Skip to main content
Fig. 2 | Molecular Cancer

Fig. 2

From: A liquid biopsy signature of circulating exosome-derived mRNAs, miRNAs and lncRNAs predict therapeutic efficacy to neoadjuvant chemotherapy in patients with advanced gastric cancer

Fig. 2

Establishment and validation of a 6-exosome-RNA model. A The linear correlation analysis of 8 validated exosomal biomarkers. B The most robust predictive genes were identified using the least absolute shrinkage and selection operator (LASSO) Cox regression algorithm. C An ensemble of 6 genes remained with nonzero coefficients. D The scores of enrolled patients in the training set which were calculated based on the 6-exosome-RNA model. E-F The boxplot and the receiver operating characteristic (ROC) analyses illustrated the predictive ability of this 6-exosome-RNA model to identify responders in the training set. G The patients’ scores in the validating set calculated according to the 6-exosome-RNA model. H The ROC analysis for the predictive power of the focal 6-exosome-RNA model, and the area under the ROC curve was 0.774

Back to article page