Table 1 Log-likelihood scores of training sets and log-posterior probabilities of the true annotations for the PROT3 benchmark. Here D denotes the training alignment data (the HOMSTRAD database without the beta-glycanase SCOP family), A denotes the DSSP annotations of the alignment data, θ _D denotes the model with parameters obtained from training on D, and θ _G denotes the model with parameters obtained from the GTJ datafiles.

From: XRate: a fast prototyping, training and annotation tool for phylo-grammars