4.7 Article

Integrated analysis of WGCNA and machine learning identified diagnostic biomarkers in dilated cardiomyopathy with heart failure

Journal

Publisher

FRONTIERS MEDIA SA
DOI: 10.3389/fcell.2022.1089915

Keywords

dilated cardiomyopathy; heart failure; diagnostic biomarker; weighted gene coexpression network analysis; machine learning

Funding

  1. National Natural Science Foundation of China
  2. Shanghai Education Committee, Shanghai Sailing Program of Science and Technology Commission of Shanghai Municipality
  3. Shanghai Ocean University Fund for Science and Technology Development
  4. [32170423]
  5. [31501166]
  6. [14CG49]
  7. [15YF1405000]

Ask authors/readers for more resources

This study identified driver genes highly associated with dilated cardiomyopathy (DCM) with heart failure (HF) and established a diagnostic model using machine learning classifiers. NPPA, OMD, and PRELP were identified as diagnostic biomarkers for DCM with HF, and the TGF-beta signaling pathway was identified as a potential mechanism underlying the condition.
The etiologies and pathogenesis of dilated cardiomyopathy (DCM) with heart failure (HF) remain to be defined. Thus, exploring specific diagnosis biomarkers and mechanisms is urgently needed to improve this situation. In this study, three gene expression profiling datasets (GSE29819, GSE21610, GSE17800) and one single-cell RNA sequencing dataset (GSE95140) were obtained from the Gene Expression Omnibus (GEO) database. GSE29819 and GSE21610 were combined into the training group, while GSE17800 was the test group. We used the weighted gene co-expression network analysis (WGCNA) and identified fifteen driver genes highly associated with DCM with HF in the module. We performed the least absolute shrinkage and selection operator (LASSO) on the driver genes and then constructed five machine learning classifiers (random forest, gradient boosting machine, neural network, eXtreme gradient boosting, and support vector machine). Random forest was the best-performing classifier established on five Lasso-selected genes, which was utilized to select out NPPA, OMD, and PRELP for diagnosing DCM with HF. Moreover, we observed the up-regulation mRNA levels and robust diagnostic accuracies of NPPA, OMD, and PRELP in the training group and test group. Single-cell RNA-seq analysis further demonstrated their stable up-regulation expression patterns in various cardiomyocytes of DCM patients. Besides, through gene set enrichment analysis (GSEA), we found TGF-beta signaling pathway, correlated with NPPA, OMD, and PRELP, was the underlying mechanism of DCM with HF. Overall, our study revealed NPPA, OMD, and PRELP serving as diagnostic biomarkers for DCM with HF, deepening the understanding of its pathogenesis.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available