Parkinson's Disease Calcium Uptake Biomarkers from GSE6613 and Validation Sets

Wangzhouyang Lou published a dataset on 2026-05-13 containing results from a machine learning and WGCNA analysis of Parkinson's disease. The study identified 5 store-operated calcium entry (SOCE)-associated feature genes, such as LPCAT3 and CLCNKB, using data from the GSE6613, GSE20163, and GSE22491 datasets. The dataset includes validation results from in vitro experiments using 6-OHDA and MPP+ models of dopaminergic neurons.

Use Cases

• Validating potential biomarkers for Parkinson's disease based on identified SOCE-associated genes like LPCAT3 and CLCNKB.
• Training machine learning models for disease discrimination using the combined gene expression model described.
• Analyzing immune dysfunction in Parkinson's disease patients based on the immune analysis results mentioned.
• Comparing gene expression trends between patient samples and in vitro 6-OHDA/MPP+ models as referenced in the study.

Strengths

• Identifies 5 specific feature genes (e.g., LPCAT3, CLCNKB, TXLNA) associated with store-operated calcium entry in Parkinson's disease.
• Includes external validation using two independent datasets (GSE20163, GSE22491) and in vitro experiments.
• Dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale modeling.
• The dataset's 9.1 MB size suggests it is relatively small, potentially containing summary results rather than raw expression data.

Provenance

Source

Analysis based on public gene expression datasets GSE6613, GSE20163, and GSE22491.

Collection Method

Combined Weighted Gene Co-expression Network Analysis (WGCNA) with machine learning algorithms (LASSO, SVM-RFE, random forest).

Freshness

Last updated 2026-05-13 11:29:58; freshness should be verified.