Skip to main content

Table 7 Evaluation measures employed in this study.

From: Using a kernel density estimation based classifier to predict species-specific microRNA precursors

Measure Abbreviation Equation1
Sensitivity (recall) %SE TP/(TP+FN)
Specificity %SP TN/(TN+FP)
Accuracy %ACC (TP+TN)/(TP+TN+FP+FN)
F-measure %Fm 2TP/(2TP+FP+FN)
Matthews' correlation coefficient %MCC (TP × TN-FP × FN)/sqrt((TP+FP) × (TN+FN) × (TP+FN) × (TN+FP))
  1. 1The definition of the abbreviations used: TP is the number of real pre-miRNAs detected; FN is the number of real pre-miRNAs missed; TN is the number of pseudo hairpins correctly classified; and FN is the number of pseudo hairpins incorrectly classified as pre-miRNA.