Skip to main content

Table 1 Average AUC values of the logistic regression model for the InterPro data set

From: Structure-based Markov random field model for representing evolutionary constraints on functional sites

Feature AUC 0.1 AUC 0.2 AUC 0.5 AUC
NW-SMRF 0.023 0.069 0.275 0.733
KLD 0.024 0.071 0.277 0.733
KLD + NW-SMRF 0.027 0.076 0.293 0.758
JSD 0.025 0.072 0.279 0.736
JSD + NW-SMRF 0.027 0.077 0.294 0.758
  1. AUC 0.1, AUC 0.2, and AUC 0.5 represent the partial area under the ROC curve spanning the false positive rates of 0.1, 0.2, and 0.5, respectively. The best AUC value between the conservation score and the combination of the conservation score with the coevolution score is shown in bold. NW-SMRF represents the coevolution measure derived from node weights. KLD and JSD represent conservation measures using KL-divergence and JS-divergence, respectively. KLD + NW-SMRF and JSD + NW-SMRF represent the logistic regression models combining the coevolution and conservation measures