Skip to main content

Table 2 Results: \(\sigma _{z}=0.5\)

From: PredictiveNetwork: predictive gene network estimation with application to gastric cancer drug response-predictive network analysis

No.TFs

Scenario

Feature selection of genes

TP

TN

Ave

Pro

NW.P

EL

LA

Pro

NW.P

EL

LA

Pro

NW.P

EL

LA

5

1

0.98

0.76

0.42

0.42

0.93

0.69

0.87

0.87

0.96

0.72

0.65

0.64

 

2

0.98

0.73

0.41

0.39

0.93

0.65

0.83

0.88

0.95

0.69

0.62

0.63

 

3

0.99

0.67

0.41

0.40

0.93

0.73

0.85

0.86

0.96

0.70

0.63

0.63

 

4

0.98

0.74

0.44

0.41

0.94

0.71

0.83

0.87

0.96

0.73

0.64

0.64

10

1

0.98

0.73

0.36

0.36

0.93

0.77

0.93

0.93

0.95

0.75

0.65

0.65

 

2

0.97

0.77

0.36

0.34

0.93

0.81

0.93

0.93

0.95

0.79

0.64

0.64

 

3

0.99

0.75

0.37

0.35

0.93

0.78

0.92

0.94

0.96

0.76

0.65

0.65

 

4

0.97

0.71

0.35

0.34

0.94

0.85

0.94

0.94

0.96

0.78

0.64

0.64

25

1

0.98

0.74

0.34

0.34

0.93

0.96

0.97

0.97

0.96

0.85

0.65

0.65

 

2

0.97

0.66

0.31

0.30

0.94

0.97

0.96

0.97

0.96

0.81

0.64

0.63

 

3

0.98

0.72

0.33

0.32

0.94

0.97

0.97

0.97

0.96

0.84

0.65

0.65

 

4

0.97

0.70

0.32

0.32

0.94

0.97

0.97

0.97

0.95

0.83

0.64

0.64

50

1

0.98

0.76

0.31

0.31

0.94

0.97

0.98

0.97

0.96

0.87

0.64

0.64

 

2

0.96

0.76

0.29

0.28

0.94

0.98

0.98

0.98

0.95

0.87

0.63

0.63

 

3

0.99

0.75

0.32

0.32

0.94

0.97

0.98

0.98

0.96

0.86

0.65

0.65

 

4

0.98

0.74

0.30

0.31

0.94

0.97

0.98

0.98

0.96

0.86

0.64

0.64

100

1

0.98

0.75

0.31

0.30

0.95

0.99

0.99

0.99

0.96

0.87

0.65

0.65

 

2

0.96

0.74

0.28

0.27

0.95

0.98

0.99

0.99

0.96

0.86

0.63

0.63

 

3

0.98

0.74

0.30

0.29

0.95

0.99

0.99

0.99

0.96

0.87

0.64

0.64

 

4

0.98

0.78

0.28

0.28

0.95

0.98

0.99

0.99

0.96

0.88

0.63

0.63

No.TFs

Scenario

Feature selection of edges

Prediction accuracy

TP

TN

Ave

MSE

Pro

NW.P

Pro

NW.P

Pro

NW.P

Pro

NW.P

EL

LA

XGB

NN

5

1

1.00

1.00

1.00

0.92

1.00

0.96

0.522

0.558

0.536

0.531

9.596

2.991

 

2

1.00

1.00

1.00

0.92

1.00

0.96

0.551

0.583

0.550

0.551

9.169

3.001

 

3

1.00

1.00

1.00

0.92

1.00

0.96

0.539

0.588

0.550

0.546

11.543

3.633

 

4

1.00

1.00

1.00

0.93

1.00

0.96

0.538

0.579

0.607

0.595

10.022

3.520

10

1

1.00

1.00

1.00

0.96

1.00

0.98

0.552

0.597

0.612

0.612

10.493

3.994

 

2

1.00

1.00

1.00

0.96

1.00

0.98

0.541

0.566

0.523

0.524

8.880

3.960

 

3

1.00

1.00

1.00

0.96

1.00

0.98

0.551

0.573

0.577

0.573

11.017

4.734

 

4

1.00

1.00

1.00

0.96

1.00

0.98

0.540

0.571

0.605

0.602

9.706

4.816

25

1

1.00

1.00

1.00

0.98

1.00

0.99

0.597

0.621

0.567

0.566

11.130

6.067

 

2

1.00

1.00

1.00

0.98

1.00

0.99

0.552

0.580

0.608

0.610

10.151

6.256

 

3

1.00

1.00

1.00

0.98

1.00

0.99

0.519

0.538

0.613

0.612

12.434

7.857

 

4

1.00

1.00

1.00

0.98

1.00

0.99

0.552

0.579

0.623

0.623

10.790

7.508

50

1

1.00

1.00

1.00

0.99

1.00

1.00

0.600

0.638

0.637

0.637

10.549

12.227

 

2

1.00

1.00

1.00

0.99

1.00

1.00

0.570

0.598

0.639

0.626

9.595

11.736

 

3

1.00

1.00

1.00

0.99

1.00

1.00

0.579

0.601

0.564

0.565

12.086

14.921

 

4

1.00

1.00

1.00

0.99

1.00

1.00

0.537

0.559

0.612

0.617

10.722

14.226

100

1

1.00

1.00

1.00

1.00

1.00

1.00

0.630

0.647

0.612

0.609

12.256

23.636

 

2

1.00

1.00

1.00

1.00

1.00

1.00

0.682

0.684

0.631

0.6338

11.634

21.663

 

3

1.00

1.00

1.00

1.00

1.00

1.00

0.590

0.604

0.617

0.618

14.334

29.831

 

4

1.00

1.00

1.00

1.00

1.00

1.00

0.582

0.585

0.645

0.639

12.218

27.657

  1. Bold numbers indicate an outstanding performance among the methods