Skip to main content

Table 4 Enhancing above various thresholds on PlaneDimers , where PresCont ’s threshold was chosen such that the specificity approximately equals that of enhancing

From: CRF-based models of protein surfaces improve protein-protein interaction site predictions

  tp tn fp fn Spec. Sen. MCC  
Enhancing above 0.500 2181 23182 4145 1414 0.848 0.607 0.362  
PresCont 2100 23197 4130 1495 0.849 0.584 0.346  
Enhancing above 0.525 2303 22917 4410 1292 0.839 0.641 0.373  
PresCont 2206 22912 4415 1389 0.838 0.614 0.353  
Enhancing above 0.550 2507 22103 5224 1088 0.809 0.697 0.375  
PresCont 2419 22102 5225 1176 0.809 0.673 0.358  
Enhancing above 0.575 2560 21992 5335 1035 0.805 0.712 0.380  
PresCont 2463 21915 5412 1132 0.802 0.685 0.358  
Enhancing above 0.600 2379 22685 4642 1216 0.830 0.662 0.376  
PresCont 2253 22780 4547 1342 0.834 0.627 0.356  
Enhancing above 0.625 2287 23044 4283 1308 0.843 0.636 0.376  
PresCont 2136 23049 4278 1459 0.843 0.594 0.346  
  1. The sensitivity increased that way by 4%-7%. For every pair of experiments, the number of true negatives (tn), false negatives (fn), false positives (fp) and true positives (tp) are displayed.