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

Table 4 Comparison of H-SVM-LR with other β-turns prediction methods on BT547 and BT823 datasets.

Prediction method	Dataset	Qtotal	Qpredicted	Qobserved	MCC
H-SVM-LR		82.84	63.60	68.5	0.55
Zheng and Kurgan [2]		80.5	61.6	54.2	0.45
Liu et al. [20]	BT547	80.6	64.3	44.5	0.44
Hu and Li [19]		76.6	47.6	70.2	0.43
DEBT [21]		80.0	55.9	68.7	0.49
COUDES [9]		74.6	48.7	70.4	0.42
H-SVM-LR		82.32	64.48	72.72	0.56
Zheng and Kurgan [2]		80.6	60.8	54.6	0.45
Liu et al. [20]	BT823	80.5	62.3	44.6	0.44
Hu and Li [19]		76.8	53.0	72.3	0.45
DEBT [21]		80.9	55.9	66.1	0.48
COUDES [9]		74.2	47.5	69.6	0.41

a
Note: The results of the method of Liu et al. are obtained from their corresponding paper. The results of other β-turns prediction methods are obtained from [22].

ISSN: 1477-5956