Convolutional neural network model to predict causal risk factors that share complex regulatory features.
- Lee T Graduate School of Medical Science and Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Sung MK Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Lee S Graduate School of Medical Science and Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Yang W Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Oh J Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Kim JY Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
- Hwang S Seminar for Statistics, Eidgenössische Technische Hochschule (ETH) Zurich, CH-8092 Zurich, Switzerland.
- Ban HJ Future Medicine Division, Korea Institute of Oriental Medicine, Daejeon 34054, Republic of Korea.
- Choi JK Department of Bio and Brain Engineering, KAIST, Daejeon 34141, Republic of Korea.
- 2019-10-11
Published in:
- Nucleic acids research. - 2019
Autoimmune Diseases
Genetic Predisposition to Disease
Genome-Wide Association Study
Humans
Mental Disorders
Neural Networks, Computer
Polymorphism, Single Nucleotide
Quantitative Trait Loci
Regulatory Sequences, Nucleic Acid
Risk Factors
English
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.
- Language
-
- English
- Open access status
- gold
- Identifiers
-
- DOI 10.1093/nar/gkz868
- PMID 31598692
- Persistent URL
- https://sonar.ch/global/documents/112915
Statistics
Document views: 30
File downloads:
- Full-text: 0