Skip to main content

Table 1 Details of input and hidden layers, as well as parameters for each architecture used

From: Integrating pathway knowledge with deep neural networks to reduce the dimensionality in single-cell RNA-seq data

Dataset

Architecture

Nodes Layer 1

Nodes layer 2

Effective parameters (million)

 

Dense

100

–

0.95 M

Dense + pathway

100 + 92

–

0.95 M

Dense + PPI

100 + 348

–

0.96 M

Mouse

Dense + PPI and GRN

100 + 696

–

1.01 M

 

Dense + PPI and GRN

100 + 696

100

1.08 M

Pathway

92

–

0.01 M

Pathway

92

100

0.02 M

Dense

100

–

1.80 M

Human

Pathway

93

–

0.01 M

 

Pathway

93

100

0.02 M