PLA2G2A is a candidate biomarker for sepsis diagnosis in mice through machine learning algorithms
- 1Graduate School of Dalian Medical University , , ,
- 2Department of Peripheral Vascular Intervention, Central Hospital of Dalian University of Technology , , ,
- 3Department of Critical Care Medicine, Central Hospital of Dalian University of Technology , , ,
Abstract
Objective: In this study, machine-learning screening was implemented on human transcriptomic data from public GEO datasets and independent experiments were served to validate candidate biomarkers for sepsis in mice models.
Methods: Microarray data were obtained from the GSE236713 dataset, and differentially expressed genes (DEGs) were screened. We carried out enrichment analysis with the help of gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG). We utilized machine learning algorithms, such as least absolute shrinkage and selection operator (LASSO), logistic regression (LR), support vector machine (SVM). For the key genes, we conducted single-gene enrichment and immune Infiltration Analysis. We selected C57BL/6J SPF-grade male mice to construct a sepsis model. The proteins were then detected via western blotting (WB), tissue homogenization, tissue staining, immunohistochemistry (IHC), and cytokines.
Results: Multiple groups of DEGs were identified via dataset analysis. Weighted gene co-expression network analysis (WGCNA) was used to identify related modules. Machine learning was used to screen key genes, such as cholinergic receptor muscarinic 1 (CHRM1) and Secreted phospholipase A2 (sPLA2-IIA) (encoded by PLA2G2A ). sPLA2-IIA expression was also higher in the mouse sepsis model group than the sham group. And its expression was implying regulatory effects. The successful mouse model is characterized by elevated levels of IL-6, TNF-α, and multi-organ damage.
Conclusion: In this study, we identified PLA2G2A as the candidate biomarker for diagnosis of sepsis in mice models through machine learning algorithms. And the data obtained may be helpful for subsequent research on sepsis pathogenesis.
Related
- Single-cell, spatial, and machine learning analyses identify ANKIB1 as an oligodendrocyte-anchored palmitoylation-associated candidate biomarker of Alzheimer’s disease
- Machine learning for biomarker-driven thalassemia diagnosis: a framework for causal effect estimation
- Machine Learning-Based Diagnosis of Coronary Heart Disease with Clinical and Biomarker Data.
- Integrated Transcriptomic Analysis Identifies ENO3 as a Candidate Lactate Metabolism‐Associated Biomarker in Colorectal Cancer Metastasis
- Minute-Scale Sleep-Onset HRV as a Candidate Risk-Stratification Biomarker for Diabetic Retinopathy: An Exploratory Pilot Study
BibTeX
@article{zhu2026pla2g2a,
title = {{PLA2G2A is a candidate biomarker for sepsis diagnosis in mice through machine learning algorithms}},
author = {Hong Zhu and Pai Peng and Shiquan Han and Rongli Yang},
journal = {Frontiers in immunology},
year = {2026},
month = sep,
doi = {10.3389/fimmu.2026.1937718},
url = {https://europepmc.org/article/PMC/PMC13661449},
note = {CC BY},
}
RIS
TY - JOUR
TI - PLA2G2A is a candidate biomarker for sepsis diagnosis in mice through machine learning algorithms
AU - Hong Zhu
AU - Pai Peng
AU - Shiquan Han
AU - Rongli Yang
PY - 2026
DA - 2026/09/30
JO - Frontiers in immunology
DO - 10.3389/fimmu.2026.1937718
UR - https://europepmc.org/article/PMC/PMC13661449
AB - Objective: In this study, machine-learning screening was implemented on human transcriptomic data from public GEO datasets and independent experiments were served to validate candidate biomarkers for sepsis in mice models. Methods: Microarray data were obtained from the GSE236713 dataset, and differentially expressed genes (DEGs) were screened. We carried out enrichment analysis with the help of gene ontology (GO) and Kyoto encyclopedia of genes and genomes (KEGG). We utilized machine learning algorithms, such as least absolute shrinkage and selection operator (LASSO), logistic regression (LR), support vector machine (SVM). For the key genes, we conducted single-gene enrichment and immune Infiltration Analysis. We selected C57BL/6J SPF-grade male mice to construct a sepsis model. The proteins were then detected via western blotting (WB), tissue homogenization, tissue staining, immunohistochemistry (IHC), and cytokines. Results: Multiple groups of DEGs were identified via dataset analysis. Weighted gene co-expression network analysis (WGCNA) was used to identify related modules. Machine learning was used to screen key genes, such as cholinergic receptor muscarinic 1 (CHRM1) and Secreted phospholipase A2 (sPLA2-IIA) (encoded by PLA2G2A ). sPLA2-IIA expression was also higher in the mouse sepsis model group than the sham group. And its expression was implying regulatory effects. The successful mouse model is characterized by elevated levels of IL-6, TNF-α, and multi-organ damage. Conclusion: In this study, we identified PLA2G2A as the candidate biomarker for diagnosis of sepsis in mice models through machine learning algorithms. And the data obtained may be helpful for subsequent research on sepsis pathogenesis.
SN - 1664-3224
ER -