Skip to main content

Table 5 Performance of 3-way classification using SVM classifier

From: Plus ça change – evolutionary sequence divergence predicts protein subcellular localization signals

 

Divergence

Classical features

Combination

 

AUC

MCC

AUC

MCC

AUC

MCC

MTS

0.67±0.03

0.36±0.06

0 . 8 7±0.03

0.76±0.05

0 . 8 7±0.03

0 . 7 7±0.03

SP

0.50±0.00

0.00±0.00

0.81±0.08

0.70±0.11

0 . 9 0±0.06

0 . 8 3±0.07

N-signal-free

0.66±0.02

0.36±0.03

0.85±0.03

0.72±0.05

0 . 8 7±0.02

0 . 7 7±0.03

% accuracy

70.82±1.61

87.24±1.86

8 9 . 3 0±0.66

  1. The 5-fold cross-validation performance of an SVM classifier using: divergence features only, classical features only, and the two combined; is shown for three-way classification on the yeast curated ortholog dataset. Classical features are computed based on the N-terminal 40 residues.
Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us