Fig. 3From: Bioinformatic analysis of underlying mechanisms of Kawasaki disease via Weighted Gene Correlation Network Analysis (WGCNA) and the Least Absolute Shrinkage and Selection Operator method (LASSO) regression modelScreening of node genes. A PPI network map of 80 genes, which includes 33 nodes and 43 edges. Light brown circles stand for common genes appearing in the five algorithms. B LASSO model. λ = λ.1se, mean-squared error (MSE) = 0.02655. C The variation of coefficients of hub genes with different Log λ. ROC curves of the seven genes alone (ADM, ALPL, BCL6, HK3, MMP9, PYGL and S100A12) in both the training set (D) and validation set (GS18606) (E)Back to article page