Fig. 1From: Machine learning analysis of gene expression profile reveals a novel diagnostic signature for osteoporosisWeighted gene co-expression network analysis (WGCNA). a Clustering of the 90 samples. b Selection of the soft threshold in the WGCNA. The red line represents the correlation coefficient, and the first point above the red line is the soft threshold (β = 14). c Clustering of the gene modules. Each designated color represents a gene module, and the genes that could not be grouped into other modules were placed in the grey module. d The correlation between gene modules and phenotypes. Darker color indicated greater the correlation between gene modules and phenotypesBack to article page