Skip to main content

Table 1 The performance of SCM with different pairs of weights on two data sets Sd957 and SOLproDB.

From: Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition

Classifier (W1, W2)

Sd957

SOLproDB

 

Training (%)

Test (%)

R

Training (%)

Test (%)

R

SCM (0.8, 0.2)

83.52

82.72

0.981

59.99

58.99

1.000

SCM (0.9, 0.1)

84.47

84.29

0.953

59.99

58.99

1.000

SCM (1.0, 0)

84.99

87.43

0.682

63.85

60.00

0.776

  1. R is a correlation coefficient.