Fig. 6: Prognostic model based on PGAM2-regulated genes and sialylation. | npj Precision Oncology

Fig. 6: Prognostic model based on PGAM2-regulated genes and sialylation.

From: Machine learning-driven comprehensive profiling of tumor heterogeneity and sialylation in hepatocellular carcinoma

Fig. 6

A Forest plot showing the results of univariate Cox regression analysis for 12 genes associated with survival, selected from the PGAM2-related transcription factor TARGET gene chain (importance > 10) and sialylation-related genes. B LASSO-Cox regression analysis to select prognostic genes, leading to the identification of a risk model based on 9 genes. C Multivariate Cox regression analysis and forest plot showing the hazard ratios for each prognostic gene. D Bar plot displaying the Coef of the 9 prognostic genes used to calculate risk scores. E, F Risk score vs survival time scatter plot and heatmap showing the expression of prognostic genes across different risk groups. G PCA plot showing dimensionality reduction of prognostic genes, visualizing the separation between high- and low-risk groups. H Time-dependent ROC curves for 1, 3, and 5 years, demonstrating the predictive accuracy of the risk model. I Kaplan–Meier survival curve comparing high-risk and low-risk groups.

Back to article page