Skip to main content

Table 2 PV accuracy compared with other algorithms and HMM models

From: A new decoding algorithm for hidden Markov models improves the prediction of the topology of all-beta membrane proteins

Method Q 2 SOV SOV(BetaTM) SOV(Loop) Q ok
cross-validation      
Posterior-Viterbil 0.82 0.87 0.92 0.81 0.80
Viterbi1 0.63 0.33 0.27 0.35 0.0
1-best1 0.65 0.41 0.37 0.41 0.07
HMMB2HTMR2 0.83 0.87 0.88 0.84 0.73
PROFTmb3 0.83 0.87 0.88 0.84 0.73
pred-tmbb4 (Viterbi) 0.78 0.83 0.81 0.82 0.60
pred-tmbb4 (1-best) 0.78 0.83 0.81 0.82 0.60
pred-tmbb4 (posterior) 0.78 0.82 0.80 0.82 0.60
blind-test      
Posterior-Viterbi1 0.80 0.81 0.84 0.74 0.60
Viterbi1 0.62 0.38 0.35 0.40 0.20
1-best1 0.63 0.38 0.36 0.40 0.20
HMMB2HTMR2 0.80 0.81 0.84 0.74 0.60
PROFTmb3 0.72 0.65 0.72 0.58 0.40
pred-tmbb4 (Viterbi) 0.71 0.73 0.79 0.71 0.20
pred-tmbb4 (1-best) 0.71 0.73 0.79 0.71 0.20
pred-tmbb4 (posterior) 0.72 0.75 0.81 0.71 0.20
  1. 1 Model taken from Martelli et al., 2002 [12]
  2. 2 Fariselli et al. 2003 [21]
  3. 3 Bigelow et al., 2004 [17]
  4. 4 Bagos et al., 2004 [16]