The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets
T1 contains miRNA genes from miRBase as positives. Negatives were generated by randomly shuffling the nucleotides of the positives. For T2, the RNAz tool was used to generate miRNA gene candidates. Positives are candidate genes that overlap with the actual miRNA genes from miRBase.