Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

DeepWAS: multivariate genotype-phenotype associations by directly integrating regulatory information using deep learning

[img]
Preview
PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
3MB
[img] Other (Supporting Information)
4MB

Item Type:Article
Title:DeepWAS: multivariate genotype-phenotype associations by directly integrating regulatory information using deep learning
Creators Name:Arloth, J. and Eraslan, G. and Andlauer, T.F.M. and Martins, J. and Iurato, S. and Kühnel, B. and Waldenberger, M. and Frank, J. and Gold, R. and Hemmer, B. and Luessi, F. and Nischwitz, S. and Paul, F. and Wiendl, H. and Gieger, C. and Heilmann-Heimbach, S. and Kacprowski, T. and Laudes, M. and Meitinger, T. and Peters, A. and Rawal, R. and Strauch, K. and Lucae, S. and Müller-Myhsok, B. and Rietschel, M. and Theis, F.J. and Binder, E.B. and Mueller, N.S.
Abstract:Genome-wide association studies (GWAS) identify genetic variants associated with traits or diseases. GWAS never directly link variants to regulatory mechanisms. Instead, the functional annotation of variants is typically inferred by post hoc analyses. A specific class of deep learning-based methods allows for the prediction of regulatory effects per variant on several cell type-specific chromatin features. We here describe "DeepWAS", a new approach that integrates these regulatory effect predictions of single variants into a multivariate GWAS setting. Thereby, single variants associated with a trait or disease are directly coupled to their impact on a chromatin feature in a cell type. Up to 61 regulatory SNPs, called dSNPs, were associated with multiple sclerosis (MS, 4,888 cases and 10,395 controls), major depressive disorder (MDD, 1,475 cases and 2,144 controls), and height (5,974 individuals). These variants were mainly non-coding and reached at least nominal significance in classical GWAS. The prediction accuracy was higher for DeepWAS than for classical GWAS models for 91% of the genome-wide significant, MS-specific dSNPs. DSNPs were enriched in public or cohort-matched expression and methylation quantitative trait loci and we demonstrated the potential of DeepWAS to generate testable functional hypotheses based on genotype data alone. DeepWAS is available at https://github.com/cellmapslab/DeepWAS.
Keywords:Deep Learning, Genetic Association Studies, Genome-Wide Association Study, Multivariate Analysis, Quantitative Trait Loci, Single Nucleotide Polymorphism
Source:PLoS Computational Biology
ISSN:1553-734X
Publisher:Public Library of Science
Volume:16
Number:2
Page Range:e1007616
Date:3 February 2020
Official Publication:https://doi.org/10.1371/journal.pcbi.1007616
PubMed:View item in PubMed
Related to:
URLURL Type
https://edoc.mdc-berlin.de/18193/Preprint version

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library