187
Views
0
CrossRef citations to date
0
Altmetric
ORIGINAL RESEARCH

Use of Machine Learning for the Identification and Validation of Immunogenic Cell Death Biomarkers and Immunophenotypes in Coronary Artery Disease

, , , &
Pages 223-249 | Received 10 Oct 2023, Accepted 28 Dec 2023, Published online: 11 Jan 2024
 

Abstract

Objective

Immunogenic cell death (ICD) is part of the immune system’s response to coronary artery disease (CAD). In this study, we bioinformatically evaluated the diagnostic and therapeutic utility of immunogenic cell death-related genes (IRGs) and their relationship with immune infiltration features in CAD.

Methods

We acquired the CAD-related datasets GSE12288, GSE71226, and GSE120521 from the Gene Expression Omnibus (GEO) database and the IRGs from the GeneCards database. After identifying the immune cell death-related differentially expressed genes (IRDEGs), we developed a risk model and detected immune subtypes in CAD. IRDEGs were identified using least absolute shrinkage and selection operator (LASSO) analysis. Using a nomogram, we confirmed that both the LASSO model and ICD signature genes had good diagnostic performance.

Results

There was a high degree of coincidence and immune representativeness between two CAD groups based on characteristic genes and hub genes. Hub genes were associated with the interaction of neuroactive ligands with receptors and cell adhesion receptors. The two groups differed in terms of adipogenesis, allograft rejection, and apoptosis, as well as the ICD signature and hub gene expression levels. The two CAD-ICD subtypes differed in terms of immune infiltration.

Conclusion

Quantitative real-time PCR (qRT-PCR) correlated CAD with the expression of OAS3, ITGAV, and PIBF1. The ICD signature genes are candidate biomarkers and reference standards for immune grouping in CAD and can be beneficial in precise immune-targeted therapy.

Abbreviations

OAS3, 2’-5’-oligoadenylate synthetase 3 [EC2.7.7.84]; ITGAV, integrin α chain V; PIBF1, progesterone-induced-blocking factor 1; AKR1C3, aldo-keto reductase family 1 member C3 [EC 1.1.1.188]; NOX4, nicotinamide adenine dinucleotide phosphate hydrogen oxidase 4 [EC1.6.99.1]; SMPX, small muscle protein X-linked.

Data Sharing Statement

The original contributions presented in the study are included in the article/Supplementary Files, further inquiries can be directed to the corresponding author.

Ethics Approval and Informed Consent

This study was conducted in accordance with the declaration of Helsinki.The studies involving human participants were reviewed and approved by the Medical Ethics Committee of the Second Hospital of Hebei Medical University (approval number 2023-C016, dated February 28, 2023). All enrolled participants gave their informed consent.

Acknowledgments

We would like to thank Editage (www.editage.cn) for English language editing.

Disclosure

The authors report no conflicts of interest in this work.

Additional information

Funding

This research was supported by the Transversal Research Project of Kuntuo Xincheng Pharmaceutical Research & Development (Beijing) Co., Ltd.