Skip to main content

Table 10 Performance for 3-way classification using SVM classifier on automatically collected orthologs

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

 

F Div Yeast (73)

F Div Human (81)

 

AUC

MCC

AUC

MCC

MTS

0.65±0.09

0.31±0.18

0.66±0.05

0.31±0.11

SP

0.60±0.07

0.19±0.14

0.70±0.08

0.40±0.15

N-signal-free

0.66±0.08

0.35±0.15

0.69±0.06

0.39±0.11

% accuracy

51.63±7.21

57.61±4.71

  1. The 5-fold cross-validation performance of an SVM classifier using divergence features is shown for three-way classification on the automatically generated ortholog dataset for yeasts and mammals. The number of examples is given in parenthesis at top.
Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us