Metabolomics of World Trade Center-Lung Injury: A machine learning approach

George Crowley, Sophia Kwon, Syed Hissam Haider, Erin J. Caraher, Rachel Lam, David E. St-Jules, Mengling Liu, David J. Prezant, Anna Nolan

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Introduction Biomarkers of metabolic syndrome expressed soon after World Trade Center (WTC) exposure predict development of WTC Lung Injury (WTC-LI). The metabolome remains an untapped resource with potential to comprehensively characterise many aspects of WTC-LI. This case-control study identified a clinically relevant, robust subset of metabolic contributors of WTC-LI through comprehensive high-dimensional metabolic profiling and integration of machine learning techniques. Methods Never-smoking, male, WTC-exposed firefighters with normal pre-9/11 lung function were segregated by post-9/11 lung function. Cases of WTC-LI (forced expiratory volume in 1s <lower limit of normal, n=15) and controls (n=15) were identified from previous cohorts. The metabolome of serum drawn within 6 months of 9/11 was quantified. Machine learning was used for dimension reduction to identify metabolites associated with WTC-LI. Results 580 metabolites qualified for random forests (RF) analysis to identify a refined metabolite profile that yielded maximal class separation. RF of the refined profile correctly classified subjects with a 93.3% estimated success rate. 5 clusters of metabolites emerged within the refined profile. Prominent subpathways include known mediators of lung disease such as sphingolipids (elevated in cases of WTC-LI), and branched-chain amino acids (reduced in cases of WTC-LI). Principal component analysis of the refined profile explained 68.3% of variance in five components, demonstrating class separation. Conclusion Analysis of the metabolome of WTC-exposed 9/11 rescue workers has identified biologically plausible pathways associated with loss of lung function. Since metabolites are proximal markers of disease processes, metabolites could capture the complexity of past exposures and better inform treatment. These pathways warrant further mechanistic research.

Original languageEnglish (US)
Article numbere000274
JournalBMJ Open Respiratory Research
Volume5
Issue number1
DOIs
StatePublished - Aug 1 2018

Fingerprint

Metabolomics
Metabolome
Lung Injury
Lung
Firefighters
Branched Chain Amino Acids
Sphingolipids
Forced Expiratory Volume
Principal Component Analysis
Lung Diseases
Case-Control Studies
Biomarkers
Smoking
Serum
Research
Machine Learning
Therapeutics

Keywords

  • occupational lung disease
  • systemic disease and lungs

ASJC Scopus subject areas

  • Pulmonary and Respiratory Medicine

Cite this

Crowley, G., Kwon, S., Haider, S. H., Caraher, E. J., Lam, R., St-Jules, D. E., ... Nolan, A. (2018). Metabolomics of World Trade Center-Lung Injury: A machine learning approach. BMJ Open Respiratory Research, 5(1), [e000274]. https://doi.org/10.1136/bmjresp-2017-000274

Metabolomics of World Trade Center-Lung Injury : A machine learning approach. / Crowley, George; Kwon, Sophia; Haider, Syed Hissam; Caraher, Erin J.; Lam, Rachel; St-Jules, David E.; Liu, Mengling; Prezant, David J.; Nolan, Anna.

In: BMJ Open Respiratory Research, Vol. 5, No. 1, e000274, 01.08.2018.

Research output: Contribution to journalArticle

Crowley, G, Kwon, S, Haider, SH, Caraher, EJ, Lam, R, St-Jules, DE, Liu, M, Prezant, DJ & Nolan, A 2018, 'Metabolomics of World Trade Center-Lung Injury: A machine learning approach', BMJ Open Respiratory Research, vol. 5, no. 1, e000274. https://doi.org/10.1136/bmjresp-2017-000274
Crowley G, Kwon S, Haider SH, Caraher EJ, Lam R, St-Jules DE et al. Metabolomics of World Trade Center-Lung Injury: A machine learning approach. BMJ Open Respiratory Research. 2018 Aug 1;5(1). e000274. https://doi.org/10.1136/bmjresp-2017-000274
Crowley, George ; Kwon, Sophia ; Haider, Syed Hissam ; Caraher, Erin J. ; Lam, Rachel ; St-Jules, David E. ; Liu, Mengling ; Prezant, David J. ; Nolan, Anna. / Metabolomics of World Trade Center-Lung Injury : A machine learning approach. In: BMJ Open Respiratory Research. 2018 ; Vol. 5, No. 1.
@article{a2e3fa9e019d4078914b8835be1c6ab1,
title = "Metabolomics of World Trade Center-Lung Injury: A machine learning approach",
abstract = "Introduction Biomarkers of metabolic syndrome expressed soon after World Trade Center (WTC) exposure predict development of WTC Lung Injury (WTC-LI). The metabolome remains an untapped resource with potential to comprehensively characterise many aspects of WTC-LI. This case-control study identified a clinically relevant, robust subset of metabolic contributors of WTC-LI through comprehensive high-dimensional metabolic profiling and integration of machine learning techniques. Methods Never-smoking, male, WTC-exposed firefighters with normal pre-9/11 lung function were segregated by post-9/11 lung function. Cases of WTC-LI (forced expiratory volume in 1s",
keywords = "occupational lung disease, systemic disease and lungs",
author = "George Crowley and Sophia Kwon and Haider, {Syed Hissam} and Caraher, {Erin J.} and Rachel Lam and St-Jules, {David E.} and Mengling Liu and Prezant, {David J.} and Anna Nolan",
year = "2018",
month = "8",
day = "1",
doi = "10.1136/bmjresp-2017-000274",
language = "English (US)",
volume = "5",
journal = "BMJ Open Respiratory Research",
issn = "2052-4439",
publisher = "BMJ Publishing Group",
number = "1",

}

TY - JOUR

T1 - Metabolomics of World Trade Center-Lung Injury

T2 - A machine learning approach

AU - Crowley, George

AU - Kwon, Sophia

AU - Haider, Syed Hissam

AU - Caraher, Erin J.

AU - Lam, Rachel

AU - St-Jules, David E.

AU - Liu, Mengling

AU - Prezant, David J.

AU - Nolan, Anna

PY - 2018/8/1

Y1 - 2018/8/1

N2 - Introduction Biomarkers of metabolic syndrome expressed soon after World Trade Center (WTC) exposure predict development of WTC Lung Injury (WTC-LI). The metabolome remains an untapped resource with potential to comprehensively characterise many aspects of WTC-LI. This case-control study identified a clinically relevant, robust subset of metabolic contributors of WTC-LI through comprehensive high-dimensional metabolic profiling and integration of machine learning techniques. Methods Never-smoking, male, WTC-exposed firefighters with normal pre-9/11 lung function were segregated by post-9/11 lung function. Cases of WTC-LI (forced expiratory volume in 1s

AB - Introduction Biomarkers of metabolic syndrome expressed soon after World Trade Center (WTC) exposure predict development of WTC Lung Injury (WTC-LI). The metabolome remains an untapped resource with potential to comprehensively characterise many aspects of WTC-LI. This case-control study identified a clinically relevant, robust subset of metabolic contributors of WTC-LI through comprehensive high-dimensional metabolic profiling and integration of machine learning techniques. Methods Never-smoking, male, WTC-exposed firefighters with normal pre-9/11 lung function were segregated by post-9/11 lung function. Cases of WTC-LI (forced expiratory volume in 1s

KW - occupational lung disease

KW - systemic disease and lungs

UR - http://www.scopus.com/inward/record.url?scp=85054499120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054499120&partnerID=8YFLogxK

U2 - 10.1136/bmjresp-2017-000274

DO - 10.1136/bmjresp-2017-000274

M3 - Article

AN - SCOPUS:85054499120

VL - 5

JO - BMJ Open Respiratory Research

JF - BMJ Open Respiratory Research

SN - 2052-4439

IS - 1

M1 - e000274

ER -