Skip to main content
Figure 3 | BMC Bioinformatics

Figure 3

From: How to find simple and accurate rules for viral protease cleavage specificities

Figure 3

The receiver operator characteristic (ROC) for the OSRE rules’ accuracy on the out-of-sample HIV-1 PR 3261 data set. The triangles show the results for the OSRE HIV-1 PR 746 rules and the circles show the results for the OSRE HIV-1 PR 1625 rules (the five symbols correspond to results using 1, 2, 3, 4, and 5 rules, respectively). The diamonds and stars show the rough set rules’ prediction accuracy, Table III and Fig. 1b in [17]. The diamonds and stars show the results when 1, 2, 3, ..., and 9 rules are used from [17]. The squares and the crosses in the detail Figure, Fig. 4, are the results for Table IV and Fig. 1a in [17]. The dots show the prediction accuracy for the HIVcleave web-server [37]. The solid curve shows the ROC curve for the hitherto best predictor, a linear support vector machine trained on the HIV-1 PR 1625 data set [38], which does not provide any rules. The dashed diagonal line marks the expected results for random prediction.

Back to article page