1
|
Cui T, El Mekkaoui K, Reinvall J, Havulinna AS, Marttinen P, Kaski S. Gene-gene interaction detection with deep learning. Commun Biol 2022; 5:1238. [PMID: 36371468 PMCID: PMC9653457 DOI: 10.1038/s42003-022-04186-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2022] [Accepted: 10/27/2022] [Indexed: 11/13/2022] Open
Abstract
The extent to which genetic interactions affect observed phenotypes is generally unknown because current interaction detection approaches only consider simple interactions between top SNPs of genes. We introduce an open-source framework for increasing the power of interaction detection by considering all SNPs within a selected set of genes and complex interactions between them, beyond only the currently considered multiplicative relationships. In brief, the relation between SNPs and a phenotype is captured by a neural network, and the interactions are quantified by Shapley scores between hidden nodes, which are gene representations that optimally combine information from the corresponding SNPs. Additionally, we design a permutation procedure tailored for neural networks to assess the significance of interactions, which outperformed existing alternatives on simulated datasets with complex interactions, and in a cholesterol study on the UK Biobank it detected nine interactions which replicated on an independent FINRISK dataset.
Collapse
Affiliation(s)
- Tianyu Cui
- Department of Computer Science, Aalto University, Espoo, Finland.
| | | | - Jaakko Reinvall
- Department of Computer Science, Aalto University, Espoo, Finland
| | - Aki S Havulinna
- Finnish Institute for Health and Welfare (THL), Helsinki, Finland
- Institute for Molecular Medicine Finland, FIMM-HiLIFE, Helsinki, Finland
| | - Pekka Marttinen
- Department of Computer Science, Aalto University, Espoo, Finland
- Finnish Institute for Health and Welfare (THL), Helsinki, Finland
| | - Samuel Kaski
- Department of Computer Science, Aalto University, Espoo, Finland
- Department of Computer Science, University of Manchester, Manchester, UK
| |
Collapse
|
2
|
Li Y, Ma Y, Wang K, Zhang M, Wang Y, Liu X, Hao M, Yin X, Liang M, Zhang H, Wang X, Chen X, Zhang Y, Duan W, Kang L, Qiao B, Wang J, Jin L. Using Composite Phenotypes to Reveal Hidden Physiological Heterogeneity in High-Altitude Acclimatization in a Chinese Han Longitudinal Cohort. PHENOMICS (CHAM, SWITZERLAND) 2021; 1:3-14. [PMID: 36939745 PMCID: PMC9584130 DOI: 10.1007/s43657-020-00005-8] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/18/2020] [Revised: 10/16/2020] [Accepted: 10/26/2020] [Indexed: 11/30/2022]
Abstract
Altitude acclimatization is a human physiological process of adjusting to the decreased oxygen availability. Since several physiological processes are involved and their correlations are complicated, the analyses of single traits are insufficient in revealing the complex mechanism of high-altitude acclimatization. In this study, we examined these physiological responses as the composite phenotypes that are represented by a linear combination of physiological traits. We developed a strategy that combines both spectral clustering and partial least squares path modeling (PLSPM) to define composite phenotypes based on a cohort study of 883 Chinese Han males. In addition, we captured 14 composite phenotypes from 28 physiological traits of high-altitude acclimatization. Using these composite phenotypes, we applied k-means clustering to reveal hidden population physiological heterogeneity in high-altitude acclimatization. Furthermore, we employed multivariate linear regression to systematically model (Models 1 and 2) oxygen saturation (SpO2) changes in high-altitude acclimatization and evaluated model fitness performance. Composite phenotypes based on Model 2 fit better than single trait-based Model 1 in all measurement indices. This new strategy of using composite phenotypes may be potentially employed as a general strategy for complex traits research such as genetic loci discovery and analyses of phenomics.
Collapse
Affiliation(s)
- Yi Li
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
- Institute for Six-Sector Economy, Fudan University, Shanghai, 200433 China
| | - Yanyun Ma
- Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200438 China
- Institute for Six-Sector Economy, Fudan University, Shanghai, 200433 China
| | - Kun Wang
- Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200438 China
| | - Menghan Zhang
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
| | - Yi Wang
- Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200438 China
| | - Xiaoyu Liu
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
| | - Meng Hao
- Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200438 China
| | - Xianhong Yin
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
| | - Meng Liang
- Ministry of Education Key Laboratory of Contemporary Anthropology, Department of Anthropology and Human Genetics, School of Life Sciences, Fudan University, Shanghai, 200438 China
| | - Hui Zhang
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
| | - Xiaofeng Wang
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
| | - Xingdong Chen
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
- Fudan-Taizhou Institute of Health Sciences, Taizhou, 225300 China
| | - Yao Zhang
- Key Laboratory of High Altitude Environment and Genes Related To Diseases of Tibet Autonomous Region, School of Medicine, Xizang Minzu University, Xianyang, 712082 China
| | - Wenyuan Duan
- Institute of Cardiovascular Disease, Shandong Provincial Western Hospital, Jinan, Shandong 250022 China
| | - Longli Kang
- Key Laboratory of High Altitude Environment and Genes Related To Diseases of Tibet Autonomous Region, School of Medicine, Xizang Minzu University, Xianyang, 712082 China
| | - Bin Qiao
- Institute of Cardiovascular Disease, Shandong Provincial Western Hospital, Jinan, Shandong 250022 China
| | - Jiucun Wang
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
- Institute for Six-Sector Economy, Fudan University, Shanghai, 200433 China
- Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058), Chinese Academy of Medical Sciences, Beijing, 100730 China
| | - Li Jin
- State Key Laboratory of Genetic Engineering, Collaborative Innovation Center for Genetics and Development, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai, 200438 China
- Institute for Six-Sector Economy, Fudan University, Shanghai, 200433 China
- Research Unit of Dissecting the Population Genetics and Developing New Technologies for Treatment and Prevention of Skin Phenotypes and Dermatological Diseases (2019RU058), Chinese Academy of Medical Sciences, Beijing, 100730 China
| |
Collapse
|
3
|
Assessing genetic and environmental influences on epicardial and abdominal adipose tissue quantities: a classical twin study. Int J Obes (Lond) 2017; 42:163-168. [PMID: 28852208 DOI: 10.1038/ijo.2017.212] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/03/2017] [Revised: 06/30/2017] [Accepted: 08/16/2017] [Indexed: 12/19/2022]
Abstract
BACKGROUND/OBJECTIVES Various adipose tissue compartments play an important role in the development of cardiometabolic diseases. The quantity of different fat compartments is influenced by genetic and environmental factors. The aim of our study was to evaluate the magnitude of genetic and environmental effects on epicardial, subcutaneous and visceral adipose tissue (EAT, SAT and VAT) quantities in a cohort of adult twin pairs. SUBJECTS/METHODS In this cross-sectional study we investigated adult twins (57 monozygotic (MZ) and 33 dizygotic (DZ) same-gender twin pairs; 180 twin subjects). We measured EAT volume using electrocardiogram-gated native computed tomography (CT) scan of the heart, and abdominal SAT and VAT areas were quantified between the third and fourth lumbar vertebra on native CT images. We calculated genetic and environmental impact on the size of various adipose tissue compartments by analyzing co-twin correlations in MZ and DZ pairs separately, and furthermore by using genetic structural equation models. RESULTS In co-twin analysis, MZ twins had stronger correlations than DZ twins for EAT (rMZ=0.81, rDZ=0.32), similar to SAT and VAT quantities (rMZ=0.80, rDZ=0.68 and rMZ=0.79, rDZ=0.48, respectively). In multi-trait model fitting analysis, the overall contribution of genetic factors to EAT, SAT and VAT volumes were 80%, 78% and 70%, whereas environmental factors were 20%, 22% and 30%, respectively. Common pathway model analyses indicated that none of the EAT, SAT and VAT phenotypes was independent of the other two. CONCLUSIONS Genetic factors have substantial influence, while environmental factors have only a modest impact on EAT volume, abdominal SAT and VAT quantities. There is a considerable amount of common genetic background influencing the quantities of all three adipose tissue compartments.
Collapse
|
4
|
Gervasini G, Gamero-Villarroel C. Discussing the putative role of obesity-associated genes in the etiopathogenesis of eating disorders. Pharmacogenomics 2015; 16:1287-1305. [DOI: 10.2217/pgs.15.77] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/26/2022] Open
Abstract
In addition to the identification of mutations clearly related to Mendelian forms of obesity; genome-wide association studies and follow-up studies have in the last years pinpointed several loci associated with BMI. These genetic alterations are located in or near genes expressed in the hypothalamus that are involved in the regulation of eating behavior. Accordingly, it seems plausible that these SNPs, or others located in related genes, could also help develop aberrant conduct patterns that favor the establishment of eating disorders should other susceptibility factors or personality dimensions be present. However, and somewhat surprisingly, with few exceptions such as BDNF, the great majority of the genes governing these pathways remain untested in patients with anorexia nervosa, bulimia nervosa or binge-eating disorder. In the present work, we review the few existing studies, but also indications and biological concepts that point to these genes in the CNS as good candidates for association studies with eating disorder patients.
Collapse
Affiliation(s)
- Guillermo Gervasini
- Department of Medical & Surgical Therapeutics, Division of Pharmacology, Medical School, University of Extremadura, Av. Elvas s/n, E-06005, Badajoz, Spain
| | - Carmen Gamero-Villarroel
- Department of Medical & Surgical Therapeutics, Division of Pharmacology, Medical School, University of Extremadura, Av. Elvas s/n, E-06005, Badajoz, Spain
| |
Collapse
|
5
|
A gene-based information gain method for detecting gene-gene interactions in case-control studies. Eur J Hum Genet 2015; 23:1566-72. [PMID: 25758991 DOI: 10.1038/ejhg.2015.16] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2014] [Revised: 11/30/2014] [Accepted: 01/14/2015] [Indexed: 12/31/2022] Open
Abstract
Currently, most methods for detecting gene-gene interactions (GGIs) in genome-wide association studies are divided into SNP-based methods and gene-based methods. Generally, the gene-based methods can be more powerful than SNP-based methods. Some gene-based entropy methods can only capture the linear relationship between genes. We therefore proposed a nonparametric gene-based information gain method (GBIGM) that can capture both linear relationship and nonlinear correlation between genes. Through simulation with different odds ratio, sample size and prevalence rate, GBIGM was shown to be valid and more powerful than classic KCCU method and SNP-based entropy method. In the analysis of data from 17 genes on rheumatoid arthritis, GBIGM was more effective than the other two methods as it obtains fewer significant results, which was important for biological verification. Therefore, GBIGM is a suitable and powerful tool for detecting GGIs in case-control studies.
Collapse
|