Skip to main content

Table 4 Power of GENN to detect primary genetic model in data with genetic heterogeneity.

From: Power of grammatical evolution neural networks to detect gene-gene interactions in the presence of error

Source of Noise

Power (%) to Detect Primary Model (5,10)

 

Model 1

Model 2

Model 3

Model 4

Model 5

Model 6

GH

34

49

20

13

8

11

GE+GH

48

49

20

13

8

10

GH+PC

10

11

3

0

4

3

GH+MS

31

35

12

11

9

9

GE+GH+PC

11

8

3

0

1

2

GE+GH+MS

43

29

13

7

8

5

GH+PC+MS

3

8

3

1

5

3

GE+GH+PC+MS

4

8

1

3

0

2

  1. GE = 5% Genotyping Error; GH = 50% Genetic Heterogeneity; PC = 50% Phenocopy; MS = 5% Missing Data