Table 1

Performance of basic DBN and NN models and their combinations tested on SD576.

Model

Q3 (%)

SOV (%)

CH

CE

CC


DBNlinear+NC

75.1

74.0

0.69

0.60

0.55

DBNlinear+CN

74.6

73.3

0.68

0.61

0.53

DBNlinear

77.0

75.8

0.72

0.64

0.58

DBNsigmoid+NC

75.8

74.5

0.72

0.60

0.56

DBNsigmoid+CN

74.6

73.3

0.69

0.61

0.54

DBNsigmoid

77.4

75.9

0.74

0.64

0.59

DBNfinal

78.2

76.8

0.74

0.65

0.60

NNlinear

77.6

73.2

0.72

0.64

0.60

NNsigmoid

77.1

71.0

0.72

0.63

0.59

NNfinal

77.8

73.3

0.73

0.64

0.60

DBNN

80.0

78.1

0.77

0.68

0.63


All the eleven models listed in the table are described in Methods. The average results of seven-fold cross-validation are shown.

Yao et al. BMC Bioinformatics 2008 9:49   doi:10.1186/1471-2105-9-49

Open Data