A transcriptomic study for identifying cardia- and non-cardia-specific gastric cancer prognostic factors using genetic algorithm-based methods.

摘要: Gastric cancer (GC) is a heterogeneous tumour with numerous differences of epidemiologic and clinicopathologic features between cardia non-cardia cancer. However, few studies were performed to construct site-specific GC prognostic models. In this study, we identified transcriptomic biomarkers using genetic algorithm (GA)-based support vector machine (GA-SVM) GA-based Cox regression method (GA-Cox) in the Cancer Genome Atlas (TCGA) database. The area under time-dependent receive operating characteristic (ROC) curve (AUC) regarding 5-year survival concordance index (C-index) was used evaluate predictive ability Finally, 10 13 for cancer, respectively. Compared traditional models, addition these could notably improve model preference (cardia: AUCtraditional vs AUCcombined  = 0.720 0.899, P = 8.75E-08; non-cardia:  = 0.798 0.994, P = 7.11E-16). combined nomograms exhibited superior performance prediction (C-indexcardia  = 0.816; C-indexnoncardia  = 0.812). We also constructed user-friendly molecular system (GC-SMS, https://njmu-zhanglab.shinyapps.io/gc_sms/), which freely available users. conclusion, developed models predicting survival, providing more individualized therapy patients.