Table 5 Comparison of miPred and miR-KDE in terms of the feature set and the classification mechanism.
From: Using a kernel density estimation based classifier to predict species-specific microRNA precursors
| Â | Without the four stem-loop features1 | With the four stem-loop features2 | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Â | %SE | %SP | %ACC | %Fm | %MCC | %SE | %SP | %ACC | %Fm | %MCC |
HU2163 | ||||||||||
   SVM | 88.0% | 88.0% | 88.0% | 88.0% | 75.9% | 90.7% | 90.7% | 90.7% | 90.7% | 81.5% |
   RVKDE | 85.2% | 90.7% | 88.0% | 87.6% | 76.0% | 88.9% | 92.6% | 90.7% | 90.6% | 81.5% |
NH33504 | ||||||||||
   SVM | 96.7% | 90.4% | 93.6% | 93.7% | 87.3% | 97.3% | 91.3% | 94.3% | 94.4% | 88.7% |
   RVKDE | 94.8% | 93.4% | 94.1% | 94.1% | 88.2% | 95.8% | 93.5% | 94.7% | 94.7% | 89.3% |