Fig. 3

Identification of biomarkers. a Importance scores of the features obtained from the XGBoost model trained with the DE-m7G-lncRNAs. Features are listed in descending order of their importance scores, and only the top 10 features are shown in the figure. b Feature selection analyzed by Boruta algorithm. The horizontal axis is the name of each variable, and the vertical axis is the Z-value of each variable. The box plot shows the Z-value of each variable in the model calculation. The green boxes represent the 38 important variables, the yellow represents tentative attributes, and the red represents unimportant variables. c Venn diagram displaying the intersection results of the top 10 feature lncRNAs obtained from the Boruta and XGBoost algorithms