Table 5 Mathew correlation coefficient of parsimony models over seven benchmark data using four information theoretic filters
From: iRDA: a new filter towards predictive, stable, and enriched candidate genes
| Â | mRMR | CMIM | FCBF | iRDA | ||||
|---|---|---|---|---|---|---|---|---|
| Â | % | # | % | # | % | # | % | # |
Brain | 87.96 | 4 | 84.61 | 5 | 92.26 | 4 | 92.11 | 3 |
CNS | 68.64 | 2 | 68.64 | 2 | 67.08 | 6 | 71.51 | 3 |
Colon | 85.54 | 5 | 78.63 | 2 | 78.63 | 2 | 83.35 | 4 |
Leukemia | 100 | 4 | 96.95 | 5 | 97.01 | 3 | 100 | 3 |
Lung | 96.11 | 2 | 98.1 | 5 | 98.05 | 4 | 98.05 | 3 |
Lymphoma | 96.62 | 4 | 93.01 | 2 | 0.18 | 5 | 96.5 | 3 |
Prostate | 92.23 | 5 | 90.65 | 6 | 90.36 | 5 | 92.15 | 3 |
avg | 89.62 | 3.71 | 87.23 | 3.86 | 74.80 | 4.14 | 90.52 | 3.14 |