Identification of Key MicroRNAs and Genes between Colorectal Adenoma and Colorectal Cancer via Deep Learning on GEO Databases and Bioinformatics

Abstract

Background. 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. Methods. 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. Results. 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 ( $P=0.036$ ), hsa-miR-320a ( $P=0.045$ ), and has-miR-338 ( $P=0.0063$ ) 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 ( $P<0.001$ ), while the expression levels of TPD52L2 and WNK4 in CRC tissues were significantly higher than normal tissues ( $P<0.01$ ). These key genes are significantly associated with the immune infiltration of CRC. Conclusion. This preliminary study will help identify patients with CRA and early CRC and establish prevention and monitoring strategies to reduce the incidence of CRC.