Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning
Summary: The genetic effect explains the causality from genetic mutations to the development of complex diseases. Existing genome-wide association study (GWAS) approaches are always built under a linear assumption, restricting their generalization in dissecting complicated causality such as the rece...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2020-09-01
|
Series: | Patterns |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666389920300684 |
id |
doaj-700d37dfe5d94cfba51af0491748e9c0 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Feng Bao Yue Deng Mulong Du Zhiquan Ren Sen Wan Kenny Ye Liang Shaohua Liu Bo Wang Junyi Xin Feng Chen David C. Christiani Meilin Wang Qionghai Dai |
spellingShingle |
Feng Bao Yue Deng Mulong Du Zhiquan Ren Sen Wan Kenny Ye Liang Shaohua Liu Bo Wang Junyi Xin Feng Chen David C. Christiani Meilin Wang Qionghai Dai Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning Patterns kernel learning association analysis deep learning genome-wide association studies disease causality |
author_facet |
Feng Bao Yue Deng Mulong Du Zhiquan Ren Sen Wan Kenny Ye Liang Shaohua Liu Bo Wang Junyi Xin Feng Chen David C. Christiani Meilin Wang Qionghai Dai |
author_sort |
Feng Bao |
title |
Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning |
title_short |
Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning |
title_full |
Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning |
title_fullStr |
Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning |
title_full_unstemmed |
Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel Learning |
title_sort |
explaining the genetic causality for complex phenotype via deep association kernel learning |
publisher |
Elsevier |
series |
Patterns |
issn |
2666-3899 |
publishDate |
2020-09-01 |
description |
Summary: The genetic effect explains the causality from genetic mutations to the development of complex diseases. Existing genome-wide association study (GWAS) approaches are always built under a linear assumption, restricting their generalization in dissecting complicated causality such as the recessive genetic effect. Therefore, a sophisticated and general GWAS model that can work with different types of genetic effects is highly desired. Here, we introduce a deep association kernel learning (DAK) model to enable automatic causal genotype encoding for GWAS at pathway level. DAK can detect both common and rare variants with complicated genetic effects where existing approaches fail. When applied to four real-world GWAS datasets including cancers and schizophrenia, our DAK discovered potential casual pathways, including the association between dilated cardiomyopathy pathway and schizophrenia. The Bigger Picture: Genetic mutations cause complex diseases in many different ways. Comprehensively identifying the genetic causality can lead to valuable insights into the development and treatment of diseases. However, existing genome-wide association study (GWAS) approaches are always built under linear assumption and simple disease models, restricting their generalization in discovering the complicated causality. DAK (deep association kernel learning) is a GWAS method that is constructed in a deep-learning framework and can simultaneously identify multiple types of genetic causalities without any modifications to the model. For biological contributions, the proposed approach enables the understanding of non-linear, complex genetic causalities and improves functional studies of the disease; for computational contributions, our method unifies kernel learning and association analysis in a joint explainable deep-learning framework. |
topic |
kernel learning association analysis deep learning genome-wide association studies disease causality |
url |
http://www.sciencedirect.com/science/article/pii/S2666389920300684 |
work_keys_str_mv |
AT fengbao explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT yuedeng explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT mulongdu explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT zhiquanren explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT senwan explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT kennyyeliang explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT shaohualiu explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT bowang explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT junyixin explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT fengchen explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT davidcchristiani explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT meilinwang explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning AT qionghaidai explainingthegeneticcausalityforcomplexphenotypeviadeepassociationkernellearning |
_version_ |
1724401385125969920 |
spelling |
doaj-700d37dfe5d94cfba51af0491748e9c02020-12-03T04:32:31ZengElsevierPatterns2666-38992020-09-0116100057Explaining the Genetic Causality for Complex Phenotype via Deep Association Kernel LearningFeng Bao0Yue Deng1Mulong Du2Zhiquan Ren3Sen Wan4Kenny Ye Liang5Shaohua Liu6Bo Wang7Junyi Xin8Feng Chen9David C. Christiani10Meilin Wang11Qionghai Dai12Department of Automation, Tsinghua University, Beijing 100084, China; Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing 100084, ChinaSchool of Astronautics, Beihang University, Beijing 100191, China; Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191, China; Corresponding authorDepartment of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA; Department of Biostatistics, Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaSchool of Astronautics, Beihang University, Beijing 100191, ChinaSchool of Astronautics, Beihang University, Beijing 100191, ChinaDepartment of Environmental Genomics, Jiangsu Key Laboratory of Cancer Biomarkers, Prevention and Treatment, Collaborative Innovation Center for Cancer Personalized Medicine, Nanjing Medical University, Nanjing 211166, China; Department of Genetic Toxicology, The Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaDepartment of Biostatistics, Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, ChinaDepartment of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA; Department of Medicine, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114, USADepartment of Environmental Genomics, Jiangsu Key Laboratory of Cancer Biomarkers, Prevention and Treatment, Collaborative Innovation Center for Cancer Personalized Medicine, Nanjing Medical University, Nanjing 211166, China; Department of Genetic Toxicology, The Key Laboratory of Modern Toxicology of Ministry of Education, Center for Global Health, School of Public Health, Nanjing Medical University, Nanjing 211166, China; Corresponding authorDepartment of Automation, Tsinghua University, Beijing 100084, China; Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing 100084, China; Corresponding authorSummary: The genetic effect explains the causality from genetic mutations to the development of complex diseases. Existing genome-wide association study (GWAS) approaches are always built under a linear assumption, restricting their generalization in dissecting complicated causality such as the recessive genetic effect. Therefore, a sophisticated and general GWAS model that can work with different types of genetic effects is highly desired. Here, we introduce a deep association kernel learning (DAK) model to enable automatic causal genotype encoding for GWAS at pathway level. DAK can detect both common and rare variants with complicated genetic effects where existing approaches fail. When applied to four real-world GWAS datasets including cancers and schizophrenia, our DAK discovered potential casual pathways, including the association between dilated cardiomyopathy pathway and schizophrenia. The Bigger Picture: Genetic mutations cause complex diseases in many different ways. Comprehensively identifying the genetic causality can lead to valuable insights into the development and treatment of diseases. However, existing genome-wide association study (GWAS) approaches are always built under linear assumption and simple disease models, restricting their generalization in discovering the complicated causality. DAK (deep association kernel learning) is a GWAS method that is constructed in a deep-learning framework and can simultaneously identify multiple types of genetic causalities without any modifications to the model. For biological contributions, the proposed approach enables the understanding of non-linear, complex genetic causalities and improves functional studies of the disease; for computational contributions, our method unifies kernel learning and association analysis in a joint explainable deep-learning framework.http://www.sciencedirect.com/science/article/pii/S2666389920300684kernel learningassociation analysisdeep learninggenome-wide association studiesdisease causality |