Table 4 Performance based on the 1st and leaf layer clusters
From: Genome-scale MicroRNA target prediction through clustering with Dirichlet process mixture model
Dataset | Sensitivity | Specificity | Accuracy | MCC | ||||
|---|---|---|---|---|---|---|---|---|
1st | Leaf | 1st | Leaf | 1st | Leaf | 1st | Leaf | |
Training 75% of CLASH, iPAR, negative | 0.93 | 0.94 | 0.96 | 0.97 | 0.95 | 0.96 | 0.89 | 0.91 |
Testing 25% of CLASH, iPAR, negative | 0.93 | 0.94 | 0.96 | 0.97 | 0.94 | 0.96 | 0.89 | 0.91 |
Validation-1 CLEAR-CLIP | 0.87 | 0.92 | – | – | 0.87 | 0.92 | – | – |
Validation-2 mirTarbase (val.) | 0.63 | 0.60 | – | – | 0.63 | 0.60 | – | – |
Validation-3 mirTarbase (pre.) | 0.60 | 0.58 | – | – | 0.60 | 0.58 | – | – |