Jia-Qi Ma's dataset contains non-targeted metabolomics data from 67 carotid artery plaque samples (40 stable, 27 unstable). The study identified 98 metabolites differentially associated with unstable plaques and used four machine learning algorithms to screen for potential biomarkers. The dataset was last updated on 2026-05-12.
Use Cases
- Training ML models to classify plaque stability based on metabolite signatures.
- Identifying metabolic pathways (e.g., cGMP-PKG signaling) associated with unstable plaques.
- Screening for specific metabolites as potential biomarkers for stroke risk prediction.
Strengths
- Data is derived from 67 clinical plaque samples with clear case counts (40 stable, 27 unstable).
- Analysis identified 98 significantly differential metabolites and several enriched KEGG pathways.
- Four distinct machine learning algorithms (RF, SVM, LASSO, LR) were applied for feature analysis.
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 (13.7 KB), indicating limited scope.
Provenance
- Source
- Jia-Qi Ma via figshare
- Collection Method
- Non-targeted metabolomics analysis performed on carotid artery plaque tissue samples.
- Freshness
- Last updated 2026-05-12 04:20:13