Evaluation of Bioinformatic Programmes for the Analysis of Variants within Splice Site Consensus Regions

Figure 4

ROC curve comparison of the four prediction programmes. Each ROC curve shows a trade-off between sensitivity and specificity for each programme over a range of decision threshold values. The perfect ROC curve would align with the upper left corner, at a sensitivity of 100% and a false-positive rate of 0%. Therefore, the closer the ROC curve is to the upper left axis, the greater the accuracy of the prediction programme is.