Identification of diagnostic biomarkers in patients with gestational diabetes mellitus based on transcriptome gene expression and methylation correlation analysis

Abstract

BackgroundGestational diabetes mellitus (GDM) has a high prevalence in the period of pregnancy. However, the lack of gold standards in current screening and diagnostic methods posed the biggest limitation. Regulation of gene expression caused by DNA methylation plays an important role in metabolic diseases. In this study, we aimed to screen GDM diagnostic markers, and establish a diagnostic model for predicting GDM.MethodsFirst, we acquired data of DNA methylation and gene expression in GDM samples (N = 41) and normal samples (N = 41) from the Gene Expression Omnibus (GEO) database. After pre-processing the data, linear models were used to identify differentially expressed genes (DEGs). Then we performed pathway enrichment analysis to extract relationships among genes from pathways, construct pathway networks, and further analyzed the relationship between gene expression and methylation of promoter regions. We screened for genes which are significantly negatively correlated with methylation and established mRNA-mRNA-CpGs network. The network topology was further analyzed to screen hub genes which were recognized as robust GDM biomarkers. Finally, the samples were randomly divided into training set (N = 28) and internal verification set (N = 27), and the support vector machine (SVM) ten-fold cross-validation method was used to establish a diagnostic classifier, which verified on internal and external data sets.ResultsIn this study, we identified 465 significant DEGs. Functional enrichment analysis revealed that these genes were associated with Type I diabetes mellitus and immunization. And we constructed an interactional network including 1091 genes by using the regulatory relationships of all 30 enriched pathways. 184 epigenetics regulated genes were screened by analyzing the relationship between gene expression and promoter regions’ methylation in the network. Moreover, the accuracy rate in the training data set was increased up to 96.3, and 82.1% in the internal validation set, and 97.3% in external validation data sets after establishing diagnostic classifiers which were performed by analyzing the gene expression profiles of obtained 10 hub genes from this network, combined with SVM.ConclusionsThis study provided new features for the diagnosis of GDM and may contribute to the diagnosis and personalized treatment of GDM.

Data-Driven Modeling of Pregnancy-Related Complications

“…This is illustrated by a study on modeling GA [114] using stacked generalization [115] to integrate biological signals across seven different omics. In another study, the incorporation of transcriptomic and epigenetic data was shown to increase performance in the identification of GDM in addition to helping in the elucidation of its biological basis [116]. However, the individual characteristics of different omics as well as their inherent differences in numbers of features (e.g., sparse microbiome data versus targeted proteomics assays) pose unique challenges for their integration into statistical models.…”

Identification of Diagnostic CpG Signatures in Patients with Gestational Diabetes Mellitus via Epigenome-Wide Association Study Integrated with Machine Learning

“…As a widely applied machine learning algorithm, SVM is reported to be used in the investigation of GDM. It has been reported that SVM is applied in the identification of diagnostic biomarkers in patients with GDM based on transcriptome gene expression and methylation analysis [ 7 ]. The artificial immune recognition system and SVM model contribute to predicting GDM [ 77 ].…”

“…Although the progression of GDM has been investigated for decades, the practical and well-designed diagnostic models for the clinical prediction of GDM are extremely limited [ 6 ]. Therefore, it is essential to find effective biomarkers for improving the diagnosis and alleviating the adverse pregnancy outcomes of GDM [ 7 , 8 ]. However, the advancement of this research field is still poor.…”

“…Machine learning is a category of information science that trains the computer to execute tasks by recognizing patterns in massive datasets and using them to determine rules or algorithms that optimize task achievement [ 24 ]. It has been reported that machine learning is beneficial to the discovery of predictive biomarkers and diagnosis of GDM [ 7 , 25 – 27 ]. Support vector machine (SVM) is a practical machine learning model and has been confirmed to be useful classifiers in all kinds of fields, including face recognition, handwritten digit recognition, text classification, and bioinformatics [ 28 ].…”

Identification of Key Candidate Genes and Chemical Perturbagens in Diabetic Kidney Disease Using Integrated Bioinformatics Analysis

“…It has also been used in identifying the chemical perturbagens capable of intervening the critical molecular pathways in diseased conditions. For example, the genomics and transcriptomics data profiling has helped in elucidating the pathogenesis of diabetes (15)(16)(17) and in identifying potential new mechanisms in DN (18,19). However, there are only a few studies that shed light on the potential pathogenesis mechanism and cross-talks between GDKD, TDKD and early diabetic nephropathy (EDN).…”