Skip to main content

Table 4 Comparison of performance parameters of Parepro with other methods using the NewHumVar dataset

From: Predicting the phenotypic effects of non-synonymous single nucleotide polymorphisms based on support vector machines

Prediction Method Sensitivity Specificity Q2 MCC PM (%)
PolyPhen 0.30 0.92 0.72 0.28 79
SIFT 0.32 0.87 0.69 0.22 88
HydridMeth 0.34 0.94 0.73 0.36 100
Parepro 0.40 0.94 0.78 0.42 100
  1. The prediction results of PolyPhen, SIFT and HydridMeth were obtained from Capriotti et al. [10].
  2. Q2: the overall accuracy
  3. MCC: Matthews correlation coefficient
  4. PM is the percentage of predicted mutations.