A dynamic Bayesian network approach to protein secondary structure prediction

BMC Bioinformatics

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

Method	Q₃ (%)	SOV (%)	C _H	C _E	C _C
HMMCrooks	72.8	--	--	--	--
HMMChu	72.2	68.3	0.61	0.52	0.51
DBN_diag/ErrSig	72.5/0.42	65.9/0.63	0.66/0.01	0.55/0.01	0.51/0.01
DBN_final/ErrSig	76.3/0.41	72.7/0.63	0.71/0.01	0.61/0.01	0.57/0.01

DBN_final and DBN_diag 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.

ISSN: 1471-2105