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

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

Use Cases

• Training classifiers for bladder cancer detection based on sex-specific gene expression signatures.
• Investigating biological pathways like PI3K-AKT signaling and extracellular matrix reorganization in bladder cancer.
• Validating potential biomarkers such as PRAC1, PCDH11Y, AR, PLXNA1, USP54, and PMEPA1 in external datasets.
• Benchmarking feature selection methods (e.g., recursive feature elimination, random forest) for biomarker discovery.

Strengths

• Performance metrics are provided, with male and female-specific panels achieving AUCs of 0.932 and 0.914.
• Gene panels were limited to 50 genes or less, suggesting a focus on concise, high-impact biomarkers.
• Results were validated on unseen external datasets, indicating a robustness check.
• The dataset is openly licensed under CC-BY-4.0.

Limitations

• Row count and column-level documentation are unknown, requiring manual inspection after download.
• The dataset is very small at 15.0 KB, indicating limited scope, likely containing only gene lists or summary results.
• The description does not specify the source or number of original RNA-seq samples used in the analysis.

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 05:58:38; freshness should be verified.