Format

Send to

Choose Destination
Nucleic Acids Res. 2019 Oct 10. pii: gkz868. doi: 10.1093/nar/gkz868. [Epub ahead of print]

Convolutional neural network model to predict causal risk factors that share complex regulatory features.

Author information

1
Graduate School of Medical Science and Engineering, KAIST, Daejeon 34141, Republic of Korea.
2
Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
3
MRC Laboratory of Molecular Biology, Francis Crick Avenue, Cambridge CB2 0QH, UK.
4
Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul 06351, Republic of Korea.
5
Korean Bioinformation Center (KOBIC), KRIBB, Daejeon 34141, Republic of Korea.
6
Seminar for Statistics, Eidgenössische Technische Hochschule (ETH) Zurich, CH-8092 Zurich, Switzerland.
7
Future Medicine Division, Korea Institute of Oriental Medicine, Daejeon 34054, Republic of Korea.

Abstract

Major progress in disease genetics has been made through genome-wide association studies (GWASs). One of the key tasks for post-GWAS analyses is to identify causal noncoding variants with regulatory function. Here, on the basis of >2000 functional features, we developed a convolutional neural network framework for combinatorial, nonlinear modeling of complex patterns shared by risk variants scattered among multiple associated loci. When applied for major psychiatric disorders and autoimmune diseases, neural and immune features, respectively, exhibited high explanatory power while reflecting the pathophysiology of the relevant disease. The predicted causal variants were concentrated in active regulatory regions of relevant cell types and tended to be in physical contact with transcription factors while residing in evolutionarily conserved regions and resulting in expression changes of genes related to the given disease. We demonstrate some examples of novel candidate causal variants and associated genes. Our method is expected to contribute to the identification and functional interpretation of potential causal noncoding variants in post-GWAS analyses.

PMID:
31598692
DOI:
10.1093/nar/gkz868

Supplemental Content

Full text links

Icon for Silverchair Information Systems
Loading ...
Support Center