Identification of Gene Signatures Differentiating Cancer from Normal Tissues Across Histological Classifications of Gastric Adenocarcinoma via Machine Learning Methods.

Gastric adenocarcinoma is a significant global health concern. Among the myriad histologic classification methods for this cancer, the Lauren classification stands out as a pivotal tool. Nonetheless, the precision and detail of current histological staging techniques frequently face scrutiny. Utilizing high-resolution single-cell transcriptomic data, this research delves into the distinctive gene expression patterns in diffuse, intestinal, and mixed gastric cancers by deploying various machine learning algorithms. The main goal was to recognize important gene markers and establish efficient classification models. The data was derived from the tumor microenvironment, with cells categorized into six groups according to two locations: tumoral and normal, and three histology types: diffuse, intestinal, and mixed. Every cell describes the expression level of 56,265 genes. We integrated seven feature selection algorithms and four classification algorithms, which increased the accuracy of classification. Importantly, our approach detected intricate expression patterns realized for the first time-for example, high expression of CLDN4 in intestinal-type gastric cancers and CCL4 and CXCR4 in diffuse-type gastric cancers. The identified gene markers and gene expression patterns provide insights into subtype-specific molecular characteristics of gastric cancer. These candidate markers may serve as a foundation for future studies aimed at validating their utility in subtype classification and clinical stratification.