Department of General Surgery, Qilu Hospital of Shandong University, 107 Wenhuaxi Road, Jinan 250012, Shandong, China.
Contrast Media Mol Imaging. 2023 Feb 5;2023:6457152. doi: 10.1155/2023/6457152. eCollection 2023.
Deep learning techniques are gaining momentum in medical research. Colorectal adenoma (CRA) is a precancerous lesion that may develop into colorectal cancer (CRC) and its etiology and pathogenesis are unclear. This study aims to identify transcriptome differences between CRA and CRC via deep learning on Gene Expression Omnibus (GEO) databases and bioinformatics in the Chinese population.
In this study, three microarray datasets from the GEO database were used to identify the differentially expressed genes (DEGs) and differentially expressed miRNAs (DEMs) in CRA and CRC. The FunRich software was performed to predict the targeted mRNAs of DEMs. The targeted mRNAs were overlapped with DEGs to determine the key DEGs. Molecular mechanisms of CRA and CRC were evaluated using enrichment analysis. Cytoscape was used to construct protein-protein interaction (PPI) and miRNA-mRNA regulatory networks. We analyzed the expression of key DEMs and DEGs, their prognosis, and correlation with immune infiltration based on the Kaplan-Meier plotter, UALCAN, and TIMER databases.
A total of 38 DEGs are obtained after the intersection, including 11 upregulated genes and 27 downregulated genes. The DEGs were involved in the pathways, including epithelial-to-mesenchymal transition, sphingolipid metabolism, and intrinsic pathway for apoptosis. The expression of has-miR-34c ( = 0.036), hsa-miR-320a ( = 0.045), and has-miR-338 ( = 0.0063) was correlated with the prognosis of CRC patients. The expression levels of BCL2, PPM1L, ARHGAP44, and PRKACB in CRC tissues were significantly lower than normal tissues ( < 0.001), while the expression levels of TPD52L2 and WNK4 in CRC tissues were significantly higher than normal tissues ( < 0.01). These key genes are significantly associated with the immune infiltration of CRC.
This preliminary study will help identify patients with CRA and early CRC and establish prevention and monitoring strategies to reduce the incidence of CRC.
深度学习技术在医学研究中逐渐兴起。结直肠腺瘤（CRA）是一种癌前病变，可能发展为结直肠癌（CRC），但其病因和发病机制尚不清楚。本研究旨在通过对中国人群的基因表达综合数据库（GEO）进行深度学习，鉴定 CRA 和 CRC 之间的转录组差异。
本研究使用 GEO 数据库中的三个微阵列数据集，鉴定 CRA 和 CRC 之间差异表达的基因（DEGs）和差异表达的 microRNA（DEMs）。使用 FunRich 软件预测 DEMs 的靶向 mRNAs。将靶向 mRNAs 与 DEGs 重叠，以确定关键的 DEGs。通过富集分析评估 CRA 和 CRC 的分子机制。使用 Cytoscape 构建蛋白质-蛋白质相互作用（PPI）和 miRNA-mRNA 调控网络。我们根据 Kaplan-Meier plotter、UALCAN 和 TIMER 数据库，分析关键 DEMs 和 DEGs 的表达、预后及其与免疫浸润的相关性。
经过交叠，共获得 38 个 DEGs，包括 11 个上调基因和 27 个下调基因。这些 DEGs 参与了上皮间质转化、鞘脂代谢和内在凋亡途径等途径。miR-34c（ = 0.036）、miR-320a（ = 0.045）和 miR-338（ = 0.0063）的表达与 CRC 患者的预后相关。CRC 组织中 BCL2、PPM1L、ARHGAP44 和 PRKACB 的表达水平明显低于正常组织（ < 0.001），而 TPD52L2 和 WNK4 的表达水平明显高于正常组织（ < 0.01）。这些关键基因与 CRC 的免疫浸润显著相关。
本初步研究将有助于鉴定 CRA 和早期 CRC 患者，并制定预防和监测策略，以降低 CRC 的发病率。
