Table 4_Exploration of candidate genes associated with rare SNVs in pulmonary stenosis usi

185 sporadic pulmonary stenosis patients and 100 healthy controls were analyzed using whole-exome sequencing. Three machine learning algorithms—LASSO, random forest, and XGBoost—were applied to prioritize 17 candidate genes associated with the condition. The dataset, created by Yuting Liu and last updated in June 2026, provides a basis for investigating the genetic architecture of this congenital heart disease.

Use Cases

• Prioritizing candidate disease genes based on rare variant burden analysis results mentioned in the description
• Comparing feature selection patterns of different machine learning algorithms (LASSO, RF, XGBoost) on genomic data
• Validating candidate genes through protein-protein interaction network analysis as described in the methods
• Assessing gene expression of prioritized candidates in human pulmonary artery endothelial cells (HPAECs)

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 and conventional statistical tests for cross-validation
• Results include a specific list of 17 prioritized candidate genes

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 very small at 22.0 KB, indicating limited scope

Provenance

Source

Yuting Liu via figshare

Collection Method

Rare pathogenic single nucleotide variants identified from whole-exome sequencing data using multiple pathogenicity-filtering strategies.

Freshness

Last updated 2026-06-04 22:01:43; freshness should be verified