Machine Learning-Derived Sex-Specific Bladder Cancer Biomarkers from RNA-Seq Data

A gene panel dataset resulting from a machine learning study on sex-stratified bladder cancer RNA-seq data. The study applied four feature selection methods to identify biomarkers, with male and female-specific panels achieving areas under the ROC curve of 0.932 and 0.914, respectively, on unseen data. The dataset was authored by Joseph R. Pizzi and last updated on 2026-04-29.

Use Cases

• Training classifiers for male bladder cancer detection based on the 50-gene panel.
• Investigating female-specific tumor progression pathways related to extracellular matrix reorganization.
• Validating sex hormone-related biomarkers like PRAC1 and PCDH11Y in external datasets.
• Comparing feature selection methods (e.g., recursive feature elimination, random forest) for biomarker discovery.

Strengths

• Performance metrics are provided, with male and female panels achieving AUCs of 0.932 and 0.914.
• The study methodology is detailed, employing four distinct machine learning feature selection strategies.
• Dataset is openly licensed under CC-BY-4.0.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 8.6 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

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

Freshness

Last updated 2026-04-29 05:58:43; freshness should be verified.