Machine Learning and Experimental Validation Identified Ferroptosis Signature and Innovative Biomarkers (ESR1 and GSTZ1) in Liver Fibrosis

Aug 2, 2026

Upload by Ezra

Targeting ferroptosis offers a promising strategy to alleviate hepatic fibrosis, yet ferroptosis-associated molecular signatures in this condition have not been previously reported. The study analyzed RNAseq datasets from GSE6764, GSE188604, and TCGA-LIHC, applying machine learning approaches including WGCNA, Random Forest, and SVM to identify core genes. In a CCl4-induced mouse model and GEO validation cohorts, RT-PCR confirmed that ESR1 and GSTZ1 were markedly downregulated in fibrosis. ROC-based analyses showed strong diagnostic performance for both liver fibrosis and hepatocellular carcinoma.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

Introduction

Methods

Data sources and preprocessing

Machine learning identification

Experimental validation

ROC diagnostic evaluation

Results

Conclusion

Journal of Inflammation Research downloaded from [https://www.dovepress.com/](https://www.dovepress.com/) For personal use only. Journal of Inflammation Research Dovepress Open Access Full Text Article ORIGINAL RESEARCH Machine Learning and Experimental Validation Identified Ferroptosis Signature and Innovative Biomarkers (ESR1 and GSTZ1) in Liver Fibrosis Wen Luo 1 , Hongwen Wu2 , Zhijie Yang2 , Tian Lan2 , Liya Wu 3 , Yushen Huang2 1Department of Gastrointestinal Surgery, Liuzhou Workers Hospital, Liuzhou, People’s Republic of China; 2Department of Pharmacy, Liuzhou Workers Hospital, Liuzhou, People’s Republic of China; 3Department of Neurology, Liuzhou Workers Hospital, Liuzhou, People’s Republic of China Correspondence: Yushen Huang; Liya Wu, Email [hys@sr.gxmu.edu.cn](hys@sr.gxmu.edu.cn); [wly31742858@126.com](wly31742858@126.com) | Background: Targeting ferroptosis is an effective approach to mitigate hepatic fibrosis, yet no reports exist on the ferroptosis signature in liver fibrosis. This study aimed to explore ferroptosis characteristics in this disease.<br>Methods: RNAseq data from GSE6764, GSE188604 and Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) were downloaded. Multiple machine learning methods, including Weighted Gene Co-expression Network Analysis (WGCNA), Random Forest (RF) and Support Vector Machine (SVM), were used to identify core genes in liver fibrosis and ferroptosis. WGCNA can pinpoint modules linked to clinical traits, aiding in discovering diagnostic and progression molecules in complex diseases. RF and SVM are often utilized for WGCNA validation to boost result accuracy. Carbon tetrachloride (CCl4) was used to establish a mouse liver fibrosis model to validate core gene expression, which was also assessed in test and validation GEO datasets. Finally, the diagnostic role of the core genes in liver fibrosis and hepatocellular carcinoma (HCC) was also investigated using ROC analysis. Results: Multiple machine learning methods screened nine core genes, including IL1B, GSTZ1, LIFR, SLC25A37, PTGS2, MT1G, HSPB1, ESR1, and PHGDH. In vivo experimental validation, RT-PCR showed ESR1 and GSTZ1 were significantly under-expressed in the liver fibrosis group compared to the normal group. Simultaneously, in GSE6764 and GSE188604, ESR1 and GSTZ1 were also identified as protective genes for liver fibrosis. More in-depth research found that ESR1 and GSTZ1 exhibited a good diagnostic performance both in liver fibrosis and HCC, suggesting that a persistent decrease in ESR1 and GSTZ1 in patients might signal the progression from hepatic fibrosis to HCC.<br>Conclusion: The present study is the first to report the ferroptosis signature in liver fibrosis and identifies two novel biomarkers, ESR1 and GSTZ1, providing new insights for the diagnosis and treatment of liver fibrosis in the future.<br>Keywords: ESR1, GSTZ1, ferroptosis, liver fibrosis, biomarker | | --- | | Introduction<br>Liver fibrosis is a significant global health issue characterized by the excessive accumulation of extracellular matrix (ECM), leading to the disruption of normal liver architecture and function. It is a common consequence of chronic liver diseases, including viral hepatitis, alcoholic liver disease, and non-alcoholic fatty liver disease (NAFLD) .1 With the progression of liver fibrosis, the liver microenvironment undergoes significant changes, which facilitate the carcinogenesis of liver cells, leading to a higher mortality rate.2 Persistent cell death and compensatory regeneration in fibrotic liverscan lead to genetic instability, making liver parenchymal cells more susceptible to carcinogenesis.3 In addition, hepatic stellate cells secrete soluble cytokines, chemokines, and chemotactic factors, establishing a complex tumor microenvironment that leads to epithelial-mesenchymal transition, which contributes to the occurrence of liver cancer.4 According to recent studies, liver fibrosis affects millions of

FAQs

What was the main goal of this study on ferroptosis and liver fibrosis?

The study aimed to explore ferroptosis characteristics in liver fibrosis and identify relevant diagnostic biomarkers.

How were core ferroptosis-related genes identified?

RNAseq datasets (GSE6764, GSE188604, and TCGA-LIHC) were analyzed using multiple machine learning methods including WGCNA, Random Forest, and SVM to screen core genes.

What experimental evidence supports ESR1 and GSTZ1 as biomarkers?

In a CCl4-induced mouse liver fibrosis model, RT-PCR showed ESR1 and GSTZ1 were significantly under-expressed in fibrosis versus normal groups, and both genes were also identified in external GEO datasets.

Aug 2, 2026

Upload by Ezra