Research Paper Volume 13, Issue 1 pp 794—812

Systematic construction and validation of an epithelial–mesenchymal transition risk model to predict prognosis of lung adenocarcinoma

Predictive value of the ERG signature for LUAD in the training set (TCGA). (A) Value of each coefficient representing its relative contribution to the predictive signature. (B) Heatmap of the mRNA expression levels of the nine signature-comprising ERGs. (C) Rank of risk signature and score distribution. (D) Distribution of patients in the low- and high-risk groups based on their survival status (OS). (E) OS times of the patients between high- and low-risk groups. (F) Time-dependent ROC curve analysis for the prediction of 1-, 3-, and 5-year OS using the ERG signature. (G) Univariate Cox regression analysis of the ERG signature and clinical features of the patients. (H) Multivariate Cox regression analysis of the ERG signature and clinical features of the patients.

Figure 4. Predictive value of the ERG signature for LUAD in the training set (TCGA). (A) Value of each coefficient representing its relative contribution to the predictive signature. (B) Heatmap of the mRNA expression levels of the nine signature-comprising ERGs. (C) Rank of risk signature and score distribution. (D) Distribution of patients in the low- and high-risk groups based on their survival status (OS). (E) OS times of the patients between high- and low-risk groups. (F) Time-dependent ROC curve analysis for the prediction of 1-, 3-, and 5-year OS using the ERG signature. (G) Univariate Cox regression analysis of the ERG signature and clinical features of the patients. (H) Multivariate Cox regression analysis of the ERG signature and clinical features of the patients.