scholarly journals Improving Neural Networks for Genotype-Phenotype Prediction Using Published Summary Statistics

2021 ◽  
Author(s):  
Tianyu Cui ◽  
Khaoula El Mekkaoui ◽  
Aki S Havulinna ◽  
Pekka Marttinen ◽  
Samuel Kaski
Keyword(s):  
Neural Networks ◽  
Linear Regression ◽  
Association Studies ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Phenotype Prediction ◽  
Individual Level ◽  
Main Effect

Phenotype prediction is a necessity in numerous applications in genetics. However, when the size of the individual-level data of the cohort of interest is small, statistical learning algorithms, from linear regression to neural networks, usually fail due to insufficient data. Fortunately, summary statistics from genome-wide association studies (GWAS) on other large cohorts are often publicly available. In this work, we propose a new regularization method, namely, main effect prior (MEP), for making use of GWAS summary statistics from external datasets. The main effect prior is generally applicable for machine learning algorithms, such as neural networks and linear regression. With simulation and real-world experiments, we show empirically that MEP improves the prediction performance on both homogeneous and heterogeneous datasets. Moreover, deep neural networks with MEP outperform standard baselines even when the training set is small.

scholarly journals Multiple similarly effective solutions exist for biomedical feature selection and classification problems

2017 ◽  
Vol 7 (1) ◽  
Author(s):  
Jiamei Liu ◽  
Cheng Xu ◽  
Weifeng Yang ◽  
Yayun Shu ◽  
Weiwei Zheng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Association Studies ◽  
Binary Classification ◽  
Learning Algorithms ◽  
Optimal Solution ◽  
Machine Learning Algorithms ◽  
Disease Classification ◽  
Genome Wide Association Studies ◽  
Classification Problems

Abstract Binary classification is a widely employed problem to facilitate the decisions on various biomedical big data questions, such as clinical drug trials between treated participants and controls, and genome-wide association studies (GWASs) between participants with or without a phenotype. A machine learning model is trained for this purpose by optimizing the power of discriminating samples from two groups. However, most of the classification algorithms tend to generate one locally optimal solution according to the input dataset and the mathematical presumptions of the dataset. Here we demonstrated from the aspects of both disease classification and feature selection that multiple different solutions may have similar classification performances. So the existing machine learning algorithms may have ignored a horde of fishes by catching only a good one. Since most of the existing machine learning algorithms generate a solution by optimizing a mathematical goal, it may be essential for understanding the biological mechanisms for the investigated classification question, by considering both the generated solution and the ignored ones.

scholarly journals Estimating Heritability and Genetic Correlation in Case Control Studies Directly and with Summary Statistics

2018 ◽  
Author(s):  
Omer Weissbrod ◽  
Jonathan Flint ◽  
Saharon Rosset
Keyword(s):  
Genetic Correlation ◽  
Association Studies ◽  
Genetic Correlations ◽  
Large Data ◽  
Case Control ◽  
Data Sets ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Case Control Studies ◽  
Individual Level

AbstractMethods that estimate heritability and genetic correlations from genome-wide association studies have proven to be powerful tools for investigating the genetic architecture of common diseases and exposing unexpected relationships between disorders. Many relevant studies employ a case-control design, yet most methods are primarily geared towards analyzing quantitative traits. Here we investigate the validity of three common methods for estimating genetic heritability and genetic correlation. We find that the Phenotype-Correlation-Genotype-Correlation (PCGC) approach is the only method that can estimate both quantities accurately in the presence of important non-genetic risk factors, such as age and sex. We extend PCGC to work with summary statistics that take the case-control sampling into account, and demonstrate that our new method, PCGC-s, accurately estimates both heritability and genetic correlations and can be applied to large data sets without requiring individual-level genotypic or phenotypic information. Finally, we use PCGC-S to estimate the genetic correlation between schizophrenia and bipolar disorder, and demonstrate that previous estimates are biased due to incorrect handling of sex as a strong risk factor. PCGC-s is available at https://github.com/omerwe/PCGCs.

scholarly journals CoMM-S4: A Collaborative Mixed Model Using Summary-Level eQTL and GWAS Datasets in Transcriptome-Wide Association Studies

2021 ◽  
Vol 12 ◽  
Author(s):  
Yi Yang ◽  
Kar-Fu Yeung ◽  
Jin Liu
Keyword(s):  
Likelihood Ratio ◽  
Genetic Variants ◽  
Association Studies ◽  
Ratio Test ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Expression Trait ◽  
Individual Level ◽  
Trait Association ◽  
Eqtl Data

Motivation: Genome-wide association studies (GWAS) have achieved remarkable success in identifying SNP-trait associations in the last decade. However, it is challenging to identify the mechanisms that connect the genetic variants with complex traits as the majority of GWAS associations are in non-coding regions. Methods that integrate genomic and transcriptomic data allow us to investigate how genetic variants may affect a trait through their effect on gene expression. These include CoMM and CoMM-S2, likelihood-ratio-based methods that integrate GWAS and eQTL studies to assess expression-trait association. However, their reliance on individual-level eQTL data render them inapplicable when only summary-level eQTL results, such as those from large-scale eQTL analyses, are available.Result: We develop an efficient probabilistic model, CoMM-S4, to explore the expression-trait association using summary-level eQTL and GWAS datasets. Compared with CoMM-S2, which uses individual-level eQTL data, CoMM-S4 requires only summary-level eQTL data. To test expression-trait association, an efficient variational Bayesian EM algorithm and a likelihood ratio test were constructed. We applied CoMM-S4 to both simulated and real data. The simulation results demonstrate that CoMM-S4 can perform as well as CoMM-S2 and S-PrediXcan, and analyses using GWAS summary statistics from Biobank Japan and eQTL summary statistics from eQTLGen and GTEx suggest novel susceptibility loci for cardiovascular diseases and osteoporosis.Availability and implementation: The developed R package is available at https://github.com/gordonliu810822/CoMM.

scholarly journals Improved polygenic prediction by Bayesian multiple regression on summary statistics

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Luke R. Lloyd-Jones ◽  
Jian Zeng ◽  
Julia Sidorenko ◽  
Loïc Yengo ◽  
Gerhard Moser ◽  
...  
Keyword(s):  
Multiple Regression ◽  
Association Studies ◽  
Meta Analysis ◽  
Multiple Regression Model ◽  
Data Sets ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Individual Level ◽  
Level Data ◽  
The Uk

Abstract Accurate prediction of an individual’s phenotype from their DNA sequence is one of the great promises of genomics and precision medicine. We extend a powerful individual-level data Bayesian multiple regression model (BayesR) to one that utilises summary statistics from genome-wide association studies (GWAS), SBayesR. In simulation and cross-validation using 12 real traits and 1.1 million variants on 350,000 individuals from the UK Biobank, SBayesR improves prediction accuracy relative to commonly used state-of-the-art summary statistics methods at a fraction of the computational resources. Furthermore, using summary statistics for variants from the largest GWAS meta-analysis (n ≈ 700, 000) on height and BMI, we show that on average across traits and two independent data sets that SBayesR improves prediction R2 by 5.2% relative to LDpred and by 26.5% relative to clumping and p value thresholding.

scholarly journals Estimating genetic nurture with summary statistics of multigenerational genome-wide association studies

2021 ◽  
Vol 118 (25) ◽  
pp. e2023184118
Author(s):  
Yuchang Wu ◽  
Xiaoyuan Zhong ◽  
Yunong Lin ◽  
Zijie Zhao ◽  
Jiawen Chen ◽  
...  
Keyword(s):  
Complex Traits ◽  
Association Studies ◽  
Genetic Correlations ◽  
Genetic Effects ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Phenotypic Data ◽  
Individual Level ◽  
Indirect Genetic Effects ◽  
Genome Wide

Marginal effect estimates in genome-wide association studies (GWAS) are mixtures of direct and indirect genetic effects. Existing methods to dissect these effects require family-based, individual-level genetic, and phenotypic data with large samples, which is difficult to obtain in practice. Here, we propose a statistical framework to estimate direct and indirect genetic effects using summary statistics from GWAS conducted on own and offspring phenotypes. Applied to birth weight, our method showed nearly identical results with those obtained using individual-level data. We also decomposed direct and indirect genetic effects of educational attainment (EA), which showed distinct patterns of genetic correlations with 45 complex traits. The known genetic correlations between EA and higher height, lower body mass index, less-active smoking behavior, and better health outcomes were mostly explained by the indirect genetic component of EA. In contrast, the consistently identified genetic correlation of autism spectrum disorder (ASD) with higher EA resides in the direct genetic component. A polygenic transmission disequilibrium test showed a significant overtransmission of the direct component of EA from healthy parents to ASD probands. Taken together, we demonstrate that traditional GWAS approaches, in conjunction with offspring phenotypic data collection in existing cohorts, could greatly benefit studies on genetic nurture and shed important light on the interpretation of genetic associations for human complex traits.

scholarly journals metaCCA: Summary statistics-based multivariate meta-analysis of genome-wide association studies using canonical correlation analysis

2015 ◽  
Author(s):  
Anna Cichonska ◽  
Juho Rousu ◽  
Pekka Marttinen ◽  
Antti J Kangas ◽  
Pasi Soininen ◽  
...  
Keyword(s):  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Statistical Power ◽  
Association Studies ◽  
Meta Analysis ◽  
Original Data ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Individual Level

A dominant approach to genetic association studies is to perform univariate tests between genotype-phenotype pairs. However, analysing related traits together increases statistical power, and certain complex associations become detectable only when several variants are tested jointly. Currently, modest sample sizes of individual cohorts and restricted availability of individual-level genotype-phenotype data across the cohorts limit conducting multivariate tests. We introduce metaCCA, a computational framework for summary statistics-based analysis of a single or multiple studies that allows multivariate representation of both genotype and phenotype. It extends the statistical technique of canonical correlation analysis to the setting where original individual-level records are not available, and employs a covariance shrinkage algorithm to achieve robustness. Multivariate meta-analysis of two Finnish studies of nuclear magnetic resonance metabolomics by metaCCA, using standard univariate output from the program SNPTEST, shows an excellent agreement with the pooled individual-level analysis of original data. Motivated by strong multivariate signals in the lipid genes tested, we envision that multivariate association testing using metaCCA has a great potential to provide novel insights from already published summary statistics from high-throughput phenotyping technologies.

scholarly journals Bayesian large-scale multiple regression with summary statistics from genome-wide association studies

2016 ◽  
Author(s):  
Xiang Zhu ◽  
Matthew Stephens
Keyword(s):  
Multiple Regression ◽  
Large Scale ◽  
Association Studies ◽  
Genome Wide Association ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Individual Level ◽  
Genome Wide ◽  
Level Data ◽  
Wide Range

Bayesian methods for large-scale multiple regression provide attractive approaches to the analysis of genome-wide association studies (GWAS). For example, they can estimate heritability of complex traits, allowing for both polygenic and sparse models; and by incorporating external genomic data into the priors they can increase power and yield new biological insights. However, these methods require access to individual genotypes and phenotypes, which are often not easily available. Here we provide a framework for performing these analyses without individual-level data. Specifically, we introduce a “Regression with Summary Statistics” (RSS) likelihood, which relates the multiple regression coefficients to univariate regression results that are often easily available. The RSS likelihood requires estimates of correlations among covariates (SNPs), which also can be obtained from public databases. We perform Bayesian multiple regression analysis by combining the RSS likelihood with previously-proposed prior distributions, sampling posteriors by Markov chain Monte Carlo. In a wide range of simulations RSS performs similarly to analyses using the individual data, both for estimating heritability and detecting associations. We apply RSS to a GWAS of human height that contains 253,288 individuals typed at 1.06 million SNPs, for which analyses of individual-level data are practically impossible. Estimates of heritability (52%) are consistent with, but more precise, than previous results using subsets of these data. We also identify many previously-unreported loci that show evidence for association with height in our analyses. Software is available at https://github.com/stephenslab/rss.

scholarly journals Powerful tests for multi-marker association analysis using ensemble learning

2014 ◽  
Author(s):  
Badri Padhukasahasram ◽  
Chandan K Reddy ◽  
L. Keoki Williams
Keyword(s):  
Machine Learning ◽  
Ensemble Learning ◽  
Association Analysis ◽  
Association Studies ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Genome Wide Association Studies ◽  
Major Drawback ◽  
Association Tests ◽  
Single Marker

Multi-marker approaches are currently gaining a lot of interest in genome wide association studies and can enhance power to detect new associations under certain conditions. Gene- and pathway-based association tests are increasingly being viewed as useful complements to the more widely used single marker association analysis which have successfully uncovered numerous disease variants. A major drawback of single-marker based methods is that they do not consider pairwise and higher-order interactions between genetic variants. Here, we describe novel tests for multi-marker association analyses that are based on phenotype predictions obtained from machine learning algorithms. Instead of utilizing only a linear or logistic regression model, we propose the use of ensembles of diverse machine learning algorithms for constructing such association tests. As the true mathematical relationship between a phenotype and any group of genetic and clinical variables is unknown in advance and may be complex, such a strategy gives us a general and flexible framework to approximate this relationship across different sets of SNPs. We show how phenotype prediction obtained from ensemble learning algorithms can be used for constructing tests for the joint association of multiple variants. We first apply our method to simulated datasets to demonstrate its power and correctness. Then, we apply our method to previously studied asthma-related genes in two independent asthma cohorts to conduct association tests.

scholarly journals Estimating genetic nurture with summary statistics of multi-generational genome-wide association studies

2020 ◽  
Author(s):  
Yuchang Wu ◽  
Xiaoyuan Zhong ◽  
Yunong Lin ◽  
Zijie Zhao ◽  
Jiawen Chen ◽  
...  
Keyword(s):  
Complex Traits ◽  
Association Studies ◽  
Genetic Correlations ◽  
Genetic Effects ◽  
Genome Wide Association Studies ◽  
Summary Statistics ◽  
Phenotypic Data ◽  
Individual Level ◽  
Indirect Genetic Effects ◽  
Genome Wide

AbstractMarginal effect estimates in genome-wide association studies (GWAS) are mixtures of direct and indirect genetic effects. Existing methods to dissect these effects require family-based, individual-level genetic and phenotypic data with large samples, which is difficult to obtain in practice. Here, we propose a novel statistical framework to estimate direct and indirect genetic effects using summary statistics from GWAS conducted on own and offspring phenotypes. Applied to birth weight, our method showed nearly identical results with those obtained using individual-level data. We also decomposed direct and indirect genetic effects of educational attainment (EA), which showed distinct patterns of genetic correlations with 45 complex traits. The known genetic correlations between EA and higher height, lower BMI, less active smoking behavior, and better health outcomes were mostly explained by the indirect genetic component of EA. In contrast, the consistently identified genetic correlation of autism spectrum disorder (ASD) with higher EA resides in the direct genetic component. Polygenic transmission disequilibrium test showed a significant over-transmission of the direct component of EA from healthy parents to ASD probands. Taken together, we demonstrate that traditional GWAS approaches, in conjunction with offspring phenotypic data collection in existing cohorts, could greatly benefit studies on genetic nurture and shed important light on the interpretation of genetic associations for human complex traits.

Sign in / Sign up

Export Citation Format

Share Document