Skip to main content

Advertisement

Table 1 Comparison of Proposed Method Performance against Existing Methods on Publicly Available Datasets. As shown in the table, the proposed method achieves a high classification performance on all datasets tested. In particular, the performance is superior to that of the referenced method in 3/6 datasets and matches that of the referenced method in the remaining 3 datasets. The last column shows the ratio of genes selected by both ours and the cross reference method over the total number of gene-features in the cross reference method. Abbreviations: S2N: Signal to Noise, CC: Correlation Coefficient, NA: Neighborhood Analysis, FA: Factor Analysis, 2-tail T: 2-Tail Student test, ER: Expression Ratio, K-NN: K-Nearest Neighbors. *Outlier samples for this dataset were omitted from the classification in both the reference and our method.

From: Individualized markers optimize class prediction of microarray data

Cross Reference Method Our Method
Data Set Performance Selection/Classification Performance Sensitivity Specificity Common genes
  CV Test   CV Test    
AML/ALL - 29/34 S2N/NA - 33/34 90.9% 100% 48/50
Breast Cancer 47/49 5/5* CC/FA 48/49 5/5* 100%* 100%* 81/100
Lung Cancer - 148/149 2-tail T/ER - 148/149 93.3% 100% 8/8
AML/MLL/ALL 54/57 14/15 CC/K-NN 56/5 4/4, 3/3, 8/8 - - 14/45
CNS 47/60 - S2N/K-NN 55/60 - 85.7% 94.9% 22/100
Lymph Node 31/34 - CC/FA 31/34 - 83.3% 95.4% N/A