Isfahan University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Integrative Analysis of Dna Methylation and Gene Expression Through Machine Learning Identifies Stomach Cancer Diagnostic and Prognostic Biomarkers Publisher Pubmed



Hosseini M1 ; Lotfishahreza M2 ; Nikpour P1
Authors
Show Affiliations
Authors Affiliations
  1. 1. Department of Genetics and Molecular Biology, Faculty of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
  2. 2. Department of Computer Engineering, University of Isfahan, Shahreza Campus, Isfahan, Iran

Source: Journal of Cellular and Molecular Medicine Published:2023


Abstract

DNA methylation is an early event in tumorigenesis. Here, by integrative analysis of DNA methylation and gene expression and utilizing machine learning approaches, we introduced potential diagnostic and prognostic methylation signatures for stomach cancer. Differentially-methylated positions (DMPs) and differentially-expressed genes (DEGs) were identified using The Cancer Genome Atlas (TCGA) stomach adenocarcinoma (STAD) data. A total of 256 DMPs consisting of 140 and 116 hyper- and hypomethylated positions were identified between 443 tumour and 27 nontumour STAD samples. Gene expression analysis revealed a total of 2821 DEGs with 1247 upregulated and 1574 downregulated genes. By analysing the impact of cis and trans regulation of methylation on gene expression, a dominant negative correlation between methylation and expression was observed, while for trans regulation, in hypermethylated and hypomethylated genes, there was mainly a negative and positive correlation with gene expression, respectively. To find diagnostic biomarkers, we used 28 hypermethylated probes locating in the promoter of 27 downregulated genes. By implementing a feature selection approach, eight probes were selected and then used to build a support vector machine diagnostic model, which had an area under the curve of 0.99 and 0.97 in the training and validation (GSE30601 with 203 tumour and 94 nontumour samples) cohorts, respectively. Using 412 TCGA-STAD samples with both methylation and clinical data, we also identified four prognostic probes by implementing univariate and multivariate Cox regression analysis. In summary, our study introduced potential diagnostic and prognostic biomarkers for STAD, which demands further validation. © 2023 The Authors. Journal of Cellular and Molecular Medicine published by Foundation for Cellular and Molecular Medicine and John Wiley & Sons Ltd.
Experts (# of related papers)
Other Related Docs
15. Deregulation of Mtdh Gene Expression in Gastric Cancer, Asian Pacific Journal of Cancer Prevention (2012)
35. Novel Somatic Variants in Ctnna1 Gene in Iranian Patients With Diffuse Gastric Cancer, Gastroenterology and Hepatology from Bed to Bench (2021)
38. Msi1 Overexpression in Diffuse Type of Gastric Cancer, Pathology Research and Practice (2013)