Correlation Analysis of Biomarkers for Idiopathic Pulmonary Fibrosis

A multi-omics dataset integrating bulk transcriptomic, single-cell RNA sequencing, and literature-derived gene sets to identify candidate biomarkers for idiopathic pulmonary fibrosis (IPF). The dataset was created by Yongbin Wang and last updated on April 23, 2026. It contains results from 101 machine-learning model combinations and validation in an independent clinical cohort.

Use Cases

• Validate candidate biomarkers CD247, IL7R, and RETN based on differential expression analysis results.
• Build diagnostic models for IPF based on the three identified feature genes and their reported AUC values.
• Analyze regulatory networks based on described transcription factor and non-coding RNA interactions.
• Investigate cell-type specificity of dysregulation based on single-cell expression and pseudotime trajectory analyses mentioned.

Strengths

• Integrates multiple data types: bulk transcriptomics, single-cell RNA-seq, and literature-derived gene sets.
• Validation includes results from 101 machine-learning model combinations and an independent clinical cohort.
• Candidate biomarkers were identified with reported single-gene AUC values greater than 0.7.

Limitations

• Row count and column-level documentation are unknown, limiting suitability assessment.
• The dataset is very small at 9.6 KB, suggesting it contains summary results rather than raw experimental data.
• The independent clinical cohort used for RT-qPCR validation is described as 'modest'.

Provenance

Source

Integrated data from the Gene Expression Omnibus (GEO) and other public scRNA-seq datasets.

Collection Method

Differential expression analysis, consensus clustering, functional enrichment, and machine-learning modeling.

Time Range

null

Freshness

Last updated 2026-04 23 17:24:17; freshness should be verified.

Geography

null