Skip to main content


Fig. 1 | BMC Genomics

Fig. 1

From: Significant improvement of miRNA target prediction accuracy in large datasets using meta-strategy based on comprehensive voting and artificial neural networks

Fig. 1

ROC curves of individual predictors in the eleven newly designed non-redundant datasets. The datasets from top to bottom and from left to right are: D4, D3–1, D3–2, D3–3, D3–4, D2–1, D2–2, D2–3, D2–4, D2–5, and D2–6, respectively. Samples in the D4 dataset has prediction scores from four individual predictors, therefore, there are four ROC curves each for a predictor. Similarly, the D3 series datasets and D2 series datasets have three and two ROC curves, respectively. In each of the insets, x-axis shows the value of 1-specificity, while y-axis shows the values of sensitivity

Back to article page