Skip to main content

Table 2 Performance of DBNgeo, DBNfinal, and DBNmod tested on SD576.

From: A dynamic Bayesian network approach to protein secondary structure prediction

Model

Q3 (%)

SOV (%)

Relative entropy (bit)

   

Helix

Sheet

Coil

Average

DBNgeo

76.7

74.3

0.247

0.170

0.290

0.236

DBNfinal

78.2

76.8

0.236

0.096

0.210

0.181

DBNmod

78.2

76.3

0.214

0.038

0.110

0.121

  1. The seven-fold cross-validation test results on three models with different segment length distributions are explained in the text. The performance is measured by Q3, SOV, and the relative entropies between the observed segment length distributions from SD576 and the model's predictions [Eq. (2)]. Clearly, DBNfinal and DBNmod have visible improvement over DBNgeo.