Skip to main content

Table 3 Comparison with other methods on the N3D dataset.

From: Improving the prediction of disease-related variants using protein three-dimensional structure

  Q2 P[D] S[D] P[N] S[D] C AUC PM
SIFT 0.77 0.77 0.74 0.76 0.79 0.53 0.83 96
PolyPhen2 0.80 0.78 0.83 0.82 0.76 0.60 0.86 99
SVM-SEQ 0.80 0.78 0.84 0.82 0.76 0.59 0.86 100
SVM-3D 0.82 0.80 0.85 0.84 0.79 0.63 0.89 100
  1. The accuracy measures are defined in Methods section. D and N are disease-related and neutral variants respectively. PM is the predicted fraction of the dataset. Methods are tested on N3D dataset.