Identification of Shared and Unique Key Biomarkers of Alcohol Liver Cirrhosis and Non-Alcoholic Steatohepatitis Through Machine Learning Network-Based Algorithms
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Introduction
Liver fibrosis can progress to cirrhosis, liver failure, or hepatocellular carcinoma, which often requires transplantation and burdens healthcare systems around the world. Advances in single-cell RNA sequencing and machine learning have enhanced the understanding of immune responses in many liver diseases particularly alcohol liver cirrhosis (ALC) and non-alcoholic steatohepatitis (NASH). This study aims to identify key biomarkers involved in these conditions and assess their potential as non-invasive diagnostic tools.
Methods
Two gene expression profiles GSE136103 and GSE115469 were used to conduct differential gene expression (DEG) analysis. Using the results from DEG analysis, we then applied two machine learning network-based algorithms, master regulator analysis (MRA) and weighted key driver analysis (wKDA), to identify potential biomarker genes for NASH and ALC.
Results
A total of 1,435 and 5,074 DEGs were identified for ALC and NASH compared to healthy controls, including 1,077 shared DEGs between the two diseases. The MRA showed HLA-DPA1, HLA-DRB1, IFI44L, ISG15, and CD74 as the potential master regulators of ALC and HLA-DPB1, HLA-DQB1, HLA-DRB5, PFN1, and TMSB4X as the potential master regulators of NASH. In addition, wKDA analysis indicated CD300A, FCGR2A, RGS1, HLA-DMB, and C1QA as the key drivers of ALC and INPP5D, NCKAP1L, RAC2, PTPRC, and TYROBP as key drivers of NASH.
Conclusion
This study presented a comprehensive framework for analyzing single-cell RNA-seq data, demonstrating the potential of combining advanced network-based machine-learning techniques with conventional DEG analysis to uncover actionable prognostic markers for ALC and NASH with potential use as target biomarkers in drug development.