Fig. 3

Construction and verification of NAC prognostic risk model. A: Forest map shows the results of the univariate analysis of the top 10 NAC-related key genes; B: LASSO coefficient profiles of the prognostic genes. Change track of each independent variable in LASSO Cox regression analysis. The horizontal axis represents the log value of the independent variable lambda, and the vertical axis represents the coefficient of the independent variable; C: Cross-validation for turning parameter selection in the LASSO regression model. Two vertical dashed lines indicated the optimal values using the minimum criteria. Optimal genes with the best discriminative capability were selected for developing the Prognostic model; D: LASSO regression coefficients of the 9 optimized genes for constructing the prognostic model; E: Risk score distribution for each sample in the GSE25055 cohort; F: Kaplan-Meier curves comparing the OS of patients separated by risk groups, the red line represents line the high-risk score group, while the blue line represents the low-risk score group; G: Expression of the 9 prognostic model genes in the GSE25055 cohort between high- and low-risk group; H: Time-dependent receiver operating characteristic (ROC) curve of the prognostic model