Identification of Neuroinflammation-Related Diagnostic Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis: An Integrated Bioinformatics and Machine Learning Approach.
- 1Department of Gastroenterology The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital of Wannan Medical University) Wuhu Anhui China.
- 2Department of Gastroenterology Shannan People's Hospital Shannan Xizang Autonomous Region China.
Abstract
Metabolic dysfunction-associated steatohepatitis (MASH) is a liver disease that progresses and may be connected to neuroinflammation, though the specific molecular mechanisms are not yet understood. The objective of this research was to explore candidate diagnostic biomarkers related to neuroinflammation-associated gene programs for MASH through integrated bioinformatics and machine learning, as a hypothesis-generating study. Genes with differential expression (DEGs) were pinpointed from the GSE89632 dataset, which includes 39 MASH samples compared with 24 controls. Candidate genes were identified using weighted gene coexpression network analysis (WGCNA) and gene sets related to neuroinflammation. A diagnostic model was constructed using 81 machine learning algorithm combinations (filtered from an initial set of 113 by excluding models with fewer than 2 features) within the training set, and its performance was subsequently evaluated in GSE126848 (31 MASH vs. 26 controls) as an evaluation set. Because the evaluation set contributed to model selection, it does not represent a fully independent validation cohort. Regulatory network construction, drug prediction, and molecular docking were used for further analysis of key genes. A total of 90 disease-associated neuroinflammation-related candidate genes were identified. Five candidate key genes (IRS1, HBEGF, MYC, CD274, and HMOX1) were screened, and a diagnostic model was constructed. The model achieved an AUC of 0.978 in the training set and 0.823 in the evaluation set; however, because the evaluation set contributed to model selection in the original analysis, the 0.823 estimate should be interpreted with caution. These findings are exploratory and require experimental validation. This exploratory study identified five neuroinflammation-related candidate genes that may serve as candidate biomarkers for MASH. These findings provide candidate molecular links and potential therapeutic hypotheses, but require experimental validation and should be regarded as hypothesis-generating rather than clinically actionable.
Related
- Identification of mitophagy-related genes with diagnostic value in focal segmental glomerulosclerosis using bioinformatics analysis
- Identification of pyroptosis-related hub genes and construction of a diagnostic model for acute liver failure based on integrated bioinformatics and machine learning.
- Efficacy and safety of GLP-1 receptor agonists in patients with metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH) : A systematic review and meta-analysis
- Commentary: Wogonoside alleviates metabolic dysfunction-associated steatohepatitis by modulating AMPK and xCT/GPX4 pathways to restrain lipid dysregulation and ferroptosis
- GLP-1 receptor agonists in metabolic dysfunction-associated steatohepatitis: protocol for a systematic review and meta-analysis of randomized controlled trials
BibTeX
@article{jia2026identification,
title = {{Identification of Neuroinflammation-Related Diagnostic Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis: An Integrated Bioinformatics and Machine Learning Approach.}},
author = {Yuliang Jia and Maocairang Li and Duo Ga and Xueyi Qian},
journal = {Gastroenterology research and practice},
year = {2026},
month = nov,
doi = {10.1155/grp/2878164},
url = {https://europepmc.org/article/MED/42996511},
note = {CC BY},
}
RIS
TY - JOUR
TI - Identification of Neuroinflammation-Related Diagnostic Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis: An Integrated Bioinformatics and Machine Learning Approach.
AU - Yuliang Jia
AU - Maocairang Li
AU - Duo Ga
AU - Xueyi Qian
PY - 2026
DA - 2026/11/05
JO - Gastroenterology research and practice
DO - 10.1155/grp/2878164
UR - https://europepmc.org/article/MED/42996511
AB - Metabolic dysfunction-associated steatohepatitis (MASH) is a liver disease that progresses and may be connected to neuroinflammation, though the specific molecular mechanisms are not yet understood. The objective of this research was to explore candidate diagnostic biomarkers related to neuroinflammation-associated gene programs for MASH through integrated bioinformatics and machine learning, as a hypothesis-generating study. Genes with differential expression (DEGs) were pinpointed from the GSE89632 dataset, which includes 39 MASH samples compared with 24 controls. Candidate genes were identified using weighted gene coexpression network analysis (WGCNA) and gene sets related to neuroinflammation. A diagnostic model was constructed using 81 machine learning algorithm combinations (filtered from an initial set of 113 by excluding models with fewer than 2 features) within the training set, and its performance was subsequently evaluated in GSE126848 (31 MASH vs. 26 controls) as an evaluation set. Because the evaluation set contributed to model selection, it does not represent a fully independent validation cohort. Regulatory network construction, drug prediction, and molecular docking were used for further analysis of key genes. A total of 90 disease-associated neuroinflammation-related candidate genes were identified. Five candidate key genes (IRS1, HBEGF, MYC, CD274, and HMOX1) were screened, and a diagnostic model was constructed. The model achieved an AUC of 0.978 in the training set and 0.823 in the evaluation set; however, because the evaluation set contributed to model selection in the original analysis, the 0.823 estimate should be interpreted with caution. These findings are exploratory and require experimental validation. This exploratory study identified five neuroinflammation-related candidate genes that may serve as candidate biomarkers for MASH. These findings provide candidate molecular links and potential therapeutic hypotheses, but require experimental validation and should be regarded as hypothesis-generating rather than clinically actionable.
SN - 1687-6121
SN - 1687-630X
ER -