Fig. 3

The prognostic model could efficiently predict the survival of HCC patients. a The distribution of risk scores of TCGA training set samples on the left. A point represents a sample, the red point indicates the sample with high risk score, the green point indicates the sample with low risk score, and the intersection point is the optimal risk score; the clustering heatmap of mRNA expression of selected NRs in the TCGA training set on the second left. The rows represent genes, the columns represent samples, red indicates high expression, blue indicates low expression, and the categories of samples are marked with different colors on the top of the heatmap; the Kaplan-Meier survival curve of the TCGA training set was performed on the third left. The horizontal axis represents time, the vertical axis represents survival rate, and the color represents different groups; the time-dependent ROC curve of TCGA training set on the right. The horizontal axis represents false positive, and the vertical axis represents true positive. The accuracy of prediction is evaluated by the value of AUC (the area under ROC curve). b The distribution of risk scores on TCGA testing set samples; the clustering heatmap of mRNAs expression on TCGA testing set samples; the Kaplan-Meier survival curve and the time-dependent ROC curve on TCGA testing set samples. c The distribution of risk scores on TCGA testing set samples; the clustering heatmap of mRNAs expression on TCGA testing set samples; the Kaplan-Meier survival curve and the time-dependent ROC curve on ICGC testing set samples