Skip to main content

Table 4 Details about the architecture of Deep GONet

From: Deep GONet: self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data

Layer

Input

1

2

3

4

5

6

Output

Total

Level GO-BP

–

7

6

5

4

3

2

–

6

#neurons

54675

1574

1386

951

515

255

90

1

4772

#connections

–

86M

2.2M

1.3M

490K

131K

23K

90

90.1M

#GO connections

–

43504

1709

1585

1010

491

175

–

48K

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us