Skip to main content

Table 4 Comparison of lineage-specific models with traditional universal models on three training sets using five-fold cross-validation

From: Prediction of bioluminescent proteins by using sequence-derived features and lineage-specific scheme

Lineage Model Sensitivity Specificity Accuracy MCC AUC
Bacteria PredBLP-U 0.790 ± 0.010 0.918 ± 0.014 0.854 ± 0.003 0.714 ± 0.007 0.872 ± 0.006
PredBLP-B 0.832 ± 0.012 0.943 ± 0.016 0.888 ± 0.006 0.780 ± 0.013 0.920 ± 0.010
Eukaryota PredBLP-U 0.417 ± 0.053 0.883 ± 0.041 0.650 ± 0.033 0.340 ± 0.075 0.670 ± 0.017
PredBLP-E 0.667 ± 0.053 0.833 ± 0.053 0.750 ± 0.026 0.510 ± 0.054 0.806 ± 0.015
Archaea PredBLP-U 0.750 ± 0.079 0.875 ± 0.079 0.813 ± 0.040 0.637 ± 0.081 0.868 ± 0.016
PredBLP-A 0.825 ± 0.061 0.900 ± 0.094 0.863 ± 0.047 0.733 ± 0.095 0.917 ± 0.019
  1. The results are reported by maximizing the MCC values of prediction on the corresponding dataset over five-fold cross-validation. PredBLP-U stands for the universal model of the proposed PredBLP predictor. PredBLP-B, PredBLP-E and PredBLP-A indicate three lineage-specific models (i.e. bacteria-, eukaryota- and archaea- specific model) respectively