Research Paper Volume 15, Issue 20 pp 11244—11267
CDKN2A was a cuproptosis-related gene in regulating chemotherapy resistance by the MAGE-A family in breast cancer: based on artificial intelligence (AI)-constructed pan-cancer risk model
Figure 10. CRG-TDGs-based nomogram construction. (A) LASSO analysis. (B) Multivariate cox regression selected ARID1A, ARID1B, BCLAF1, BRCA2, CDK12, CDKN2A, DICER1, INO80, NPRL2, PRDM2, RBM10, TRAF3, TRIM33, and TRIP11 to construct multi-gene risk model, of which the C-index is 0.7 (log-rank p=6.9582e-12). (C) K-M analysis showed the prognosis difference between the high-risk group and the low-risk group, and (D) the gene expression profile is also explored. ROC analysis is performed to assess the prediction efficiency of the risk model in (E) the GEO cohort and (F) the TCGA cohort. (G) Univariate cox regression displayed that T stage, N stage, and M stage are all prognosis-related factors in the GEO breast cancer cohort, while (H) multivariate cox regression displayed only T stage, N stage, and risk-score are prognosis-related factors. (I) The multivariate cox regression model visualization display. ROC analysis is performed to assess the prediction efficiency of the nomogram in (J) the GEO cohort and (K) the TCGA cohort. (L) Calibration of GEO-based NOMOGRAM.