Mitochondria-Related Biomarkers in Liver Fibrosis via Machine Learning and WGCNA

A transcriptomic analysis dataset identifies key mitochondria-related genes associated with liver fibrosis. The data was generated by Yupeng Ma and last updated in May 2026. It includes bulk and single-cell RNA-seq datasets from GEO and results from an XGBoost model prioritizing targets like ACOT9.

Use Cases

• Prioritizing therapeutic targets for liver fibrosis based on mitochondria-related gene expression.
• Training interpretable machine learning models for biomarker discovery using transcriptomic data.
• Analyzing cell-type-specific expression patterns of fibrosis-related genes from single-cell RNA-seq data.
• Validating candidate biomarkers in human disease models based on upregulation in cirrhosis datasets.

Strengths

• Integrates multiple public RNA-seq datasets (GSE152329, GSE167216, GSE119953, GSE254610, GSE145086, GSE233084).
• Identifies 38 mitochondria-related differentially expressed genes in a CCl4-induced fibrosis model.
• Includes in vivo validation in a mouse model and in vitro functional validation in human LX-2 cells.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect bias inherent to the specific GEO datasets and experimental models used.

Provenance

Source

Gene Expression Omnibus (GEO) public repositories.

Collection Method

Transcriptomic analysis combining WGCNA, differential expression, and machine learning (XGBoost) on bulk and single-cell RNA-seq data.

Freshness

Last updated 2026-05-28 04:44:13; freshness should be verified.