Evaluation of random forests performance for genome-wide association studies in the presence of interaction effects.
Ontology highlight
ABSTRACT:
SUBMITTER: Kim Y
PROVIDER: S-EPMC2795965 | biostudies-literature | 2009 Dec
REPOSITORIES: biostudies-literature
Publications
Evaluation of random forests performance for genome-wide association studies in the presence of interaction effects.
Kim Yoonhee Y Wojciechowski Robert R Sung Heejong H Mathias Rasika A RA Wang Li L Klein Alison P AP Lenroot Rhoshel K RK Malley James J Bailey-Wilson Joan E JE
BMC proceedings 20091215
Random forests (RF) is one of a broad class of machine learning methods that are able to deal with large-scale data without model specification, which makes it an attractive method for genome-wide association studies (GWAS). The performance of RF and other association methods in the presence of interactions was evaluated using the simulated data from Genetic Analysis Workshop 16 Problem 3, with knowledge of the major causative markers, risk factors, and their interactions in the simulated traits ...[more]
Similar Datasets
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.
| S-EPMC3853073 | biostudies-literature
Project description:BackgroundMachine learning methods and in particular random forests (RFs) are a promising alternative to standard single SNP analyses in genome-wide association studies (GWAS). RFs provide variable importance measures (VIMs) to rank SNPs according to their predictive power. However, in contrast to the established genome-wide significance threshold, no clear criteria exist to determine how many SNPs should be selected for downstream analyses.ResultsWe propose a new variable selection approach, recurrent relative variable importance measure (r2VIM). Importance values are calculated relative to an observed minimal importance score for several runs of RF and only SNPs with large relative VIMs in all of the runs are selected as important. Evaluations on simulated GWAS data show that the new method controls the number of false-positives under the null hypothesis. Under a simple alternative hypothesis with several independent main effects it is only slightly less powerful than logistic regression. In an experimental GWAS data set, the same strong signal is identified while the approach selects none of the SNPs in an underpowered GWAS.ConclusionsThe novel variable selection method r2VIM is a promising extension to standard RF for objectively selecting relevant SNPs in GWAS while controlling the number of false-positive results.
| S-EPMC4736152 | biostudies-literature
Project description:It is a commonly held belief that most complex diseases (e.g., diabetes, asthma, cancer) are affected in part by interactions between genes and environmental factors. However, investigators conducting genome-wide association studies typically test for only the marginal effects of each genetic marker on disease. In this paper, the authors propose an efficient and easily implemented 2-step analysis of genome-wide association study data aimed at identifying genes involved in a gene-environment interaction. The procedure complements screening for marginal genetic effects and thus has the potential to uncover new genetic signals that have not been identified previously.
| S-EPMC2732981 | biostudies-literature
Project description:BACKGROUND:Single-nucleotide polymorphisms (SNPs) selection and identification are the most important tasks in Genome-wide association data analysis. The problem is difficult because genome-wide association data is very high dimensional and a large portion of SNPs in the data is irrelevant to the disease. Advanced machine learning methods have been successfully used in Genome-wide association studies (GWAS) for identification of genetic variants that have relatively big effects in some common, complex diseases. Among them, the most successful one is Random Forests (RF). Despite of performing well in terms of prediction accuracy in some data sets with moderate size, RF still suffers from working in GWAS for selecting informative SNPs and building accurate prediction models. In this paper, we propose to use a new two-stage quality-based sampling method in random forests, named ts-RF, for SNP subspace selection for GWAS. The method first applies p-value assessment to find a cut-off point that separates informative and irrelevant SNPs in two groups. The informative SNPs group is further divided into two sub-groups: highly informative and weak informative SNPs. When sampling the SNP subspace for building trees for the forest, only those SNPs from the two sub-groups are taken into account. The feature subspaces always contain highly informative SNPs when used to split a node at a tree. RESULTS:This approach enables one to generate more accurate trees with a lower prediction error, meanwhile possibly avoiding overfitting. It allows one to detect interactions of multiple SNPs with the diseases, and to reduce the dimensionality and the amount of Genome-wide association data needed for learning the RF model. Extensive experiments on two genome-wide SNP data sets (Parkinson case-control data comprised of 408,803 SNPs and Alzheimer case-control data comprised of 380,157 SNPs) and 10 gene data sets have demonstrated that the proposed model significantly reduced prediction errors and outperformed most existing the-state-of-the-art random forests. The top 25 SNPs in Parkinson data set were identified by the proposed model including four interesting genes associated with neurological disorders. CONCLUSION:The presented approach has shown to be effective in selecting informative sub-groups of SNPs potentially associated with diseases that traditional statistical approaches might fail. The new RF works well for the data where the number of case-control objects is much smaller than the number of SNPs, which is a typical problem in gene data and GWAS. Experiment results demonstrated the effectiveness of the proposed RF model that outperformed the state-of-the-art RFs, including Breiman's RF, GRRF and wsRF methods.
| S-EPMC4331719 | biostudies-literature
Project description: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.
| S-EPMC3148549 | biostudies-literature
Project description:As computational power improves, the application of more advanced machine learning techniques to the analysis of large genome-wide association (GWA) datasets becomes possible. While most traditional statistical methods can only elucidate main effects of genetic variants on risk for disease, certain machine learning approaches are particularly suited to discover higher order and non-linear effects. One such approach is the Random Forests (RF) algorithm. The use of RF for SNP discovery related to human disease has grown in recent years; however, most work has focused on small datasets or simulation studies which are limited.Using a multiple sclerosis (MS) case-control dataset comprised of 300 K SNP genotypes across the genome, we outline an approach and some considerations for optimally tuning the RF algorithm based on the empirical dataset. Importantly, results show that typical default parameter values are not appropriate for large GWA datasets. Furthermore, gains can be made by sub-sampling the data, pruning based on linkage disequilibrium (LD), and removing strong effects from RF analyses. The new RF results are compared to findings from the original MS GWA study and demonstrate overlap. In addition, four new interesting candidate MS genes are identified, MPHOSPH9, CTNNA3, PHACTR2 and IL7, by RF analysis and warrant further follow-up in independent studies.This study presents one of the first illustrations of successfully analyzing GWA data with a machine learning algorithm. It is shown that RF is computationally feasible for GWA data and the results obtained make biologic sense based on previous studies. More importantly, new genes were identified as potentially being associated with MS, suggesting new avenues of investigation for this complex disease.
| S-EPMC2896336 | biostudies-literature
Project description:Genome-wide association studies (GWAS) are increasingly utilized for identifying novel susceptible genetic variants for complex traits, but there is little consensus on analysis methods for such data. Most commonly used methods include single single nucleotide polymorphism (SNP) analysis or haplotype analysis with Bonferroni correction for multiple comparisons. Since the SNPs in typical GWAS are often in linkage disequilibrium (LD), at least locally, Bonferroni correction of multiple comparisons often leads to conservative error control and therefore lower statistical power. In this paper, we propose a hidden Markov random field model (HMRF) for GWAS analysis based on a weighted LD graph built from the prior LD information among the SNPs and an efficient iterative conditional mode algorithm for estimating the model parameters. This model effectively utilizes the LD information in calculating the posterior probability that an SNP is associated with the disease. These posterior probabilities can then be used to define a false discovery controlling procedure in order to select the disease-associated SNPs. Simulation studies demonstrated the potential gain in power over single SNP analysis. The proposed method is especially effective in identifying SNPs with borderline significance at the single-marker level that nonetheless are in high LD with significant SNPs. In addition, by simultaneously considering the SNPs in LD, the proposed method can also help to reduce the number of false identifications of disease-associated SNPs. We demonstrate the application of the proposed HMRF model using data from a case-control GWAS of neuroblastoma and identify 1 new SNP that is potentially associated with neuroblastoma.
| S-EPMC2800164 | biostudies-literature
Project description:BackgroundThe typical objective of Genome-wide association (GWA) studies is to identify single-nucleotide polymorphisms (SNPs) and corresponding genes with the strongest evidence of association (the 'most-significant SNPs/genes' approach). Borrowing ideas from micro-array data analysis, we propose a new method, named RS-SNP, for detecting sets of genes enriched in SNPs moderately associated to the phenotype. RS-SNP assesses whether the number of significant SNPs, with p-value P ? ?, belonging to a given SNP set S is statistically significant. The rationale of proposed method is that two kinds of null hypotheses are taken into account simultaneously. In the first null model the genotype and the phenotype are assumed to be independent random variables and the null distribution is the probability of the number of significant SNPs in S greater than observed by chance. The second null model assumes the number of significant SNPs in S depends on the size of and not on the identity of the SNPs in . Statistical significance is assessed using non-parametric permutation tests.ResultsWe applied RS-SNP to the Crohn's disease (CD) data set collected by the Wellcome Trust Case Control Consortium (WTCCC) and compared the results with GENGEN, an approach recently proposed in literature. The enrichment analysis using RS-SNP and the set of pathways contained in the MSigDB C2 CP pathway collection highlighted 86 pathways rich in SNPs weakly associated to CD. Of these, 47 were also indicated to be significant by GENGEN. Similar results were obtained using the MSigDB C5 pathway collection. Many of the pathways found to be enriched by RS-SNP have a well-known connection to CD and often with inflammatory diseases.ConclusionsThe proposed method is a valuable alternative to other techniques for enrichment analysis of SNP sets. It is well founded from a theoretical and statistical perspective. Moreover, the experimental comparison with GENGEN highlights that it is more robust with respect to false positive findings.
| S-EPMC3079664 | biostudies-literature
Project description:The primary goal of genome-wide association studies (GWAS) is to discover variants that could lead, in isolation or in combination, to a particular trait or disease. Standard approaches to GWAS, however, are usually based on univariate hypothesis tests and therefore can account neither for correlations due to linkage disequilibrium nor for combinations of several markers. To discover and leverage such potential multivariate interactions, we propose in this work an extension of the Random Forest algorithm tailored for structured GWAS data. In terms of risk prediction, we show empirically on several GWAS datasets that the proposed T-Trees method significantly outperforms both the original Random Forest algorithm and standard linear models, thereby suggesting the actual existence of multivariate non-linear effects due to the combinations of several SNPs. We also demonstrate that variable importances as derived from our method can help identify relevant loci. Finally, we highlight the strong impact that quality control procedures may have, both in terms of predictive power and loci identification. Variable importance results and T-Trees source code are all available at www.montefiore.ulg.ac.be/~botta/ttrees/ and github.com/0asa/TTree-source respectively.
| S-EPMC3973686 | biostudies-literature
Project description:Genome-wide association studies (GWAS) have successfully discovered hundreds of associations between genetic variants and complex traits. Most GWAS have focused on the identification of single variants. It has been shown that most of the variants that were discovered by GWAS could only partially explain disease heritability. The explanation for this missing heritability is generally believed to be gene-gene (GG) or gene-environment (GE) interactions and other structural variants. Generalized multifactor dimensionality reduction (GMDR) has been proven to be reasonably powerful in detecting GG and GE interactions; however, its performance has been found to decline when outlying quantitative traits are present. This paper proposes a robust GMDR estimation method (based on the L-estimator and M-estimator estimation methods) in an attempt to reduce the effects caused by outlying traits. A comparison of robust GMDR with the original MDR based on simulation studies showed the former method to outperform the latter. The performance of robust GMDR is illustrated through a real GWA example consisting of 8,577 samples from the Korean population using the Homeostasis Model Assessment of Insulin Resistance (HOMA-IR) level as a phenotype. Robust GMDR identified the KCNH1 gene to have strong interaction effects with other genes on the function of insulin secretion.
| S-EPMC4534386 | biostudies-literature