Sex-Specific Bladder Cancer Biomarker Panels Identified via Machine Learning

Gene expression panels for sex-specific bladder cancer biomarker discovery derived from RNA-seq data using machine learning. The dataset was created by Joseph R. Pizzi and published on figshare in April 2026. It contains results from applying four feature selection methods to identify robust gene signatures.

Use Cases

• Validate identified sex-specific biomarker panels based on genes like PRAC1 and PCDH11Y for male tumors
• Investigate enriched pathways such as PI3K-AKT signaling and extracellular matrix reorganization based on the results
• Benchmark machine learning feature selection methods (e.g., recursive feature elimination, random forest) for biomarker discovery
• Design targeted in vivo/vitro experiments based on high-impact predictors related to androgen signaling, such as AR, PLXNA1, USP54, and PMEPA1

Strengths

• Performance metrics are provided, with sex-specific panels achieving AUCs of 0.932 (male) and 0.914 (female)
• The study employed a structured methodology using four distinct machine learning feature selection techniques
• Results were validated on external datasets, suggesting some generalizability

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• The dataset is very small (12.9 KB), indicating limited scope, likely containing summary results rather than raw data

Provenance

Source

figshare

Collection Method

Machine learning analysis of gender and disease-stratified RNA-seq data

Freshness

Last updated 2026-04-29 05:58:45; freshness should be verified