Skip to main content
. Author manuscript; available in PMC: 2012 Jun 1.
Published in final edited form as: Proteins. 2011 Apr 12;79(6):1952–1963. doi: 10.1002/prot.23020

Figure 4. Effect of spatial averaging and Z-scoring on the predictive power of four of the studied structural features.

Figure 4

Linear classifier ROC curves derived for four pairs of residue features: A. Angle0.1Z vs. Angle10; B. Solvation0.01Z vs. Solvation10; C. Temperature0.01Z vs. Temperature10; D. brl0.001010Z vs. brl0.001010. For all four pairs of features, the ROC curves of the manipulated versions (red) are considerably higher than the curves of their non-manipulated counterparts (blue). The diagonal (dashed line) relates to a random classification (a pure guess). Consequently, manipulation improves AUC values (see text).