Skip to main content

Table 3 Comparison of H-SVM-LR with other β-turns prediction methods on the BT426 dataset.

From: Predicting beta-turns in proteins using support vector machines with fractional polynomials

Prediction method Qtotal Qpredicted Qobserved MCC
H-SVM-LR 82.87 64.83 70.66 0.56
Zheng and Kurgan [2] 80.9 62.7 55.6 0.47
Liu et al. [20] 80.9 63.6 49.2 0.44
Hu and Li [19] 79.8 55.6 68.9 0.47
DEBT [21] 79.2 54.8 70.1 0.48
BTSVM [17] 78.7 56.0 62.0 0.45
NetTurnP [1] 78.2 54.4 75.6 0.50
MOLEBRNN [15] 77.9 53.9 66.0 0.45
Zhang et al.(multiple alignment) [18] 77.3 53.1 67.0 0.45
BetaTPred2 [14] 75.5 49.8 72.3 0.43
Kim [16] 75.0 46.5 66.7 0.40
COUDES [9] 74.8 48.8 69.9 0.42
BTPRED [13] 74.4 48.3 57.3 0.35
  1. a
  2. Note: The results of the method of Liu et al. and NetTurnP method are obtained from their corresponding papers. The results of other β-turns prediction methods are obtained from [22].