Research Paper Volume 14, Issue 7 pp 3155—3174
A novel classification method for NSCLC based on the background interaction network and the edge-perturbation matrix
Figure 4. Construction and verification of the prognostic-related gene risk scoring model. (A) The forest plot of prognostic genes (univariate cox analysis result). (B) Confidence interval of each Lambda corresponding to LASSO regression. (C) The change trajectory of the independent variable in LASSO regression; the abscissa represents the logarithm of the independent variable Lambda, and the ordinate represents the coefficient of the independent variable. (D) LASSO regression coefficient of key prognostic genes. (E) Z-score heatmap of key prognostic genes expression levels.