PEDF, a pleiotropic WTC-LI biomarker: Machine learning biomarker identification and validation

Abstract

Biomarkers predict World Trade Center-Lung Injury (WTC-LI); however, there remains unaddressed multicollinearity in our serum cytokines, chemokines, and high-throughput platform datasets used to phenotype WTC-disease. To address this concern, we used automated, machine-learning, high-dimensional data pruning, and validated identified biomarkers. The parent cohort consisted of male, never-smoking firefighters with WTC-LI (FEV1, %Pred< lower limit of normal (LLN); n = 100) and controls (n = 127) and had their biomarkers assessed. Cases and controls (n = 15/group) underwent untargeted metabolomics, then feature selection performed on metabolites, cytokines, chemokines, and clinical data. Cytokines, chemokines, and clinical biomarkers were validated in the non-overlapping parent-cohort via binary logistic regression with 5-fold cross validation. Random forests of metabolites (n = 580), clinical biomarkers (n = 5), and previously assayed cytokines, chemokines (n = 106) identified that the top 5% of biomarkers important to class separation included pigment epithelium-derived factor (PEDF), macrophage derived chemokine (MDC), systolic blood pressure, macrophage inflammatory protein-4 (MIP-4), growth-regulated oncogene protein (GRO), monocyte chemoattractant protein-1 (MCP-1), apolipoprotein-AII (Apo-AII), cell membrane metabolites (sphingolipids, phospholipids), and branched-chain amino acids. Validated models via confounder-adjusted (age on 9/11, BMI, exposure, and pre-9/11 FEV1, %Pred) binary logistic regression had AUCROC [0.90(0.84-0.96)]. Decreased PEDF and MIP-4, and increased Apo-AII were associated with increased odds of WTC-LI. Increased GRO, MCP-1, and simultaneously decreased MDC were associated with decreased odds of WTC-LI. In conclusion, automated data pruning identified novel WTC-LI biomarkers; performance was validated in an independent cohort. One biomarker-PEDF, an antiangiogenic agent-is a novel, predictive biomarker of particulate-matter-related lung disease. Other biomarkers-GRO, MCP-1, MDC, MIP-4-reveal immune cell involvement in WTC-LI pathogenesis. Findings of our automated biomarker identification warrant further investigation into these potential pharmacotherapy targets.

Fig 1. Study Design.

From a parent cohort of WTC-LI cases (n = 96) and controls (n = 127), a metabolomics subcohort (n = 15/group) and a validation cohort (n = 114) were drawn as described.

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.

Fig 3. Predictive performance of Final Model.

ROC_AUC of the final, confounder-adjusted, multivariate binary logistic regression shows its predictive performance as well as that of its constituents when entered separately in confounder-adjusted binary logistic regressions.