Improved polygenic prediction by Bayesian multiple regression on summary statistics

Lloyd‐Jones, Luke R.; Zeng, Jian; Sidorenko, Julia; Yengo, Loïc; Moser, G.; Kemper, Kathryn E.; Wang, Huanwei; Zheng, Zhili; Mägi, Reedik; Esko, Tõnu; Metspalu, Andres; Wray, Naomi R.; Goddard, Michael E.; Yang, Jian; Visscher, Peter M.

doi:10.1038/s41467-019-12653-0

Cited by 383 publications

(332 citation statements)

References 67 publications

Supporting

Mentioning

328

Contrasting

Order By: Relevance

“…Methods for polygenic risk prediction 6,21,[48][49][50] and fine mapping 7-9,25,27,28,51-53 rely on models for the effect-size distribution. Several of them rely on a point-normal model: LDpred 21 assumes this model for the purpose of polygenic prediction, and state-of-the-art fine mapping methods 9,51-53 assume similar models with additional constraints.…”

Section: Discussionmentioning

confidence: 99%

The distribution of common-variant effect sizes

O’Connor

2020

Preprint

View full text Add to dashboard Cite

The genetic effect-size distribution describes the number of variants that affect disease risk and the range of their effect sizes. Accurate estimates of this distribution would provide insights into genetic architecture and set sample-size targets for future genome-wide association studies. We developed Fourier Mixture Regression (FMR) to estimate common-variant effect-size distributions from GWAS summary statistics. We validated FMR in simulations and in analyses of UK Biobank data, using interim-release summary statistics (max N=145k) to predict the results of the full release (N=460k). Analyzing summary statistics for 10 diseases (avg Neff=169k) and 22 other traits, we estimated the sample size required for genome-wide significant SNPs to explain 50% of SNP-heritability. For most diseases the requisite number of cases is 100k-1M, an attainable number; ten times more would be required to explain 90% of heritability. In well-powered GWAS, genome-wide significance is a conservative threshold, and loci at less stringent thresholds have true positive rates that remain close to 1 if confounding is controlled. Analyzing the shape of the effect-size distribution, we estimate that heritability accumulates across many thousands of SNPs with a wide range of effect sizes: the largest effects (at the 90th percentile of heritability) are 100 times larger than the smallest (10th percentile), and while the midpoint of this range varies across traits, its size is similar. These results suggest attainable sample size targets for future GWAS, and they underscore the complexity of genetic architecture.

show abstract

Section: Discussionmentioning

confidence: 99%

The distribution of common-variant effect sizes

O’Connor

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, polygenic traits are generated by many mutations of small effect, while other phenotypes can be driven by just a few clusters of SNPs with effect sizes much larger in magnitude [19]. To this end, we place a normal mixture prior on the input layer weights (θ) to flexibly estimate a wide range of SNP-level effect size distributions [10,[43][44][45]. Similarly, we follow previous works and assume that enriched SNP-sets contain at least one SNP with a nonzero effect on the trait of interest [26].…”

Section: Banns Framework Overviewmentioning

confidence: 99%

“…For the weights on the input layer, our goal is to approximate a wide range of possible SNP-level effect size distributions underlying complex traits. To this end, we assume that SNP-level effects follow a K-mixture of normal distributions [10,[43][44][45]…”

Section: Biologically Annotated Neural Networkmentioning

confidence: 99%

Multi-scale Inference of Genetic Trait Architecture using Biologically Annotated Neural Networks

Demetçi

Cheng

Darnell

et al. 2020

Preprint

View full text Add to dashboard Cite

AbstractWith the emergence of large-scale genomic datasets, there is a unique opportunity to integrate machine learning approaches as standard tools within genome-wide association (GWA) studies. Unfortunately, while machine learning methods have been shown to account for nonlinear data structures and exhibit greater predictive power over classic linear models, these same algorithms have also become criticized as “black box” techniques. Here, we present biologically annotated neural networks (BANNs), a novel probabilistic framework that makes machine learning fully amenable for GWA applications. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. Part of our key innovation is to treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects are manifested at different genomic scales. The BANN software uses scalable variational inference to provide fully interpretable posterior summaries which allow researchers to simultaneously perform (i) fine-mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations and real GWA data applications, we show that our method improves upon state-of-the-art approaches in both settings across a wide range of genetic architectures.

show abstract

“…The proportion is specified by the user, and generally several values will be considered with the candidate chosen by cross-validation. A newer method, SBayesR, in the GCTB software package (Lloyd-Jones et al, 2019) expands the point-normal prior with a mixture of normal distributions, allowing for the specification of multiple proportions (adding up to 1). Both methods require specification of the chip heritability, which can be estimated from the data.…”

Section: Of 12mentioning

confidence: 99%

Genetic Risk Scores

2019

View full text Add to dashboard Cite

Genome‐wide variation data with millions of genetic markers have become commonplace. However, the potential for interpretation and application of these data for clinical assessment of outcomes of interest, and prediction of disease risk, is currently not fully realized. Many common complex diseases now have numerous, well‐established risk loci and likely harbor many genetic determinants with effects too small to be detected at genome‐wide levels of statistical significance. A simple and intuitive approach for converting genetic data to a predictive measure of disease susceptibility is to aggregate the effects of these loci into a single measure, the genetic risk score. Here, we describe some common methods and software packages for calculating genetic risk scores and polygenic risk scores, with focus on studies of common complex diseases. We review the basic information needed, as well as important considerations for constructing genetic risk scores, including specific requirements for phenotypic and genetic data, and limitations in their application. © 2019 by John Wiley & Sons, Inc.

show abstract

Improved polygenic prediction by Bayesian multiple regression on summary statistics

Cited by 383 publications

References 67 publications

The distribution of common-variant effect sizes

The distribution of common-variant effect sizes

Multi-scale Inference of Genetic Trait Architecture using Biologically Annotated Neural Networks

Genetic Risk Scores

Contact Info

Product

Resources

About