Screening for gastric cancer (GC) is critical for improving patient survival, yet current clinical methods suffer from invasiveness and limited sensitivity. The aim of this study is to develop a machine learning model for the non-invasive diagnosis of GC using the whole-genome methylation profile of circulating free DNA (cfDNA) in plasma. Plasma cfDNA from 61 patients with GC and 29 healthy controls. First, whole‑genome bisulfite sequencing (WGBS) was performed on 29 paired GC and adjacent normal tissues to identify differentially methylated regions (DMRs). These tissue DMRs were then mapped to plasma cfDNA methylation data, yielding 32 stable DMRs that changed consistently in both tissues and plasma. Using LASSO and Random Forest (RF) algorithms, eight core diagnostic markers were selected. Four machine learning algorithms (Support Vector Machine, RF, K-Nearest Neighbor, Naïve Bayes) were used to build diagnostic models. WGBS revealed global hypomethylation and CpG island hypermethylation in GC, consistent with plasma cfDNA methylation patterns. The RF model built on the eight cfDNA methylation markers (annotated to genes including ATP8A2) performed best, achieving AUC values of 0.978 and 0.938 in the training and independent test sets, respectively, with an accuracy of 88.46%, sensitivity of 94.44%, and specificity of 75.00%. After adjusting for age, the model achieved an AUC of 0.924 on the test set, still demonstrating high discriminatory performance. Functional analysis implicated these markers in pathways such as phagocytosis and axon guidance, and showed significant correlation with immune cell infiltration. Notably, these core DMRs are not covered by the probes on the methylation arrays (450K and EPIC v2), highlighting the advantage of WGBS for novel biomarker discovery. In conclusion, tissue-plasma concordance analysis identified a panel of plasma cfDNA methylation biomarkers with strong diagnostic potential. The resulting RF model provides a promising non-invasive strategy for GC screening.

Background: While cadherin (CDH) genes are aberrantly expressed in cancers, the functions of CDH genes in gastric cancer (GC) remain poorly understood. The clinical significance and molecular mechanisms of CDH genes in GC were assessed in this study.Methods: Data from a total of 1226 GC patients included in The Cancer Genome Atlas (TCGA) and Kaplan-Meier plotter database were used to independently explore the value of CDH genes in clinical application. The TCGA RNA sequencing dataset was used to explore the molecular mechanisms of CDH genes in GC.Results: Using enrichment analysis tools, CDH genes were found to be related to cell adhesion and calcium ion binding in function. In TCGA cohort, 12 genes were found to be differentially expressed between GC para-carcinoma and tumor tissue. By analyzing GC patients in two independent cohorts, we identified and verified that CDH2, CDH6, CDH7 and CDH10 were significantly associated with a poor GC prognosis. In addition, CDH2 and CDH6 were used to construct a GC risk score signature that can significantly improve the accuracy of predicting the 5-year survival of GC patients. The GSEA approach was used to explore the functional mechanisms of the four prognostic CDH genes and their associated risk scores. It was found that these genes may be involved in multiple classic cancer-related signaling pathways, such as the Wnt and phosphoinositide 3-kinase signaling pathways in GC. In the subsequent CMap analysis, three small molecule compounds (anisomycin, nystatin and bumetanide) that may be the target molecules that determine the risk score in GC, were initially screened. Conclusions: Our current study suggests that four CDH genes can be used as potential biomarkers for GC prognosis. In addition, a prognostic signature based on the CDH2 and CDH6 genes was constructed, and their potential functional mechanisms and drug interactions explored.