PMID- 34288906 OWN - NLM STAT- MEDLINE DCOM- 20211101 LR - 20220304 IS - 1553-7358 (Electronic) IS - 1553-734X (Print) IS - 1553-734X (Linking) VI - 17 IP - 7 DP - 2021 Jul TI - PEDF, a pleiotropic WTC-LI biomarker: Machine learning biomarker identification and validation. PG - e1009144 LID - 10.1371/journal.pcbi.1009144 [doi] LID - e1009144 AB - 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. FAU - Crowley, George AU - Crowley G AD - Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, New York University School of Medicine, New York, New York, United States of America. FAU - Kim, James AU - Kim J AUID- ORCID: 0000-0002-9257-2801 AD - Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, New York University School of Medicine, New York, New York, United States of America. FAU - Kwon, Sophia AU - Kwon S AUID- ORCID: 0000-0003-3639-5107 AD - Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, New York University School of Medicine, New York, New York, United States of America. FAU - Lam, Rachel AU - Lam R AUID- ORCID: 0000-0002-8731-9481 AD - Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, New York University School of Medicine, New York, New York, United States of America. FAU - Prezant, David J AU - Prezant DJ AD - Bureau of Health Services, Fire Department of New York, Brooklyn, New York, United States of America. AD - Department of Medicine, Pulmonary Medicine Division, Montefiore Medical Center and Albert Einstein College of Medicine, Bronx, New York, United States of America. FAU - Liu, Mengling AU - Liu M AUID- ORCID: 0000-0001-9758-8522 AD - Department of Environmental Medicine, New York University School of Medicine, New York, New York, United States of America. AD - Department of Population Health, Division of Biostatistics, New York University School of Medicine, New York, New York, United States of America. FAU - Nolan, Anna AU - Nolan A AUID- ORCID: 0000-0002-0631-1171 AD - Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, New York University School of Medicine, New York, New York, United States of America. AD - Bureau of Health Services, Fire Department of New York, Brooklyn, New York, United States of America. AD - Department of Environmental Medicine, New York University School of Medicine, New York, New York, United States of America. LA - eng GR - U01 OH012069/OH/NIOSH CDC HHS/United States GR - U01 OH011300/OH/NIOSH CDC HHS/United States GR - U01 OH011855/OH/NIOSH CDC HHS/United States GR - U01OH011300/ACL/ACL HHS/United States GR - R01 HL119326/HL/NHLBI NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural PT - Research Support, Non-U.S. Gov't DEP - 20210721 PL - United States TA - PLoS Comput Biol JT - PLoS computational biology JID - 101238922 RN - 0 (Biomarkers) RN - 0 (Eye Proteins) RN - 0 (Nerve Growth Factors) RN - 0 (Serpins) RN - 0 (pigment epithelium-derived factor) SB - IM MH - Adult MH - Biomarkers/blood MH - Eye Proteins/*blood MH - Firefighters MH - Humans MH - Inhalation Exposure/statistics & numerical data MH - Longitudinal Studies MH - *Lung Injury/blood/diagnosis/epidemiology/etiology MH - *Machine Learning MH - Male MH - Middle Aged MH - Models, Statistical MH - Nerve Growth Factors/*blood MH - *Occupational Diseases/blood/epidemiology/etiology MH - Reproducibility of Results MH - Sensitivity and Specificity MH - *September 11 Terrorist Attacks MH - Serpins/*blood PMC - PMC8328304 COIS- The authors have declared that no competing interests exist. EDAT- 2021/07/22 06:00 MHDA- 2021/11/03 06:00 PMCR- 2021/07/21 CRDT- 2021/07/21 17:23 PHST- 2020/10/15 00:00 [received] PHST- 2021/06/03 00:00 [accepted] PHST- 2021/08/02 00:00 [revised] PHST- 2021/07/22 06:00 [pubmed] PHST- 2021/11/03 06:00 [medline] PHST- 2021/07/21 17:23 [entrez] PHST- 2021/07/21 00:00 [pmc-release] AID - PCOMPBIOL-D-20-01880 [pii] AID - 10.1371/journal.pcbi.1009144 [doi] PST - epublish SO - PLoS Comput Biol. 2021 Jul 21;17(7):e1009144. doi: 10.1371/journal.pcbi.1009144. eCollection 2021 Jul.