Dataset Information

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

ABSTRACT: Personalized 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.In 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.Testing 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.Our 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.

SUBMITTER: Xu M

PROVIDER: S-EPMC3148549 | biostudies-literature | 2011 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Xu Mousheng M Tantisira Kelan G KG Wu Ann A Litonjua Augusto A AA Chu Jen-hwa JH Himes Blanca E BE Damask Amy A Weiss Scott T ST

BMC medical genetics 20110630

<h4>Background</h4>Personalized 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 clas ...[more]

PMID: 21718536

Similar Datasets

Project description:BackgroundAsthma exacerbations are a serious public health concern due to high healthcare resource utilization, work/school productivity loss, impact on quality of life, and risk of mortality. The genetic basis of asthma exacerbations has been studied in several populations, but no prior study has performed a multi-ancestry meta-analysis of genome-wide association studies (meta-GWAS) for this trait. We aimed to identify common genetic loci associated with asthma exacerbations across diverse populations and to assess their functional role in regulating DNA methylation and gene expression.MethodsA meta-GWAS of asthma exacerbations in 4989 Europeans, 2181 Hispanics/Latinos, 1250 Singaporean Chinese, and 972 African Americans analyzed 9.6 million genetic variants. Suggestively associated variants (p ≤ 5 × 10-5 ) were assessed for replication in 36,477 European and 1078 non-European asthma patients. Functional effects on DNA methylation were assessed in 595 Hispanic/Latino and African American asthma patients and in publicly available databases. The effect on gene expression was evaluated in silico.ResultsOne hundred and twenty-six independent variants were suggestively associated with asthma exacerbations in the discovery phase. Two variants independently replicated: rs12091010 located at vascular cell adhesion molecule-1/exostosin like glycosyltransferase-2 (VCAM1/EXTL2) (discovery: odds ratio (ORT allele ) = 0.82, p = 9.05 × 10-6 and replication: ORT allele = 0.89, p = 5.35 × 10-3 ) and rs943126 from pantothenate kinase 1 (PANK1) (discovery: ORC allele = 0.85, p = 3.10 × 10-5 and replication: ORC allele = 0.89, p = 1.30 × 10-2 ). Both variants regulate gene expression of genes where they locate and DNA methylation levels of nearby genes in whole blood.ConclusionsThis multi-ancestry study revealed novel suggestive regulatory loci for asthma exacerbations located in genomic regions participating in inflammation and host defense.

Project description:Multivariate quantitative traits arise naturally in recent neuroimaging genetics studies, in which both structural and functional variability of the human brain is measured non-invasively through techniques such as magnetic resonance imaging (MRI). There is growing interest in detecting genetic variants associated with such multivariate traits, especially in genome-wide studies. Random forests (RFs) classifiers, which are ensembles of decision trees, are amongst the best performing machine learning algorithms and have been successfully employed for the prioritisation of genetic variants in case-control studies. RFs can also be applied to produce gene rankings in association studies with multivariate quantitative traits, and to estimate genetic similarities measures that are predictive of the trait. However, in studies involving hundreds of thousands of SNPs and high-dimensional traits, a very large ensemble of trees must be inferred from the data in order to obtain reliable rankings, which makes the application of these algorithms computationally prohibitive.We have developed a parallel version of the RF algorithm for regression and genetic similarity learning tasks in large-scale population genetic association studies involving multivariate traits, called PaRFR (Parallel Random Forest Regression). Our implementation takes advantage of the MapReduce programming model and is deployed on Hadoop, an open-source software framework that supports data-intensive distributed applications. Notable speed-ups are obtained by introducing a distance-based criterion for node splitting in the tree estimation process. PaRFR has been applied to a genome-wide association study on Alzheimer's disease (AD) in which the quantitative trait consists of a high-dimensional neuroimaging phenotype describing longitudinal changes in the human brain structure. PaRFR provides a ranking of SNPs associated to this trait, and produces pair-wise measures of genetic proximity that can be directly compared to pair-wise measures of phenotypic proximity. Several known AD-related variants have been identified, including APOE4 and TOMM40. We also present experimental evidence supporting the hypothesis of a linear relationship between the number of top-ranked mutated states, or frequent mutation patterns, and an indicator of disease severity.The Java codes are freely available at http://www2.imperial.ac.uk/~gmontana.

Project description:BackgroundAsthma therapy is typically prescribed and titrated based on patient or parent self-report of symptoms. No longitudinal studies have assessed the relationship between symptoms and severe asthma exacerbations in children. The goal of our study was (1) to assess the association of asthma symptoms with severe asthma exacerbations and (2) to compare predictors of persistent asthma symptoms and predictors of severe asthma exacerbations.MethodsThe Childhood Asthma Management Program was a multicenter clinical trial of 1,041 children randomized to receive budesonide, nedocromil, or placebo (as-needed ?-agonist). We conducted a post hoc analysis of diary cards that were completed by subjects on a daily basis to categorize subjects as having persistent vs intermittent symptoms. We defined a severe asthma exacerbation as an episode requiring ? 3 days use of oral corticosteroids, hospitalization, or ED visit due to asthma based on self-report at study visits every 4 months.ResultsWhile accounting for longitudinal measures, having persistent symptoms from asthma was significantly associated with having severe asthma exacerbations. Predictors of having persistent symptoms compared with intermittent symptoms included not being treated with inhaled corticosteroids, lower FEV(1)/FVC ratio, and a lower natural logarithm of provocative concentration of methacholine producing a 20% decline in FEV(1) (lnPC(20)). Predictors of having one or more severe asthma exacerbations included younger age, history of hospitalization or ED visit in the prior year, ? 3 days use of oral corticosteroids in the prior 3 months, lower FEV(1)/FVC ratio, lower lnPC(20), and higher logarithm to the base 10 eosinophil count; treatment with inhaled corticosteroids was predictive of having no severe asthma exacerbations.ConclusionsPatients with persistent symptoms from asthma were more likely to experience severe asthma exacerbations. Nevertheless, demographic and laboratory predictors of having persistent symptoms are different from predictors of severe asthma exacerbations. Although symptoms and exacerbations are closely related, their predictors are different. The current focus of the National Asthma Education and Prevention Program guidelines on the two separate domains of asthma control, impairment and risk, are supported by our analysis.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets