Metabolomics of Protection from the Development of World Trade Center-Lung Injury: A Machine Learning Approach

Abstract

INTRODUCTION: The metabolome remains an untapped resource with potential to comprehensively characterize and identify bioactive pathways of disease after WTC-PM exposure. A subset of rescue/recovery workers from the FDNY demonstrated resistance to subsequent loss of lung function. We have previously identified biomarkers significantly associated with protection from WTC-LI. OBJECTIVE: Implement machine learning and dimension reduction techniques to characterize the metabolome of WTC-exposed firefighters, stratified by resistance to WTC-LI, to identify metabolite pathways of significance to resistance to loss of lung disease post PM exposure. METHODS: Serum global metabolome of never-smoker, WTC-exposed firefighters with normal pre-9/11 lung function, segregated by forced expiratory volume-one second(FEV1) at symptomatic presentation. Control (n=15) from previously identified cohort-control and resistant to WTC-LI (FEV1, %- Pred≥107; within one-standard deviation of the highest FEV1% predicted of the study cohort, n=15) were selected. Pathways/metabolites associated with resistance to WTC-LI were determined using dimension reduction techniques. RESULTS: Metabolites most important to class separation (top 5% by RF of 594 qualified metabolites), included elevated amino acid and long-chain fatty acid metabolites, and reduced hexose monophosphate shunt metabolites in the resistant cohort. RF of the refined metabolic profile correctly classified cases and controls with a 93.3% estimated success rate. Agglomerative hierarchical clustering identified potential mechanistic relations. CONCLUSION: High-dimensional data analysis on the metabolome of a subset of WTC-PM exposed 9/11 rescue workers has identified pathways associated with resistance to loss of lung function after an acute PM exposure. These pathways represent novel potential therapeutic targets and warrant further research. FUNDING STATEMENT: NHLBI R01HL119326, CDC/NIOSH U01-OH11300, Clinical Center of Excellence 200-2017-93426, Data Center 200-2017-93326. This work was also partially funded by the NYU-HHC CTSI supported by grant UL1T38 from the National Center for Advancing Translational Sciences of the NIH and by the Saperstein Scholars Fund. DECLARATION OF INTERESTS: The authors report no conflicts of interest. ETHICS APPROVAL STATEMENT: Subjects, at the time of enrollment, consented to analysis of their information and samples for research according to Institutional Review Board (IRB) approved protocols at Montefiore Medical Center(#07-09-320) and New York University(#16-01412). All experiments conform to the relevant regulatory standards as per IRB standards.