Fig. 6

Screening for hub MERGs. A LASSO coefficient profiles of the 44 MERGs. B Tenfold cross-validation was performed to identify the optimal tuning parameter (λ). C Graphical representation depicting the impact of the decision tree count on the model error. D The Gini coefficient method random forest classifier was used to filter results. E Venn diagram of the shared genes between the random forest and LASSO algorithm datasets