A diagnostic miRNA signature for pulmonary arterial hypertension using a consensus machine learning approach
Niamh Errington,
James Iremonger,
Josephine A. Pickworth,
Sokratis Kariotis,
Christopher J. Rhodes,
Alexander MK Rothman,
Robin Condliffe,
Charles A. Elliot,
David G. Kiely,
Luke S. Howard,
John Wharton,
A. A. Roger Thompson,
Nicholas W Morrell,
Martin R. Wilkins,
Dennis Wang,
Allan Lawrie
Affiliations
Niamh Errington
Sheffield Institute for Translational Neuroscience, University of Sheffield, UK
James Iremonger
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK
Josephine A. Pickworth
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK
Sokratis Kariotis
Sheffield Institute for Translational Neuroscience, University of Sheffield, UK
Christopher J. Rhodes
National Heart & Lung Institute, Imperial College London, Hammersmith Campus, Du Cane Road, London, UK
Alexander MK Rothman
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK; Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
Robin Condliffe
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK; Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
Charles A. Elliot
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK; Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
David G. Kiely
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK
Luke S. Howard
National Pulmonary Hypertension Service, Imperial College Healthcare Trust NHS, Hammersmith Hospital, Du Cane Road, London, UK
John Wharton
National Heart & Lung Institute, Imperial College London, Hammersmith Campus, Du Cane Road, London, UK
A. A. Roger Thompson
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK; Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield, UK
Nicholas W Morrell
Department for Medicine, University of Cambridge, UK
Martin R. Wilkins
National Heart & Lung Institute, Imperial College London, Hammersmith Campus, Du Cane Road, London, UK
Dennis Wang
Sheffield Institute for Translational Neuroscience, University of Sheffield, UK; Department of Computer Science, University of Sheffield, UK; Singapore Institute for Clinical Sciences, Singapore, Singapore
Allan Lawrie
Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Beech Hill Road, Sheffield, UK; Corresponding author.
Background: Pulmonary arterial hypertension (PAH) is a rare but life shortening disease, the diagnosis of which is often delayed, and requires an invasive right heart catheterisation. Identifying diagnostic biomarkers may improve screening to identify patients at risk of PAH earlier and provide new insights into disease pathogenesis. MicroRNAs are small, non-coding molecules of RNA, previously shown to be dysregulated in PAH, and contribute to the disease process in animal models. Methods: Plasma from 64 treatment naïve patients with PAH and 43 disease and healthy controls were profiled for microRNA expression by Agilent Microarray. Following quality control and normalisation, the cohort was split into training and validation sets. Four separate machine learning feature selection methods were applied to the training set, along with a univariate analysis. Findings: 20 microRNAs were identified as putative biomarkers by consensus feature selection from all four methods. Two microRNAs (miR-636 and miR-187-5p) were selected by all methods and used to predict PAH diagnosis with high accuracy. Integrating microRNA expression profiles with their associated target mRNA revealed 61 differentially expressed genes verified in two independent, publicly available PAH lung tissue data sets. Two of seven potentially novel gene targets were validated as differentially expressed in vitro in human pulmonary artery smooth muscle cells. Interpretation: This consensus of multiple machine learning approaches identified two miRNAs that were able to distinguish PAH from both disease and healthy controls. These circulating miRNA, and their target genes may provide insight into PAH pathogenesis and reveal novel regulators of disease and putative drug targets.
