Saliva-based Biomarkers for Predicting Gastric Cancer

Saliva-based biomarkers offer a non-invasive, convenient, and patient-friendly approach for gastric cancer (GC) diagnosis, eliminating the need for uncomfortable procedures. This study aimed to identify salivary extracellular RNA (exRNA) biomarkers capable of distinguishing GC from normal samples. We used GEO dataset containing exRNA expression profiles of 98 GC and 100 normal samples. We filtered the data and applied the Mann-Whitney U test to identify statistically significant salivary exRNAs (p < 0.05). Initially, a single gene-based classification method identified potential biomarkers including GSDMA, SMR3B, NPTXR, TBCD, KCNC4, and KRT26, achieving accuracies ranging from 61.61% to 64.14%. Then, we applied AI-based methods to identify GC biomarkers. We developed machine learning models on different sets of biomarkers extracted from the original set of statistically significant exRNA using feature selection methods. An optimal primary biomarker set of eight mRNAs (GSDMA, CCDC141, TBCD, STARD13, WRB, ARHGAP23, CDHR3, BX842679.1) was identified, yielding an AUC of 0.905 and MCC of 0.770 with an ensemble stacking classifier. We performed comparative analysis with existing GC biomarker studies which demonstrated that our identified primary biomarker set outperformed previously reported biomarker panels. Out of the eight identified genes, seven have been reported in the literature to be associated with Gastric Cancer. Our results demonstrate the potential of salivary exRNA biomarkers as a non-invasive tool for GC diagnosis. Key pointsO_LIGC is often diagnosed at advanced stages using invasive procedures C_LIO_LISalivary exRNA has potential for non-invasive GC detection C_LIO_LIA machine learning model was developed to predict GC C_LIO_LIA panel of 8 salivary exRNA biomarkers for GC were identified C_LIO_LIThe biomarker panel outperformed existing salivary biomarkers for GC C_LI