Genome Wide Association Study to predict severe asthma exacerbations in children using random forests classifiers

Abstract

BackgroundPersonalized health-care promises tailored health-care solutions to individual patients based on their genetic background and/or environmental exposure history. To date, disease prediction has been based on a few environmental factors and/or single nucleotide polymorphisms (SNPs), while complex diseases are usually affected by many genetic and environmental factors with each factor contributing a small portion to the outcome. We hypothesized that the use of random forests classifiers to select SNPs would result in an improved predictive model of asthma exacerbations. We tested this hypothesis in a population of childhood asthmatics.MethodsIn this study, using emergency room visits or hospitalizations as the definition of a severe asthma exacerbation, we first identified a list of top Genome Wide Association Study (GWAS) SNPs ranked by Random Forests (RF) importance score for the CAMP (Childhood Asthma Management Program) population of 127 exacerbation cases and 290 non-exacerbation controls. We predict severe asthma exacerbations using the top 10 to 320 SNPs together with age, sex, pre-bronchodilator FEV1 percentage predicted, and treatment group.ResultsTesting in an independent set of the CAMP population shows that severe asthma exacerbations can be predicted with an Area Under the Curve (AUC) = 0.66 with 160-320 SNPs in comparison to an AUC score of 0.57 with 10 SNPs. Using the clinical traits alone yielded AUC score of 0.54, suggesting the phenotype is affected by genetic as well as environmental factors.ConclusionsOur study shows that a random forests algorithm can effectively extract and use the information contained in a small number of samples. Random forests, and other machine learning tools, can be used with GWAS studies to integrate large numbers of predictors simultaneously.

Novel genetic risk factors for asthma in African American children: Precision Medicine and the SAGE II Study

“…SNP rs660498 is located in an enhancer histone mark in monocytes and CD14 + cells, acting as an eQTL in whole blood (Ward and Kellis 2012). A recent study identified SNPs within Patched-Chain Domain Protein 1, PTCHD1 , an important paralog of PTCHD3 , as predictive of asthma exacerbations (Xu et al 2011). PTCHD3 and PTCHD1 are both predicted to play a role in the Hedgehog signaling pathway, although not as well characterized as PTCHD1 (Furmanski et al 2013; Ghahramani Seno et al 2011).…”

Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics

“…A major field of application of RFs is genetic epidemiology, specifically [63,79,31,64,51]. In the application of RFs to genome-wide association data, the focus has been on different features of the algorithm.…”

Building a genetic risk model for bipolar disorder from genome-wide association data with random forest algorithm

“…Among the many machine learning methods, such as support vector machine, linear discriminant analysis, and k -nearest neighbour classification, RF is often applied in biomedical research with different data sources, such as gene expression29. Similar applications are reported using GWA datasets for complex traits with low prediction errors, such as severe asthma3031. To our best knowledge, the present study reports the first prediction results for BPD using an RF approach to select informative markers which jointly consider the main and interaction effects among genetic variants.…”