Machine Learning-Determined Sex-Related Bladder Cancer Biomarkers from RNA-Seq Data

A gene panel dataset derived from RNA-seq analysis to identify sex-specific biomarkers for bladder cancer. The data was generated by Joseph R. Pizzi using machine learning feature selection methods and last updated in April 2026. Male and female-specific gene panels achieved areas under the ROC curve of 0.932 and 0.914, respectively, in distinguishing cancer from non-tumor samples.

Use Cases

• Train classifiers to distinguish bladder cancer from non-tumor samples based on sex-specific gene expression signatures.
• Investigate pathways like PI3K-AKT signaling and extracellular matrix reorganization in sex-specific cancer progression.
• Validate potential high-impact biomarker genes such as PRAC1, PCDH11Y, AR, PLXNA1, USP54, and PMEPA1 in external studies.

Strengths

• Performance metrics are provided, with male and female-specific panels achieving AUCs of 0.932 and 0.914.
• The study employed multiple machine learning feature selection methods (SVM-RFE, logistic regression, random forest) for robustness.
• The dataset is focused, limited to 50 genes or less per panel for practical application.

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 small at 33.3 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

Machine learning analysis of gender and disease-stratified RNA-seq data using differential expression and feature selection methods.

Freshness

Last updated 2026-04-29 05:58:42; freshness should be verified.