Skip to main content

Table 1 Cross-validation results on the yeast and the human data

From: Critical assessment of sequence-based protein-protein interaction prediction methods that do not require homologous protein sequences

 

Yeast 10N1

Yeast 100N

 

AUC

P20R 2

AUC

P20R

M1

0.83

0.55

0.83

0.11

M2

0.79

0.82

0.79

0.33

M3

0.60

0.28

0.60

0.04

M4

0.75

0.35

0.75

0.05

C

0.85

0.84

0.85

0.34

 

Human 10 N 1

Human 100 N

 

AUC

P20R

AUC

P20R

M1

0.86

0.70

0.86

0.19

M2

0.81

0.91

0.81

0.51

M3

0.67

0.36

0.67

0.05

M4

0.83

0.59

0.83

0.12

C

0.91

0.95

0.90

0.67

  1. 1Evaluation using a negative subset of size 10N randomly chosen from the 100N negative set, where N is the size of the positive set.
  2. 2Precision values at 20% recall