Fig. 3From: A machine learning approach for the identification of key markers involved in brain development from single-cell transcriptomic dataGRN in NPCs (a) neuronal cells (b) and differential GRN between the two cell types. a GRN in NPCs. Nodes represent transcripts, while links between two nodes represent regulatory interactions between two transcripts in NPCs. Gene regulatory interactions with high confidence score (confidence score > 0.75) in NPCs are shown in the diagram. b GRN in neuronal cells. Nodes represent transcripts, while links between two nodes represent regulatory interactions between two transcripts in neuronal cells. Gene regulatory interactions with high confidence score (confidence score > 0.75) in neuronal cells are shown in the diagram. c Differential GRN between two cell lines. Nodes are transcripts. Red links represent gene regulatory interactions that are activated in neuronal cells but not activated in NPCs, while blue links represents those activated in NPCs but not in neuronal cells. In this diagram, we assumed that a regulatory interaction is activated in neuronal cells (or NPCs) but is not activated in NPCs (or neuronal cells), if difference in confidence score between the two cell types is greater than 0.75, eg, an interaction whose confidence scores are 0.99 and 0.20 in neuronal cells and NPCs, respectively. Note that OTP is a representative DHG (see Table 3) and thus the gene is highlighted in redBack to article page