Prioritizing genetic variants in GWAS with lasso using permutation-assisted tuning

Abstract

Motivation Large scale genome-wide association studies (GWAS) have resulted in the identification of a wide range of genetic variants related to a host of complex traits and disorders. Despite their success, the individual single-nucleotide polymorphism (SNP) analysis approach adopted in most current GWAS can be limited in that it is usually biologically simple to elucidate a comprehensive genetic architecture of phenotypes and statistically underpowered due to heavy multiple-testing correction burden. On the other hand, multiple-SNP analyses (e.g. gene-based or region-based SNP-set analysis) are usually more powerful to examine the joint effects of a set of SNPs on the phenotype of interest. However, current multiple-SNP approaches can only draw an overall conclusion at the SNP-set level and does not directly inform which SNPs in the SNP-set are driving the overall genotype–phenotype association. Results In this article, we propose a new permutation-assisted tuning procedure in lasso (plasso) to identify phenotype-associated SNPs in a joint multiple-SNP regression model in GWAS. The tuning parameter of lasso determines the amount of shrinkage and is essential to the performance of variable selection. In the proposed plasso procedure, we first generate permutations as pseudo-SNPs that are not associated with the phenotype. Then, the lasso tuning parameter is delicately chosen to separate true signal SNPs and non-informative pseudo-SNPs. We illustrate plasso using simulations to demonstrate its superior performance over existing methods, and application of plasso to a real GWAS dataset gains new additional insights into the genetic control of complex traits. Availability and implementation R codes to implement the proposed methodology is available at https://github.com/xyz5074/plasso. Supplementary information Supplementary data are available at Bioinformatics online.

Robust Huber-LASSO for improved prediction of protein, metabolite and gene expression levels relying on individual genotype data

“…Thus, the fitted regression model does not include all the predictors in the original dataset but only those variables with the strongest effect on the molecular phenotype, circumventing the necessity for explicit multiple testing correction; this leads more interpretable prediction models and also prevents overfitting of the model. The use of LASSO is increasingly common in the field of genetic association studies [ 2–5 ].…”

Adaptive and powerful microbiome multivariate association analysis via feature selection

“…Such choices, however, may not be appropriate for the relatively small sample sizes frequently encountered in most current microbiome association analyses. Among some popular feature selection tools ( 19 , 26 , 27 , 46 ) evaluated in our numerical studies, the feature selection strategy outlined in Algorithm 1 had the optimum performance within the context of the current paper (see details in Section 1 of the online Supplementary Data ). It is of future research interest to further boost the power of AMAT by sharping the intermediate feature selection tool embedded in it.…”

Deep Feature Screening: Feature Selection for Ultra High-Dimensional Data via Deep Neural Networks

“…For example, they ignore feature dependence and nonlinear structure, lack flexibility, and require a large sample size. When implementing these methods, people tend to assume a parametric form (like linear model and logistic regression model) to describe the relationship between the response and the features and ignore the interactions among features, which, however, can be complex and nonlinear in practice (Wu et al, 2009;Yang et al, 2020). Despite that both supervised and unsupervised feature selections have important applications, most algorithms cannot combine supervised and unsupervised learnings effectively (see Ding, 2003;Varshavsky et al, 2006;Qi et al, 2018;Zhu et al, 2018;Taherkhani et al, 2018;Solorio-Fernández et al, 2020).…”