Skip to main content

Table 3 Comparison of the methods for pre-miRNA ab initio prediction using sequence HAD. The results of five distinct combinations of discriminant probabilities for the three respective stages are shown in parenthesis for Mirnacle

From: Mirnacle: machine learning with SMOTE and random forest for improving selectivity in pre-miRNA ab initio prediction

Method Sensitivity Selectivity GM Time(mm:ss)
Mirnacle (0.3,0.3,0.7) 97 81.51 88.91 14:58
Mirnacle (0.4,0.4,0.7) 86 85.15 85.57 07:31
Mirnacle (0.5,0.5,0.7) 65 86.76 75.09 03:24
Mirnacle (0.6,0.6,0.7) 55 94.83 72.21 02:05
Mirnacle (0.8,0.8,0.7) 23 95.83 46.94 01:20
TVM 97 39.34 61.77 -
miRNAFold 97 19.17 43.12 00:0.84
miRPara 97 9.70 30.67 05:24
CID-miRNA 97 11.72 33.71 90:49
VMir 28 1.32 6.07 02:32