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

A dataset by Joseph R. Pizzi, last updated on 2026-04-29, containing gene panels identified through machine learning for sex-specific bladder cancer. The data likely includes gene identifiers and associated metrics from an analysis of gender and disease-stratified RNA-seq data. The male and female-specific panels achieved areas under the ROC curve of 0.932 and 0.914, respectively, in distinguishing cancer from non-tumor controls.

Use Cases

• Validating sex-specific bladder cancer biomarker panels based on the described gene lists.
• Training machine learning models for cancer classification using the identified high-impact genes like PRAC1 and PCDH11Y.
• Investigating enriched biological pathways such as PI3K-AKT signaling and extracellular matrix reorganization mentioned in the results.
• Comparing feature selection methods (e.g., recursive feature elimination, random forest) for biomarker discovery in oncology.

Strengths

• The male and female-specific biomarker panels achieved high performance metrics (AUC of 0.932 and 0.914).
• Analysis employed multiple machine learning feature selection methods (differential expression, SVM-RFE, logistic regression, random forest).
• 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 small (15.0 KB), indicating limited scope, likely containing summary results rather than raw expression data.

Provenance

Source

figshare

Collection Method

Machine learning analysis of gender and disease-stratified RNA-seq data, as described in the study methods.

Freshness

Last updated 2026-04-29 05:58:41; freshness should be verified.