Two-Sample Instrumental Variable Analyses Using Heterogeneous Samples

Zhao, Qingyuan; Wang, Jingshu; Spiller, Wes; Bowden, Jack; Small, Dylan S.

doi:10.1214/18-sts692

Cited by 48 publications

(52 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be violated in practice 7 . Recently, large population-based biobanks have made available individual-level genome-wide data and data on a variety of exposures and outcomes, thus allowing well-powered one-sample MR studies.…”

Section: Introductionmentioning

confidence: 99%

The use of two-sample methods for Mendelian randomization analyses on single large datasets

Minelli

Greco

Plaat

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Tel: +44 (0) 207 5947758 2 Key Messages • Current availability of phenotypic and genetic data from large biobanks, such as UK Biobank, has led to increasing use of one-sample Mendelian randomization (MR) to investigate causal relationships in epidemiological research • Robust MR methods have been developed to address pleiotropy, but they assume independence between the gene-exposure and gene-outcome association estimates; this holds in two-sample MR but not in one-sample MR • We illustrate the practical implications, in terms of bias and precision of the MR causal effect estimate, of using robust two-sample methods in one-sample MR studies performed within large biobanks • Two-sample MR methods can be safely used for one-sample MR performed within large biobanks, expect for MR-Egger regression • MR-Egger is not recommended for one-sample MR unless the correlation between the gene-exposure and gene-outcome estimates due to confounding can be kept low, or the variability in instrumental strength is very high Abstract Background: With genome-wide association data for many exposures and outcomes now available from large biobanks, one-sample Mendelian randomization (MR) is increasingly used to investigate causal relationships. Many robust MR methods are available to address pleiotropy, but these assume independence between the gene-exposure and geneoutcome association estimates. Unlike in two-sample MR, in one-sample MR the two estimates are obtained from the same individuals, and the assumption of independence does not hold in the presence of confounding. Methods: With simulations mimicking a typical study in UK Biobank we assessed the performance, in terms of bias and precision of the MR estimate, of the fixed-effect and (multiplicative) random-effects meta-analysis method, weighted median estimator, weighted mode estimator and MR-Egger regression, used in both one-sample and two-sample data.We considered scenarios differing for: presence/absence of a true causal effect; amount of confounding; presence and type of pleiotropy (none, balanced or directional). Results:Even in the presence of substantial correlation due to confounding, all methods performed well when used in one-sample MR except for MR-Egger, which resulted in bias reflecting direction and magnitude of the confounding. Such bias was much reduced in the presence of very high variability in instrumental strength across variants (I 2 GX of 97%). Conclusions:Two-sample MR methods can be safely used for one-sample MR performed within large biobanks, expect for MR-Egger. MR-Egger is not recommended for one-sample MR unless the correlation between the gene-exposure and gene-outcome estimates due to confounding can be kept low, or the variability in instrumental strength is very high.

show abstract

Section: Introductionmentioning

confidence: 99%

The use of two-sample methods for Mendelian randomization analyses on single large datasets

Minelli

Greco

Plaat

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…iFunMed focuses on scenarios where GWAS and eQTL summary statistics are available from the same set of study subjects and treats multiple genetic variants as instrumental variables, akin to practice in Mendelian randomization (Davey Smith & Ebrahim, ). Generalizations of instrumental variable analysis that combine instrumental measurements, exposure and outcome/phenotype effects of which are measured on different study populations, have been recently addressed by Zhao, Wang, Bowden, and Small (). Although Mendelian randomization techniques employ the strong assumption that all the genetic effects on the phenotype are being mediated by the exposure variable—an assumption that can certainly be violated in our framework when other cellular/genomic events beyond gene expression is considered, it is still worth noting the important discussion of Zhao et al () with regard to the use of heterogeneous samples: They can lead to biased estimators and are less robust to model misspecifications.…”

Section: Discussionmentioning

confidence: 99%

iFunMed: Integrative functional mediation analysis of GWAS and eQTL studies

Rojo

Zhang

Keleş

2019

Genetic Epidemiology

View full text Add to dashboard Cite

Genome‐wide association studies (GWAS) have successfully identified thousands of genetic variants contributing to disease and other phenotypes. However, significant obstacles hamper our ability to elucidate causal variants, identify genes affected by causal variants, and characterize the mechanisms by which genotypes influence phenotypes. The increasing availability of genome‐wide functional annotation data is providing unique opportunities to incorporate prior information into the analysis of GWAS to better understand the impact of variants on disease etiology. Although there have been many advances in incorporating prior information into prioritization of trait‐associated variants in GWAS, functional annotation data have played a secondary role in the joint analysis of GWAS and molecular (i.e., expression) quantitative trait loci (eQTL) data in assessing evidence for association. To address this, we develop a novel mediation framework, iFunMed, to integrate GWAS and eQTL data with the utilization of publicly available functional annotation data. iFunMed extends the scope of standard mediation analysis by incorporating information from multiple genetic variants at a time and leveraging variant‐level summary statistics. Data‐driven computational experiments convey how informative annotations improve single‐nucleotide polymorphism (SNP) selection performance while emphasizing robustness of iFunMed to noninformative annotations. Application to Framingham Heart Study data indicates that iFunMed is able to boost detection of SNPs with mediation effects that can be attributed to regulatory mechanisms.

show abstract

“…That is, our estimate

. This requires cohort 2 to be large and also homogenous with respect to cohort 1 ( 16 , 17 ). Further assume that our estimate for the

SNP-outcome association has variance

.…”

Section: Cochran’s Q Statisticmentioning

confidence: 99%

Invited Commentary: Detecting Individual and Global Horizontal Pleiotropy in Mendelian Randomization—A Job for the Humble Heterogeneity Statistic?

Bowden

Hemani

Smith

2018

American Journal of Epidemiology

Self Cite

171

157

View full text Add to dashboard Cite

Mendelian randomization (MR) is gaining in recognition and popularity as a method for strengthening causal inference in epidemiology by utilizing genetic variants as instrumental variables. Concurrently with the explosion in empirical MR studies, there has been the steady production of new approaches for MR analysis. The recently proposed “global and individual tests for direct effects” (GLIDE) approach fits into a family of methods that aim to detect horizontal pleiotropy—at the individual single nucleotide polymorphism level and at the global level—and to adjust the analysis by removing outlying single nucleotide polymorphisms. In this commentary, we explain how existing methods can (and indeed are) being used to detect pleiotropy at the individual and global levels, although not explicitly using this terminology. By doing so, we show that the true comparator for GLIDE is not MR-Egger regression (as Dai et al., the authors of the accompanying article (Am J Epidemiol. 2018;187(12):2672–2680), claim) but rather the humble heterogeneity statistic.

show abstract

Two-Sample Instrumental Variable Analyses Using Heterogeneous Samples

Cited by 48 publications

References 62 publications

The use of two-sample methods for Mendelian randomization analyses on single large datasets

The use of two-sample methods for Mendelian randomization analyses on single large datasets

iFunMed: Integrative functional mediation analysis of GWAS and eQTL studies

Invited Commentary: Detecting Individual and Global Horizontal Pleiotropy in Mendelian Randomization—A Job for the Humble Heterogeneity Statistic?

Contact Info

Product

Resources

About