Skip to main content

Table 3 Comparative performance of DBNfinal and DBNdiag against leading HMM-type methods tested on CB513.

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

Method Q3 (%) SOV (%) C H C E C C
HMMCrooks 72.8 -- -- -- --
HMMChu 72.2 68.3 0.61 0.52 0.51
DBNdiag/ErrSig 72.5/0.42 65.9/0.63 0.66/0.01 0.55/0.01 0.51/0.01
DBNfinal/ErrSig 76.3/0.41 72.7/0.63 0.71/0.01 0.61/0.01 0.57/0.01
  1. DBNfinal and DBNdiag are methods developed in this work and their descriptions can be found in the text. Entries marked with "--" mean that the data could not be obtained from the literature. HMMChu has been trained and tested on the CB480 dataset (a reduced version of CB513), while all other methods have been trained and tested on the CB513 dataset. The average results of seven-fold cross-validation are shown.