Skip to main content

Table 10 AUC values for different sequence-based features alone and in combination with predicted solvent accessibility

From: Protein-RNA interface residue prediction using machine learning: an assessment of the state of the art

Features

NB

SVM RBFK

IDSeq

0.74

0.73

IDSeq + PA

0.73

0.73

PSSMSeq

0.76

0.80

PSSMSeq + PA

0.76

0.80

SmoPSSMSeq

0.75

0.78

SmoPSSMSeq + PA

0.75

0.75

  1. Comparison of AUC (averaged over five-folds) for different sequence features alone and in combination with predicted solvent accessibility (PA) on the RB106Seq dataset (NB - Naïve Bayes, SVM - Support Vector Machine, RBFK - Radial Basis Function Kernel).
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us