The ROC curve, which is defined as a plot of test sensitivity as the -coordinate, versus the false positive rate (FPR; 1 − specificity) as the -coordinate

<p><b>Copyright information:</b></p><p>Taken from "Human microRNA prediction through a probabilistic co-learning model of sequence and structure"</p><p>Nucleic Acids Research 2005;33(11):3570-3581.</p><p>Published online 24 Jun 2005</p><p>PMCID:PMC1159118.</p><p>© The Author 2005. Published by Oxford University Press. All rights reserved</p> The area under the ROC curve is 0.936 by non-parametric estimation. The arrow indicates the point of threshold, where = 0.033, specificity is 96% and sensitivity is 73%