Skip to main content

Table 6 Comparison of OMiMa PVLMM and MEM for donor site prediction. Comparing OMiMa with PVLMM and MEM for donor splice site prediction. The table shows Matthews correlation efficients (Mc) of top 4 models from each model class. The splice site data and results of MEM models were from Yeo and Burge [23]. In the 3-fold cross validation, the sample sizes for both training and testing sets are approximately equal to those of the original partition by Yeo and Burge.

From: Optimized mixed Markov models for motif identification

sub-model Mc sub-model Mc (Org./3-CV) sub-model Mc (Org./3-CV)
me2x5 0.659 P:2-2 0.629/0.631 3-C-1 0.658/0.663
me2x4 0.655 P:3-2 0.626/0.632 3-L-1 0.654/0.657
me2x3 0.653 P:4-2 0.625/0.630 2-C-1 0.647/0.657
me5s0 0.653 P:4-3 0.622/0.628 2-L-1 0.643/0.653