Fig. 7

LASSO regression (A) Ten time cross-validation for tuning parameter selection in the LASSO model. B LASSO coefficient profiles. The method uses an λ penalty to shrink some regression coefficients to exactly zero. The binomial deviance curve was plotted versus -log (λ), where λ is the tuning parameter. C 3 set Venn diagram shows the integration strategy among ceRNA, PPI and LASSO regression. The red circle represents for ceRNA, the blue circle represents for PPI, the green circle represents for LASSO regression. As shown, there were 2 key DE-FRGs (TLR4, PIK3CA)