PEDF, a pleiotropic WTC-LI biomarker: Machine learning biomarker identification and validation
Fig 2
Random Forests Variable Importance.
A. Mean decrease accuracy was used to determine and rank the top 5% of important metabolites, cytokines, chemokines, and clinical biomarkers. B. Agglomerative, Hierarchical Clustering identified 5 clusters of variables in the refined profile with similar patterns of expression in the metabolomics subcohort. C. PCA Loading Weights Plot visualizes clusters of variables based on intervariable correlations and provides an alternative-but-similar view of variable relationships in the metabolomics subcohort. Points are colored according to cluster membership.