Skip to main content

Table 8 Median Delays F-scores of Case III using Multiple Short Time Series with D-CLINDE

From: High-order dynamic Bayesian Network learning with hidden common causes for causal gene regulatory network

n

n h

p bias

K

Complete (C)

Hidden (H)

IgnoreHidden

H/C

p-value

50

5

0.65

4

0.570

0.282

0.378

49.5 %

—

   

8

0.745

0.426

0.533

57.2 %

—

   

16

0.838

0.605

0.609

72.1 %

—

   

32

0.898

0.784

0.657

87.3 %

9.09E-13

   

40

0.905

0.813

0.657

89.8 %

9.09E-13

   

48

0.905

0.828

0.659

91.4 %

9.09E-13

   

56

0.916

0.831

0.655

90.7 %

9.09E-13

   

64

0.918

0.828

0.657

90.2 %

9.09E-13

  

0.75

4

0.692

0.363

0.486

52.4 %

—

   

8

0.806

0.519

0.599

64.4 %

—

   

16

0.871

0.708

0.638

81.2 %

1.82E-12

   

32

0.912

0.786

0.640

86.2 %

9.09E-13

   

40

0.917

0.826

0.641

90.1 %

9.09E-13

   

48

0.919

0.834

0.636

90.8 %

9.09E-13

   

56

0.920

0.853

0.636

92.7 %

9.09E-13

   

64

0.918

0.847

0.626

92.3 %

9.09E-13

  

0.85

4

0.740

0.429

0.535

57.9 %

—

   

8

0.829

0.595

0.611

71.8 %

—

   

16

0.887

0.728

0.638

82.0 %

8.00E-11

   

32

0.915

0.816

0.637

89.2 %

1.82E-12

   

40

0.924

0.834

0.634

90.2 %

9.09E-13

   

48

0.924

0.821

0.634

88.9 %

9.09E-13

   

56

0.925

0.839

0.629

90.7 %

9.09E-13

   

64

0.922

0.850

0.631

92.3 %

9.09E-13

100

10

0.65

4

0.528

0.282

0.335

53.5 %

—

   

8

0.725

0.417

0.509

57.6 %

—

   

16

0.822

0.577

0.594

70.2 %

—

   

32

0.887

0.736

0.644

83.0 %

9.09E-13

   

40

0.894

0.759

0.648

84.9 %

9.09E-13

   

48

0.907

0.777

0.652

85.7 %

9.09E-13

   

56

0.911

0.800

0.654

87.7 %

9.09E-13

   

64

0.915

0.813

0.653

88.9 %

9.09E-13

  

0.75

4

0.676

0.372

0.461

55.0 %

—

   

8

0.807

0.525

0.578

65.0 %

—

   

16

0.873

0.680

0.630

77.9 %

6.93E-10

   

32

0.910

0.784

0.648

86.2 %

9.09E-13

   

40

0.915

0.813

0.642

88.9 %

9.09E-13

   

48

0.917

0.828

0.643

90.3 %

9.09E-13

   

56

0.922

0.822

0.642

89.2 %

9.09E-13

   

64

0.923

0.836

0.635

90.6 %

9.09E-13

  

0.85

4

0.731

0.428

0.517

58.5 %

—

   

8

0.829

0.564

0.591

68.0 %

—

   

16

0.884

0.714

0.627

80.8 %

9.09E-13

   

32

0.911

0.772

0.628

84.7 %

9.09E-13

   

40

0.919

0.787

0.622

85.6 %

9.09E-13

   

48

0.921

0.793

0.622

86.1 %

9.09E-13

   

56

0.922

0.786

0.622

85.3 %

9.09E-13

   

64

0.927

0.792

0.620

85.4 %

9.09E-13

  1. Complete is D-CLINDE on the complete data. hidden is our proposed algorithm with D-CLINDE on the incomplete data. ignoreHidden is D-CLINDE on the incomplete data. p-value is for one-sided Wilcoxon signed rank test on whether the median F-score of hidden is better than ignoreHidden, and entries larger than 0.1 are omitted. H/C is the ratio of hidden over complete as percentage.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us