Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Ensemble approach to predict specificity determinants: benchmarking and validation

Figure 1

Comparison of prediction performances. ROC-curves for prediction of subsites are shown for SPEER, GroupSim, MultiRELIEF, SDPpred and SPEL methods. Sensitivity and error rates are estimated based on the number of true positives (correctly predicted actual subsites) and false positives (predicted sites which are not actual subsites) found at each score cutoff. Sensitivity (TP/TP+FN) is defined as a number of true positives (TP) found at each score threshold divided by the sum of true positives and false negatives (FN), where false negatives are defined as actual subsites below the score threshold. Error rate (FP/FP+TN) is estimated as the number of false positives (FP) divided by the sum of false positives and true negatives (TN, non-subsites below the score threshold).

Back to article page