Deep mixed model for marginal epistasis detection and population stratification correction in genome-wide association studies

Abstract

BackgroundGenome-wide Association Studies (GWAS) have contributed to unraveling associations between genetic variants in the human genome and complex traits for more than a decade. While many works have been invented as follow-ups to detect interactions between SNPs, epistasis are still yet to be modeled and discovered more thoroughly.ResultsIn this paper, following the previous study of detecting marginal epistasis signals, and motivated by the universal approximation power of deep learning, we propose a neural network method that can potentially model arbitrary interactions between SNPs in genetic association studies as an extension to the mixed models in correcting confounding factors. Our method, namely Deep Mixed Model, consists of two components: 1) a confounding factor correction component, which is a large-kernel convolution neural network that focuses on calibrating the residual phenotypes by removing factors such as population stratification, and 2) a fixed-effect estimation component, which mainly consists of an Long-short Term Memory (LSTM) model that estimates the association effect size of SNPs with the residual phenotype.ConclusionsAfter validating the performance of our method using simulation experiments, we further apply it to Alzheimer’s disease data sets. Our results help gain some explorative understandings of the genetic architecture of Alzheimer’s disease.

Machine Learning Approaches and Applications in Genome Wide Association Study for Alzheimer’s Disease: A Systematic Review

“…One article [38] used a dataset from the National Alzheimer's Coordinating Center. One article [39] used a late-onset AD dataset provided by the Harvard Brain Tissue Resource Center and Merck Research Laboratories. Two articles [40,41] requested datasets from the database of genotype and phenotype.…”

“…QC and filtering procedures were performed on individuals and their SNPs in most of the papers using PLANK software. Only four articles [39,40,43,44] did not conduct any quality control procedures.…”

“…Number of features selection testing was used in [56] where they looked at the effectiveness of these tests through the classification task. Wang et al [39] considered only the SNPs that reside protein coding exons according to GENCODE (a public research consortium) then further excluded the SNPs on Xchromosome…”

MIDESP: Mutual Information-Based Detection of Epistatic SNP Pairs for Qualitative and Quantitative Phenotypes

“…Its extension epistatic MOdule DEtection (epiMODE) [ 28 ] uses Gibbs sampling with a reversible jump Markov chain Monte Carlo to find epistatic interactions. Machine learning methods such as neural networks [ 29 , 30 , 31 , 32 ], decision trees [ 33 ] or random forest [ 34 , 35 , 36 , 37 ] have also been utilized for epistasis detection. Step-wise approaches form a fourth category of algorithms, which first filter out SNPs with a very small or no association signal, and then test among the surviving SNPs for epistatic interactions.…”

MeSCoT: the tool for quantitative trait simulation through the mechanistic modeling of genes’ regulatory interactions

“…A common approach to simulate a complex (quantitative) trait is sampling gene-by-gene ( interaction effects for some arbitrary pairwise markers, which gives genotypic values. Sampling additional “error” effects that imitate gene-by-environment ( ) interactions simulate phenotypic values ( Forneris et al 2017 ; Vitezica et al 2017 ; Momen et al 2018 ; Wang et al 2019 ; Dai et al 2020 ; Duenk et al 2020 ). Unfortunately, such approach ignores nonrandom genes co-regulation within a genomic network and rather allows imitation of extra variance in data due to randomly generated interactions based on genomic maps than build phenotypic values using full genomic architecture.…”