Skip to main content

Table 1 Experimental results on the RNA-protein sequence data set. Experimental results with Naive Bayes (NB) and Logistic Regression (LR) models, and Mixture of Experts (ME) models on the non-redundant RNA-protein sequence data set, where the identity cutoffs are 30% and 90%. The results are shown for default threshold θ = 0.5. ME-NB-global and ME-LR-global use NB and LR at the leaves and exploits the global sequence similarity to construct the hierarchical structure. ME-NB-local exploits the local sequence similarity to construct the hierarchical structure. ME-NB-random randomizes the global similarity matrix and constructs the hierarchical structure based on the randomized matrix.

From: Mixture of experts models to exploit global sequence similarity on biomolecular sequence labeling

  RNA-protein 30% RNA-protein 90%
Classifier Precision Recall CC FM AUC Precision Recall CC FM AUC
NB 0.58 0.25 0.31 0.35 0.75 0.58 0.30 0.33 0.40 0.77
ME-NB-global 0.61 0.27 0.34 0.38 0.77 0.61 0.32 0.36 0.42 0.78
ME-NB-local 0.62 0.25 0.33 0.35 0.76 0.61 0.30 0.34 0.40 0.77
ME-NB-random 0.59 0.24 0.31 0.35 0.75 0.59 0.30 0.33 0.40 0.77
LR 0.62 0.18 0.28 0.29 0.76 0.63 0.23 0.31 0.34 0.77
ME-LR-global 0.60 0.23 0.31 0.34 0.77 0.61 0.27 0.33 0.38 0.78