Table 2_Exploration of candidate genes associated with rare SNVs in pulmonary stenosis usi

Yuting Liu published a dataset on 2026-06-04 containing prioritized candidate genes associated with pulmonary stenosis. The data was generated from whole-exome sequencing of 185 sporadic PS patients and 100 healthy controls, analyzed using gene-level burden tests and three machine learning algorithms. The final list includes 17 candidate genes prioritized through protein-protein interaction network analysis.

Use Cases

• Prioritizing candidate disease genes based on rare single nucleotide variant data from whole-exome sequencing.
• Comparing feature selection patterns across LASSO, random forest, and XGBoost algorithms for genomic data.
• Validating machine learning-derived gene candidates against results from conventional gene-based burden tests.
• Building protein-protein interaction networks to further prioritize candidate genes for functional study.
• Assessing gene expression patterns in human pulmonary artery endothelial cells for candidate validation.

Strengths

• Data is derived from whole-exome sequencing of 185 patients and 100 controls, providing a case-control study design.
• Analysis employed three distinct machine learning algorithms (LASSO, RF, XGBoost) and conventional statistical tests for cross-validation.
• The final prioritized list of 17 candidate genes is explicitly named, including HAND2, SETD2, and NOTCH3.

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 in scale at 137.0 KB, indicating limited data volume.

Provenance

Source

Yuting Liu via figshare

Collection Method

Whole-exome sequencing data analyzed with pathogenicity-filtering strategies, gene-level burden tests (SKAT-O), and machine learning algorithms.

Freshness

Last updated 2026-06-04 22:01:44; freshness should be verified.