Skip to main content

Table 8 Confusion matrices for all strategies

From: Hierarchical classification strategy for Phenotype extraction from epidermal growth factor receptor endocytosis screening

[1]

[2]

[3]

[4]

F-25

Prediction

Number of test objects

Sensitivity

  

Membrane

Vesicle

Cluster

  

Truth

Membrane

34.96

2.04

0

37

0.945

 

Vesicle

1.81

166.01

0.18

168

0.988

 

Cluster

0.12

4.39

5.49

10

0.549

F-sel

Prediction

Number of test objects

Sensitivity

  

Membrane

Vesicle

Cluster

  

Truth

Membrane

35.67

1.33

0

37

0.964

 

Vesicle

0.58

166.79

0.63

168

0.993

 

Cluster

0.17

2.77

7.06

10

0.706

H-25

Prediction

Number of test objects

Sensitivity

  

Membrane

Vesicle

Cluster

  

Truth

Membrane

34

3

0

37

0.919

 

Vesicle

0.11

166.83

1.06

168

0.993

 

Cluster

0.07

4.51

5.42

10

0.542

H-sel

Prediction

Number of test objects

Sensitivity

  

Membrane

Vesicle

Cluster

  

Truth

Membrane

35.53

1.47

0

37

0.960

 

Vesicle

0.75

166.86

0.39

168

0.993

 

Cluster

0

2.58

7.42

10

0.742

  1. Column 1 represents the strategy and class labels
  2. Column 2 represents the prediction
  3. In column 3, the number of test objects represents the ground truth
  4. In column 4, the sensitivity is given per class
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us