A generalized association test based on U statistics

Abstract

Summary:Motivation: Second generation sequencing technologies are being increasingly used for genetic association studies, where the main research interest is to identify sets of genetic variants that contribute to various phenotype. The phenotype can be univariate disease status, multivariate responses and even high-dimensional outcomes. Considering the genotype and phenotype as two complex objects, this also poses a general statistical problem of testing association between complex objects. Results: We here proposed a similarity-based test, generalized similarity U (GSU), that can test the association between complex objects. We first studied the theoretical properties of the test in a general setting and then focused on the application of the test to sequencing association studies. Based on theoretical analysis, we proposed to use Laplacian kernel based similarity for GSU to boost power and enhance robustness. Through simulation, we found that GSU did have advantages over existing methods in terms of power and robustness. We further performed a whole genome sequencing (WGS) scan for Alzherimer's Disease Neuroimaging Initiative (ADNI) data, identifying three genes, APOE, APOC1 and TOMM40, associated with imaging phenotype. Availability: We developed a C++ package for analysis of whole genome sequencing data using GSU. The source codes can be downloaded at https://github.com/changshuaiwei/gsu. Contact:

Exome-wide rare variant analyses of two bone mineral density phenotypes: the challenges of analyzing rare genetic variation

“…In addition, similar to other set-based association studies, here we have only provided an overall p -value for the association between a group of variants and the phenotypes. We note also that a nonparametric multiple-trait set-based test has recently been developed based on generalized similarity U-statistics 35 , and it would be worth comparing its performance with MURAT.…”

Unpaired Data Empowers Association Tests

“…Our method, the Semi-paired Association Test (SAT), generalizes two popular methods for association testing, the Variance Component Score Test (VCST) and the Kernel Independent Test (KIT), which are commonly used in statistical genetics to test the heritability of traits [17,20] or gene-level associations [19,28,35]. More specifically, a variant of our method, SAT-fx, generalizes the VCST, which assumes that one of the modalities is not a random variable (i.e., fixed).…”

“…Kernel independence tests are a class of nonparametric methods which are also widely used for genetic association studies [22,28]. Here we briefly review the Hilbert-Schmidt Independence Criterion (HSIC)-based independence test [22], which provides a general framework for many association tests [25].…”

“…The VCST is commonly used to test for heritability of a phenotype [16][17][18][19][20] and is implemented in popular software such as GCTA [26]. The KIT is widely used for statistical independence test in various scenarios [22,25,27,28]. We provide a connection between those methods.…”

Set‐based genetic association and interaction tests for survival outcomes based on weighted V statistics

“…The new tests can be considered an extension of the (heterogeneity) weighted‐U‐statistic‐based association tests (Wei, Elston, & Lu, 2016; Wei & Lu, 2017) to censored survival traits. The (heterogeneity) weighted‐U‐statistic‐based association tests are similarity‐based tests, defined as the summation of phenotype similarities weighted by (heterogeneity weighted) genetic similarities over all pairs of individuals (Wei & Lu, 2017; Wei et al, 2016). The phenotype similarity in weighted‐U‐statistic‐based tests can be defined on different types of data (e.g., continuous and categorical data), making the tests applicable to various types of traits.…”