Skip to main content

Advertisement

Table 4 Comparison of accuracy when predicting the structural classes using all features, each feature individually, and when excluding one features at the time.

From: SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences

Features Accuracy when predicting with one feature
   all-α all-β α/β α+β overall
All features included 92.8 80.6 74.3 71.4 80.1
using only one feature PSIPRED-NCount H 6 89.6 58.7 32.9 46.7 58.4
  PSIPRED- NCount H 8 81.9 78.3 53.8 58.7 69.0
  PSIPRED-CMV H 1 76.3 74.5 55.8 48.8 64.3
  PSIPRED-NAvgSeg H 49.9 83.3 0.0 47.8 47.9
  PSIPRED-NCount E 5 85.8 59.1 50.9 47.4 61.4
  PSIPRED- CV E 88.9 71.3 60.7 51.0 68.4
  PSIPRED-MaxSeg E 83.1 48.8 0.0 67.1 52.6
  PSIPRED-NAvgSeg E 79.2 33.9 3.2 42.4 41.8
  CV L---G 73.8 0.0 54.3 7.7 32.8
excluding the listed feature PSIPRED-NCount H 6 92.1 79.5 71.7 70.8 78.9
  PSIPRED-NCount H 8 93.0 79.5 73.1 70.3 79.3
  PSIPRED-CMV H 1 92.5 80.8 72.5 71.0 79.6
  PSIPRED-NAvgSeg H 92.5 81.0 71.4 68.7 78.8
  PSIPRED-NCount E 5 90.7 80.1 73.4 71.4 79.3
  PSIPRED-CV E 91.9 80.6 72.5 71.4 79.5
  PSIPRED-MaxSeg E 92.8 79.7 73.1 69.8 79.2
  PSIPRED-NAvgSeg E 92.3 80.6 71.1 69.2 78.7
  CV L---G 92.8 80.6 73.4 68.9 79.3
  1. Bold font shows the top two highest accuracies when using individual features, and features selected for further analysis.