Integrated Bioinformatics and Machine Learning Biomarkers for MAFLD with Psoriasis

A transcriptomic dataset from the Gene Expression Omnibus (GEO) database, analyzed to identify shared biomarkers for metabolic dysfunction–associated fatty liver disease (MAFLD) and psoriasis. The dataset includes results from weighted gene co-expression network analysis (WGCNA) and machine learning algorithms (random forest, LASSO, SVM) applied to identify six hub genes. It was authored by Shanshan Wang and last updated on April 15, 2026.

Use Cases

• Training machine learning models for early disease diagnosis based on identified hub genes like ADRB2 and WNT5A.
• Investigating immune and metabolic pathway enrichment in shared genes between psoriasis and MAFLD.
• Validating biomarker diagnostic accuracy using receiver operating characteristic (ROC) analysis.
• Assessing correlations between gene expression and immune cell infiltration in disease models.

Strengths

• Dataset size is 14.1 MB, indicating a focused and manageable download.
• The study identified six specific hub genes (ADRB2, WNT5A, S100A9, FAM110C, S100A12, TUBB6) through integrated machine learning analysis.
• Data is sourced from the authoritative Gene Expression Omnibus (GEO) database.
• Results were validated in psoriasis and MAFLD mouse models.

Limitations

• Row count and column-level documentation are unknown, requiring manual inspection after download.
• The dataset's specific temporal coverage is not stated in the provided metadata.
• Data may reflect the biases inherent to the specific GEO datasets used in the original study.

Provenance

Source

Gene Expression Omnibus (GEO) database.

Collection Method

Transcriptomic datasets retrieved and analyzed using WGCNA and machine learning algorithms.

Freshness

Last updated 2026-04-15 05:46:54.