Research Paper Volume 16, Issue 7 pp 6314—6333

Machine learning identifies novel coagulation genes as diagnostic and immunological biomarkers in ischemic stroke

class="figure-viewer-img"

Figure 1. Identification and functional enrichment analysis of differentially expressed coagulation genes (DECGs). (A) Volcano plot demonstrating an overview of DECGs, in which red dots indicate upregulated CGs in IS. (B) Heatmap showing the increased or decreased expressions of DECGs with the hierarchical clustering for ischemic stroke (IS) and healthy control (HC) groups. The colored column sidebar at the top indicates the type of samples (coral- IS; cyan-HC). (C) Visualization for the predicted results of protein-protein interaction (PPI) network among DECGs via STRING and Cytoscape. Each node represents a protein, and each line refers an interaction. Line thickness indicates the strength of interaction. (D) A functionally grouped network of enriched GO terms and pathways was generated for DECGs by ClueGO. GO terms and pathways are represented as nodes, and the node size is proportional to the enrichment significance. The most significant term (hemostasis) is considered to be the leading term and it is highlighted in the network. (E) Bar chart showing that DECGs were significantly enriched in KEGG pathways of complement and coagulation cascades, tight junction and adherens junction.