Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Oct 11:9:993142.
doi: 10.3389/fcvm.2022.993142. eCollection 2022.

Identification of energy metabolism-related biomarkers for risk prediction of heart failure patients using random forest algorithm

Hao Chen  1   2   3 , Rui Jiang  1   2 , Wentao Huang  1   3 , Kequan Chen  4 , Ruijie Zeng  1 , Huihuan Wu  1   2 , Qi Yang  1 , Kehang Guo  1 , Jingwei Li  1 , Rui Wei  5 , Songyan Liao  5 , Hung-Fat Tse  5 , Weihong Sha  1   2   3 , Zewei Zhuo  1
Affiliations

Identification of energy metabolism-related biomarkers for risk prediction of heart failure patients using random forest algorithm

Hao Chen et al. Front Cardiovasc Med. .

Abstract

Objective: Energy metabolism plays a crucial role in the improvement of heart dysfunction as well as the development of heart failure (HF). The current study is designed to identify energy metabolism-related diagnostic biomarkers for predicting the risk of HF due to myocardial infarction.

Methods: Transcriptome sequencing data of HF patients and non-heart failure (NF) people (GSE66360 and GSE59867) were obtained from gene expression omnibus (GEO) database. Energy metabolism-related differentially expressed genes (DEGs) were screened between HF and NF samples. The subtyping consistency analysis was performed to enable the samples to be grouped. The immune infiltration level among subtypes was assessed by single sample gene set enrichment analysis (ssGSEA). Random forest algorithm (RF) and support vector machine (SVM) were applied to identify diagnostic biomarkers, and the receiver operating characteristic curves (ROC) was plotted to validate the accuracy. Predictive nomogram was constructed and validated based on the result of the RF. Drug screening and gene-miRNA network were analyzed to predict the energy metabolism-related drugs and potential molecular mechanism.

Results: A total of 22 energy metabolism-related DEGs were identified between HF and NF patients. The clustering analysis showed that HF patients could be classified into two subtypes based on the energy metabolism-related genes, and functional analyses demonstrated that the identified DEGs among two clusters were mainly involved in immune response regulating signaling pathway and lipid and atherosclerosis. ssGSEA analysis revealed that there were significant differences in the infiltration levels of immune cells between two subtypes of HF patients. Random-forest and support vector machine algorithm eventually identified ten diagnostic markers (MEF2D, RXRA, PPARA, FOXO1, PPARD, PPP3CB, MAPK14, CREB1, MEF2A, PRMT1) for risk prediction of HF patients, and the proposed nomogram resulted in good predictive performance (GSE66360, AUC = 0.91; GSE59867, AUC = 0.84) and the clinical usefulness in HF patients. More importantly, 10 drugs and 15 miRNA were predicted as drug target and hub miRNA that associated with energy metabolism-related genes, providing further information on clinical HF treatment.

Conclusion: This study identified ten energy metabolism-related diagnostic markers using random forest algorithm, which may help optimize risk stratification and clinical treatment in HF patients.

Keywords: biomarker; energy metabolism; heart failure; nomogram; random forest.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Identification of differentially expressed energy metabolism-related genes. (A,B) Expressions of differentially expressed energy metabolism-related genes. (C) Circos plot showing the location of genes in 22 chromosomes. (D) Protein-protein interaction networks.
Figure 2
Figure 2
Consensus clustering analysis of energy metabolism-related genes. (A) The cumulative distribution function (CDF) curve of samples in the HF cohort. (B) The relative change in area under the CDF curve for k = 2–9. (C) Sample clustering heatmap when consumption k = 2. (D) PCA analysis for cluster A and cluster B. (E,F) The different expression of 48 genes between two clusters.
Figure 3
Figure 3
Functional analyses of DEGs identified between clusters. (A,B) Gene Ontology (GO) functional analysis. (C) Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis.
Figure 4
Figure 4
Correlation analysis between energy metabolism-related genes and immune microenvironment. (A) The relationship between two clusters and the level of immune cell infiltration. *p-value < 0.05; **p-value < 0.01; ***p-value < 0.001; ****p-value < 0.0001. (B) The relationship between 46 energy metabolism-related genes and immune cell infiltration.
Figure 5
Figure 5
Identification of diagnostic biomarkers using RF and SVM model. (A) Boxplots of the residuals of the sample. Red dot stands for root mean square of residuals. (B) Cumulative residual distribution map of the sample. (C) AUC verification results of the two models on the training dataset. (D) The influence of the number of decision trees on the error rate. (E) Results of the Gini coefficient method in the random forest classifier.
Figure 6
Figure 6
Construction of a nomogram model for HF diagnosis in training cohort (GSE66360). (A) The nomogram was used to predict the occurrence of HF. (B) Calibration curve to assess the predictive power of the nomogram model. (C) The receiver operating characteristic (ROC) analysis of nomogram.
Figure 7
Figure 7
Construction of a nomogram model for HF diagnosis in test cohort (GSE59867). (A) The nomogram was used to predict the occurrence of HF. (B) Calibration curve to assess the predictive power of the nomogram model. (C) The receiver operating characteristic (ROC) analysis of nomogram.
Figure 8
Figure 8
The prediction of energy metabolism-related miRNA.
See this image and copyright information in PMC

References

    1. Zhang F, Zhou G, Guo L, Lu F, Zhou G. Comparison of clinical efficacy of metoprolol combined with irbesartan and hydrochlorothiazide and non-invasive ventilator in the emergency treatment of patients with severe heart failure. Exp Ther Med. (2018) 16:5059–66. 10.3892/etm.2018.6828 - DOI - PMC - PubMed
    1. Chen Y-J, Chien C-S, Chiang C-E, Chen C-H, Cheng H-M. From genetic mutations to molecular basis of heart failure treatment: an overview of the mechanism and implication of the novel modulators for cardiac myosin. Int J Mol Sci. (2021) 22:6617. 10.3390/ijms22126617 - DOI - PMC - PubMed
    1. GBD 2017 Disease and Injury Incidence and Prevalence Collaborators . Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet. (2018) 392:1789–858. 10.1016/S0140-6736(18)32279-7 - DOI - PMC - PubMed
    1. Pan W, Yang D, Yu P, Yu H. Comparison of predictive value of NT-proBNP, sST2 and MMPs in heart failure patients with different ejection fractions. BMC Cardiovasc Disord. (2020) 20:208. 10.1186/s12872-020-01493-2 - DOI - PMC - PubMed
    1. Pfeffer MA, Shah AM, Borlaug BA. Heart failure with preserved ejection fraction in perspective. Circ Res. (2019) 124:1598–617. 10.1161/CIRCRESAHA.119.313572 - DOI - PMC - PubMed