Fig. 6: The construction and validation of predictive classifiers. | Nature Communications

Fig. 6: The construction and validation of predictive classifiers.

From: Proteomic characterization of gastric cancer response to chemotherapy and targeted therapy reveals potential therapeutic strategies

Fig. 6

a Diagram describing a construction and validation of the predictive modeling for sensitive (S) and non-sensitive (NS) groups. b The discovery cohort: Classification error matrix using logistic regression classifier of 80% training set and 20% testing set in DOS, XELOX, and HER2 subcohorts. The number of samples identified is noted in each box. c Heatmap showing differential expression of DSG/DNSG-sig, XSG/XNSG-sig, and HSG/HNSG-sig based on PRM quantification in an independent cohort (validation cohort) composed of 60 GC patients (two-sided Wilcoxon rank-sum test). Source data are provided as a Source Data file.

Back to article page