Department for Bioinformatics, School of Life Sciences, Pondicherry University, Puducherry, India.
OMICS. 2023 Jun;27(6):260-272. doi: 10.1089/omi.2023.0015. Epub 2023 May 25.
Gastric cancer (GC) is among the leading causes of cancer-related deaths worldwide. The discovery of robust diagnostic biomarkers for GC remains a challenge. This study sought to identify biomarker candidates for GC by integrating machine learning (ML) and bioinformatics approaches. Transcriptome profiles of patients with GC were analyzed to identify differentially expressed genes between the tumor and adjacent normal tissues. Subsequently, we constructed protein-protein interaction networks so as to find the significant hub genes. Along with the bioinformatics integration of ML methods such as support vector machine, the recursive feature elimination was used to select the most informative genes. The analysis unraveled 160 significant genes, with 88 upregulated and 72 downregulated, 10 hub genes, and 12 features from the variable selection method. The integrated analyses found that , , , and genes are significant and poised as potential diagnostic biomarkers in relation to GC. The receiver operating characteristic curve analysis found and are strongly associated with diagnosis of GC. We suggest and are considered as biomarker candidates that might potentially inform future research on diagnosis, prognosis, or therapeutic targets for GC. These findings collectively offer new future possibilities for precision/personalized medicine research and development for patients with GC.
胃癌（GC）是全球癌症相关死亡的主要原因之一。发现稳健的 GC 诊断生物标志物仍然是一个挑战。本研究旨在通过整合机器学习（ML）和生物信息学方法来鉴定 GC 的生物标志物候选物。分析 GC 患者的转录组谱，以鉴定肿瘤与相邻正常组织之间的差异表达基因。随后，我们构建了蛋白质-蛋白质相互作用网络，以找到重要的枢纽基因。通过支持向量机等 ML 方法的生物信息学整合，递归特征消除用于选择最具信息量的基因。分析揭示了 160 个显著基因，其中 88 个上调，72 个下调，10 个枢纽基因和 12 个来自变量选择方法的特征。综合分析发现 、 、 和 基因与 GC 相关，是潜在的诊断生物标志物。受试者工作特征曲线分析发现 和 与 GC 的诊断密切相关。我们建议将 和 视为生物标志物候选物，这可能为未来 GC 的诊断、预后或治疗靶点的研究提供新的可能性。这些发现为 GC 患者的精准/个性化医学研究和开发提供了新的未来可能性。
