Skip to main content

Table 3 GO terms giving a high prediction quality using only one data source

From: Integrative approaches to the prediction of protein functions based on the feature selection

Data source

GO

Term

NPWGD

NPWG

AUC

P20R

DA

OPHID (PPI)

0048489

synaptic vesicle transport

13

14

0.92

0.39

0.17

 

0006887

exocytosis

21

27

0.91

0.87

0.12

Interpro (Domain)

0006071

glycerol metabolism

10

11

0.87

0.8

0.44

 

0000160

two-component signal transduction system (phosphorelay)

10

10

1

1

0.41

 

0006801

superoxide metabolism modification-dependent

10

10

0.93

1

0.31

 

0043632

macromolecule catabolism

47

47

0.96

0.5

0.28

 

0006508

proteolysis

233

240

0.92

0.69

0.28

 

0006812

cation transport

173

176

0.90

0.93

0.15

Pfam (Domain)

0016311

dephosphorylation

48

51

0.97

0.81

0.35

 

0006338

chromatin remodeling

21

22

0.91

0.28

0.33

 

0031497

chromatin assembly protein amino acid

29

30

0.97

0.63

0.32

 

0006470

Dephosphorylation

46

49

0.98

0.69

0.31

 

0006333

chromatin assembly or disassembly

41

42

0.96

0.71

0.3

MGI (Phenotype)

0008344

adult locomotory behavior

14

19

0.9

0.21

0.31

 

0030534

adult behaviour

18

23

0.9

0.21

0.3

 

0007605

sensory perception of sound

26

40

0.94

0.55

0.27

 

0048232

male gamete generation

44

70

0.93

0.34

0.26

 

0007283

spermatogenesis

44

70

0.94

0.28

0.25

 

0000003

reproduction

101

152

0.87

0.52

0.20

OMIM (Diseases)

0008643

carbohydrate transport

11

30

0.94

0.87

0.15

Zhang et al. (Gene expression)

0001502

cartilage condensation

10

10

0.85

0.23

0.15

  1. GO terms and data sources displaying the outstanding contributions to the prediction of the given GO term are listed, where only part of the lists among the GO terms covering greater than or equal to 10 proteins are presented. NPWGD stands for number of proteins having the given GO term and the given data source, NPWG is the number of proteins with the given GO term, and DA is the difference between the AUC score and the second highest accuracy.