Integration of RNA-Seq and Machine Learning Identifies Hub Genes for Empagliflozin Benefitable Heart Failure with Reduced Ejection Fraction

Qiang Yang; Jing Gao; Tian-Yu Wang; Jun-Can Ding; Peng-Fei Hu

doi:10.2147/JIR.S429096

Integration of RNA-Seq and Machine Learning Identifies Hub Genes for Empagliflozin Benefitable Heart Failure with Reduced Ejection Fraction

J Inflamm Res. 2023 Oct 18:16:4733-4749. doi: 10.2147/JIR.S429096. eCollection 2023.

Authors

Qiang Yang^#¹, Jing Gao^#², Tian-Yu Wang¹, Jun-Can Ding¹, Peng-Fei Hu³

Affiliations

¹ Second Clinical Medical College, Zhejiang Chinese Medical University, Hangzhou, Zhejiang Province, 310053, People's Republic of China.
² Department of Cardiology, Sir Run Run Shaw Hospital, College of Medicine Zhejiang University, Hangzhou, Zhejiang Province, 310018, People's Republic of China.
³ Department of Cardiology, the Second Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, Zhejiang Province, 310005, People's Republic of China.

^# Contributed equally.

Abstract

Purpose: This study aimed to analyze the hub genes of heart failure with reduced ejection fraction (HFrEF) treated with Empagliflozin using RNA sequencing (RNA-seq) and bioinformatics methods, including machine learning.

Methods: From February 2021 to February 2023, nine patients with HFrEF were enrolled from our hospital's cardiovascular department. In addition to routine drug treatment, these patients received 10 mg of Empagliflozin once daily for two months. Efficacy was assessed and RNA-seq was performed on peripheral blood before and after treatment with empagliflozin. HFrEF-related hub genes were identified through bioinformatics analyses including differential gene expression analysis, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses, immune infiltration analysis, machine learning, immune cell correlation analysis and clinical indicator correlation analysis.

Results: The nine patients included in this study completed a two-month treatment regimen, with an average age of 62.11 ± 6.36 years. By performing bioinformatics analysis on the transcriptome from the treatment groups, 42 differentially expressed genes were identified, with six being up-regulated and 36 being down-regulated (|log2FC|>1 and adj.pvalue<0.05). Immune infiltration analysis of these genes demonstrated a significant difference in the proportion of plasma between the pre-treatment and post-treatment groups (p<0.05). Two hub genes, GTF2IP14 and MTLN, were finally identified through machine learning. Further analysis of the correlation between the hub genes and immune cells suggested a negative correlation between GTF2IP14 and naive B cells, and a positive correlation between MTLN and regulatory T cells and resting memory CD4+ T cells (p<0.05).

Conclusion: Through RNA-seq and bioinformatics analysis, this study identified GTF2IP14 and MTLN as the hub genes of HFrEF, and their mechanisms may be related to immune inflammatory responses and various immune cells.

Keywords: HFrEF; RNA-seq; bioinformatics; empagliflozin; machine learning.

Grants and funding

This study was supported by the Zhejiang Medicine and Health Science and Technology Plan Project (project number: 2020KY205), the Natural Science Foundation of Zhejiang Province (project number: LY20H020005) and the Zhejiang TCM Science and Technology Planning Project (project number: 2022ZA082).