Te 100
SRBCT Tr 63 2308 4 cDNA
  Te 20    
  1. * m denotes the number of sample in dataset. n denotes the number of genes, and k denotes the number of subclasses.
  2. **“Tr” denotes this dataset will be used as training set, while “Te” denotes this dataset will be used as test set.