Stratified polygenic risk prediction model with application to CAGI bipolar disorder sequencing data

Abstract

Genetic data consists of a wide range of marker types, including common, low frequency, and rare variants. Multiple genetic markers and their interactions play central roles in the heritability of complex disease. In this study, we propose an algorithm that uses a stratified variable selection design by genetic architectures and interaction effects, achieved by a data-set adaptive W-test. The polygenic sets in all strata were integrated to form a classification rule. The algorithm was applied to the Critical Assessment of Genome Interpretation 4 bipolar challenge sequencing data. The prediction accuracy was 60% using genetic markers on an independent test set. We found that epistasis among common genetic variants contributed most substantially to prediction precision. However, the sample size was not large enough to draw conclusions for the lack of predictability of low frequency variants and their epistasis.

Reports from CAGI: The Critical Assessment of Genome Interpretation

“…For single base variants, there are challenges that address the problem of interpreting the impact of missense mutations on protein activity using a variety of molecular and cellular phenotypes, challenges that test the ability to predict the effect of mutations in cancer driver genes on cell growth, and challenges on the effect of single‐base variants on RNA expression levels and splicing (including Beer, ; Capriotti, Martelli, Fariselli, & Casadio, ; Carraro et al., ; Katsonis & Lichtarge, ; Kreimer et al., ; Niroula & Vihinen ; Pejaver et al., ; Tang et al., 2017; Tang & Fenton, ; Xu et al., ; Yin et al., ; Zeng, Edwards, Guo, & Gifford, ; Zhang et al., ). At the level of full exome and genome sequence, there are challenges that assess methods for assigning complex traits phenotypes and that evaluate the ability to associate genome sequence and an extensive profile of phenotypic traits (including Cai et al., 2017; Daneshjou et al., ; Daneshjou et al., ; Giollo et al., ; Laksshman, Bhat, Viswanath, & Li, ; Pal, Kundu, Yin, & Moult, ; Wang et al., ). CAGI has also included challenges in which participants were asked to identify causative variants for rare diseases in gene panel, exome, and whole‐genome sequence data (including Chandonia et al., ; Kundu, Pal, Yin, & Moult, ; Pal, Kundu, Yin, & Moult, ).…”

Genome-wide copy number variation-, validation- and screening study implicates a new copy number polymorphism associated with suicide attempts in major depressive disorder

“…In another study on bipolar disorder, epistasis between ZNF33B and another gene EPHB3 on Chr. 3 showed the largest effect size (OR = 3.4) (Wang et al, 2017). Another member of this family ZNF408A was reported to be involved in neural activation and cognitive performance (Walters et al, 2010;Walter et al, 2011).…”

Incorporating methylation genome information improves prediction accuracy for drug treatment responses

“…The features related to drug response were selected in a stratified manner [ 14 ], first within each data type, and then aggregated in an ANN to predict the drug response [ 15 ]. ANNs are designed to perform learning tasks using a collection of computational units and a system of interlinking connections [ 16 ].…”