Brain-wide Genome-wide Association Study for Alzheimer's Disease via Joint Projection Learning and Sparse Regression Model

Tao Zhou, Kim Han Thung, Mingxia Liu, Dinggang Shen

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In this paper, a Brain-Wide and Genome-Wide Association (BW-GWA) study is presented to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants (i.e., Single Nucleotide Polymorphism (SNP)) in Alzheimer's Disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes to an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes to a diagnostic-label-guided joint feature space, where the intra-class projected points are constrained to be close to each other. In addition, we use L2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers, and to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and the results show that the proposed method outperforms several state-of-the-art methods in term of average Root-Mean-Square Error (RMSE) of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions found in this study have also been shown AD-related in previously studies, thus verifying the effectiveness and potential of the proposed method in AD pathogenesis study.

Original languageEnglish
JournalIEEE Transactions on Biomedical Engineering
DOIs
Publication statusAccepted/In press - 2018 Apr 6

Fingerprint

Genome-Wide Association Study
Brain
Alzheimer Disease
Genes
Joints
Learning
Phenotype
Imaging techniques
Genetic Association Studies
Labels
Single Nucleotide Polymorphism
Neuroimaging
Genotype
Nucleotides
Polymorphism
Mean square error
Feature extraction
Genome

Keywords

  • Alzheimer's disease (AD)
  • Bioinformatics
  • Brain-Wide and Genome-Wide Association (BW-GWA) study
  • Diseases
  • feature selection
  • Genomics
  • l2, 1-norm minimization
  • Magnetic resonance imaging
  • Magnetic Resonance Imaging (MRI)
  • Neuroimaging
  • Single Nucleotide Polymorphism (SNP)
  • sparse regression model

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

@article{c1a7524bb03d4bceba2f1e0691ba2a7d,
title = "Brain-wide Genome-wide Association Study for Alzheimer's Disease via Joint Projection Learning and Sparse Regression Model",
abstract = "In this paper, a Brain-Wide and Genome-Wide Association (BW-GWA) study is presented to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants (i.e., Single Nucleotide Polymorphism (SNP)) in Alzheimer's Disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes to an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes to a diagnostic-label-guided joint feature space, where the intra-class projected points are constrained to be close to each other. In addition, we use L2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers, and to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and the results show that the proposed method outperforms several state-of-the-art methods in term of average Root-Mean-Square Error (RMSE) of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions found in this study have also been shown AD-related in previously studies, thus verifying the effectiveness and potential of the proposed method in AD pathogenesis study.",
keywords = "Alzheimer's disease (AD), Bioinformatics, Brain-Wide and Genome-Wide Association (BW-GWA) study, Diseases, feature selection, Genomics, l2, 1-norm minimization, Magnetic resonance imaging, Magnetic Resonance Imaging (MRI), Neuroimaging, Single Nucleotide Polymorphism (SNP), sparse regression model",
author = "Tao Zhou and Thung, {Kim Han} and Mingxia Liu and Dinggang Shen",
year = "2018",
month = "4",
day = "6",
doi = "10.1109/TBME.2018.2824725",
language = "English",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Brain-wide Genome-wide Association Study for Alzheimer's Disease via Joint Projection Learning and Sparse Regression Model

AU - Zhou, Tao

AU - Thung, Kim Han

AU - Liu, Mingxia

AU - Shen, Dinggang

PY - 2018/4/6

Y1 - 2018/4/6

N2 - In this paper, a Brain-Wide and Genome-Wide Association (BW-GWA) study is presented to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants (i.e., Single Nucleotide Polymorphism (SNP)) in Alzheimer's Disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes to an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes to a diagnostic-label-guided joint feature space, where the intra-class projected points are constrained to be close to each other. In addition, we use L2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers, and to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and the results show that the proposed method outperforms several state-of-the-art methods in term of average Root-Mean-Square Error (RMSE) of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions found in this study have also been shown AD-related in previously studies, thus verifying the effectiveness and potential of the proposed method in AD pathogenesis study.

AB - In this paper, a Brain-Wide and Genome-Wide Association (BW-GWA) study is presented to identify the associations between the brain imaging phenotypes (i.e., regional volumetric measures) and the genetic variants (i.e., Single Nucleotide Polymorphism (SNP)) in Alzheimer's Disease (AD). The main challenges of this study include the data heterogeneity, complex phenotype-genotype associations, high-dimensional data (e.g., thousands of SNPs), and the existence of phenotype outliers. Previous BW-GWA studies, while addressing some of these challenges, did not consider the diagnostic label information in their formulations, thus limiting their clinical applicability. To address these issues, we present a novel joint projection and sparse regression model to discover the associations between the phenotypes and genotypes. Specifically, to alleviate the negative influence of data heterogeneity, we first map the genotypes to an intermediate imaging-phenotype-like space. Then, to better reveal the complex phenotype-genotype associations, we project both the mapped genotypes and the original imaging phenotypes to a diagnostic-label-guided joint feature space, where the intra-class projected points are constrained to be close to each other. In addition, we use L2,1-norm minimization on both the regression loss function and the transformation coefficient matrices, to reduce the effect of phenotype outliers, and to encourage sparse feature selections of both the genotypes and phenotypes. We evaluate our method using Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and the results show that the proposed method outperforms several state-of-the-art methods in term of average Root-Mean-Square Error (RMSE) of genome-to-phenotype predictions. Besides, the associated SNPs and brain regions found in this study have also been shown AD-related in previously studies, thus verifying the effectiveness and potential of the proposed method in AD pathogenesis study.

KW - Alzheimer's disease (AD)

KW - Bioinformatics

KW - Brain-Wide and Genome-Wide Association (BW-GWA) study

KW - Diseases

KW - feature selection

KW - Genomics

KW - l2, 1-norm minimization

KW - Magnetic resonance imaging

KW - Magnetic Resonance Imaging (MRI)

KW - Neuroimaging

KW - Single Nucleotide Polymorphism (SNP)

KW - sparse regression model

UR - http://www.scopus.com/inward/record.url?scp=85045204374&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045204374&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2824725

DO - 10.1109/TBME.2018.2824725

M3 - Article

C2 - 29993426

AN - SCOPUS:85045204374

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

ER -