Research Article

Screening of Hub Genes in Hepatocellular Carcinoma Based on Network Analysis and Machine Learning

Figure 5

(a) Power value screening by WGCNA. (b) Module-feature correlation. Each row corresponds to a module, and each column corresponds to a feature, including the corresponding correlation and value. The characteristics represented by letters are (A) age at initial pathological diagnosis, (B) bilirubin lower limit, (C) bilirubin upper limit, (D) surv time, (E) fetoprotein output value, and (F) total bilirubin upper limit. (c) Module characteristic gene clustering heat map. (d) Tom diagram in the module. Dark color indicates topological overlap, and light color indicates high topological overlap.