Skip to main content

Table 3 Accuracy comparison of PROTNN and PROTSVM

From: ProtNN: fast and accurate protein 3D-structure classification in structural and topological space

Dataset Classification approach
  ProtNN ProtSVM(linear) ProtSVM(rbf)
DS1 0.97 0.88 0.83
DS2 0.8 0.68 0.56
DS3 0.96 0.87 0.78
DS4 0.97 0.80 0.82
DS5 0.9 0.79 0.73
DS6 0.96 0.84 0.72
Avg. accuracy1 0.93 ±0.06 0.81 ±0.07 0.74 ±0.1
  1. 1Average classification accuracy of each classification approach over the six datasets. The boldface numbers highlight the best performance