Gastric cancer is the primary cause of cancer-related fatalities worldwide, and early identification and prognosis are critical to effective treatment. Recent years have seen the emergence of machine learning algorithms as potent tools for deciphering complicated medical data, such as genomes and imaging data, and enhancing the detection and management of cancer. In this study, the authors analysed gene expression data from gene samples and clinical data from patients with stomach cancer using a combination of supervised and unsupervised machine learning techniques. They identified a set of gene name that were significantly associated with patient survival and used these genes to build a prognostic model with high accuracy in predicting patient outcomes. The first step analyzed the gene expression profiles from a publicly available gastric cancer dataset. Then we involve constructing a protein-protein interaction network using available data on protein interactions relevant to gastric cancer. This network represents the complex relationships and interactions between different proteins involved in the disease. Next, graph analysis algorithms are applied to identify the central or highly connected proteins within the network. These proteins, referred to as hub proteins, may be useful as therapeutic targets and are anticipated to have a major impact on the course of gastric cancer. The discovered hub proteins may be useful in illuminating the fundamental mechanisms of and serving as prospective targets for medication development and therapy. strategies.