NF-κB-Related Metabolic Gene Signature Predicts the Prognosis and Immunotherapy Response in Gastric Cancer

Figure 3

Identification of candidate NFMGs. (a) Cross-validation for tuning parameter screening in the LASSO regression model. (b) Log (lambda) value of the 27 NFMGs in the LASSO regression model. (c) Parameter diagram of the RFE algorithm. The smaller the RMSE, the less the error of the RFE model. The corresponding genes with least RMSE were selected. (d) Venn diagram showed the overlapped NFMGs between LASSO and RFE algorithms. (e) Pearson correlation analysis between the candidate NFMGs and NF-κB transcription factor. NFMGs: NF-κB targeted metabolic genes; LASSO: least absolute shrinkage and selection operator; RFE: recursive feature elimination; RMSE: root mean square error; adj. . val: adjusted value; PCC: Pearson correlation coefficient.

(a)

(b)

(c)

(d)

(e)