Dataset Information

Detecting gene-by-smoking interactions in a genome-wide association study of early-onset coronary heart disease using random forests.

ABSTRACT: BACKGROUND:Genome-wide association studies are often limited in their ability to attain their full potential due to the sheer volume of information created. We sought to use the random forest algorithm to identify single-nucleotide polymorphisms (SNPs) that may be involved in gene-by-smoking interactions related to the early-onset of coronary heart disease. METHODS:Using data from the Framingham Heart Study, our analysis used a case-only design in which the outcome of interest was age of onset of early coronary heart disease. RESULTS:Smoking status was dichotomized as ever versus never. The single SNP with the highest importance score assigned by random forests was rs2011345. This SNP was not associated with age alone in the control subjects. Using generalized estimating equations to adjust for sex and account for familial correlation, there was evidence of an interaction between rs2011345 and smoking status. CONCLUSION:The results of this analysis suggest that random forests may be a useful tool for identifying SNPs taking part in gene-by-environment interactions in genome-wide association studies.

SUBMITTER: Maenner MJ

PROVIDER: S-EPMC2795991 | biostudies-literature | 2009 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Detecting gene-by-smoking interactions in a genome-wide association study of early-onset coronary heart disease using random forests.

Maenner Matthew J MJ Denlinger Loren C LC Langton Asher A Meyers Kristin J KJ Engelman Corinne D CD Skinner Halcyon G HG

BMC proceedings 20091215

<h4>Background</h4>Genome-wide association studies are often limited in their ability to attain their full potential due to the sheer volume of information created. We sought to use the random forest algorithm to identify single-nucleotide polymorphisms (SNPs) that may be involved in gene-by-smoking interactions related to the early-onset of coronary heart disease.<h4>Methods</h4>Using data from the Framingham Heart Study, our analysis used a case-only design in which the outcome of interest was ...[more]

PMID: 20018084

Similar Datasets

Project description:Many GWAS have identified novel loci associated with common diseases, but have focused only on main effects of individual genetic variants rather than interactions with environmental factors (GxE). Identification of GxE interactions is particularly important for coronary heart disease (CHD), a major preventable source of morbidity and mortality with strong non-genetic risk factors. Atherosclerosis is the major cause of CHD, and coronary artery calcification (CAC) is directly correlated with quantity of coronary atherosclerotic plaque. In the current study, we tested for genetic variants influencing extent of CAC via interaction with smoking (GxS), by conducting a GxS discovery GWAS in Genetic Epidemiology Network of Arteriopathy (GENOA) sibships (N?=?915 European Americans) followed by replication in Framingham Heart Study (FHS) sibships (N?=?1025 European Americans). Generalized estimating equations accounted for the correlation within sibships in strata-specific groups of smokers and nonsmokers, as well as GxS interaction. Primary analysis found SNPs that showed suggestive associations (p?10(-5)) in GENOA GWAS, but these index SNPs did not replicate in FHS. However, secondary analysis was able to replicate candidate gene regions in FHS using other SNPs (+/-250 kb of GENOA index SNP). In smoker and nonsmoker groups, replicated genes included TCF7L2 (p?=?6.0×10(-5)) and WWOX (p?=?4.5×10(-6)); and TNFRSF8 (p?=?7.8×10(-5)), respectively. For GxS interactions, replicated genes included TBC1D4 (p?=?6.9×10(-5)) and ADAMTS9 (P?=?7.1×10(-5)). Interestingly, these genes are involved in inflammatory pathways mediated by the NF-?B axis. Since smoking is known to induce chronic and systemic inflammation, association of these genes likely reflects roles in CAC development via inflammatory pathways. Furthermore, the NF-?B axis regulates bone remodeling, a key physiological process in CAC development. In conclusion, GxS GWAS has yielded evidence for novel loci that are associated with CAC via interaction with smoking, providing promising new targets for future population-based and functional studies of CAC development.

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.

Dataset Information

Detecting gene-by-smoking interactions in a genome-wide association study of early-onset coronary heart disease using random forests.

Publications

Detecting gene-by-smoking interactions in a genome-wide association study of early-onset coronary heart disease using random forests.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure