Skip to main content

Table 5 Proposed network performance with log normalization

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

     F1 PRECISION RECALL
Architecture Number of nodes
2nd layer
Accuracy Balanced accuracy Macro Micro Weighted Macro Micro Weighted Macro Micro Weighted
Dense 0.938 0.839 0.859 0.938 0.934 0.923 0.938 0.938 0.839 0.938 0.938
Pathways 0.936 0.844 0.861 0.936 0.933 0.922 0.936 0.938 0.844 0.936 0.936
Pathways 100 0.930 0.834 0.847 0.930 0.926 0.901 0.930 0.932 0.834 0.930 0.930