Evaluation of the lasso and the elastic net in genome-wide association studies

Abstract

The number of publications performing genome-wide association studies (GWAS) has increased dramatically. Penalized regression approaches have been developed to overcome the challenges caused by the high dimensional data, but these methods are relatively new in the GWAS field. In this study we have compared the statistical performance of two methods (the least absolute shrinkage and selection operator—lasso and the elastic net) on two simulated data sets and one real data set from a 50 K genome-wide single nucleotide polymorphism (SNP) panel of 5570 Fleckvieh bulls. The first simulated data set displays moderate to high linkage disequilibrium between SNPs, whereas the second simulated data set from the QTLMAS 2010 workshop is biologically more complex. We used cross-validation to find the optimal value of regularization parameter λ with both minimum MSE and minimum MSE + 1SE of minimum MSE. The optimal λ values were used for variable selection. Based on the first simulated data, we found that the minMSE in general picked up too many SNPs. At minMSE + 1SE, the lasso didn't acquire any false positives, but selected too few correct SNPs. The elastic net provided the best compromise between few false positives and many correct selections when the penalty weight α was around 0.1. However, in our simulation setting, this α value didn't result in the lowest minMSE + 1SE. The number of selected SNPs from the QTLMAS 2010 data was after correction for population structure 82 and 161 for the lasso and the elastic net, respectively. In the Fleckvieh data set after population structure correction lasso and the elastic net identified from 1291 to 1966 important SNPs for milk fat content, with major peaks on chromosomes 5, 14, 15, and 20. Hence, we can conclude that it is important to analyze GWAS data with both the lasso and the elastic net and an alternative tuning criterion to minimum MSE is needed for variable selection.

Integrative modelling of tumour DNA methylation quantifies the contribution of metabolism

“…The algorithm was developed and benchmarked to avoid over-fitting in statistical modelling of high-dimensional data containing collinearity60. We applied the Elastic Net algorithm using the R package ‘glmnet'61.…”

Least absolute shrinkage and selection operator and dimensionality reduction techniques in quantitative structure retention relationship modeling of retention in hydrophilic interaction liquid chromatography

“…The most common technique to estimate is to use crossvalidation [27,28]. In practice, an inspection of the graph of the cross-validation error curve c( ) suffices.…”

A LASSO penalized regression approach for genome-wide association analyses using related individuals: application to the Genetic Analysis Workshop 19 simulated data

“…Because of the computational intensity involved in the estimation of the parameters of the LMM, most methods perform single marker analysis [5]. As GWAS typically include a very large number of single-nucleotide polymorphisms (SNPs), it is imperative to control for type I error.…”

“…Typically, this is achieved through the use of some multiplicity adjustment method such as Bonferonni’s. Lately, least absolute shrinkage and selection operator (LASSO) regression [6] has attracted attention as an alternative tool for selecting the most promising SNPs in GWAS [5, 7]. LASSO regression has the advantage that, by modelling multiple SNPs simultaneously, it can distinguish trait contributing loci from loci that are in high linkage disequilibrium with those loci.…”