Effect of selection bias on two sample summary data based Mendelian randomization.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang K
PROVIDER: S-EPMC8027662 | biostudies-literature | 2021 Apr
REPOSITORIES: biostudies-literature
Publications
Effect of selection bias on two sample summary data based Mendelian randomization.
Scientific reports 20210407 1
Mendelian randomization (MR) is becoming more and more popular for inferring causal relationship between an exposure and a trait. Typically, instrument SNPs are selected from an exposure GWAS based on their summary statistics and the same summary statistics on the selected SNPs are used for subsequent analyses. However, this practice suffers from selection bias and can invalidate MR methods, as showcased via two popular methods: the summary data-based MR (SMR) method and the two-sample MR Steige ...[more]
Similar Datasets
Project description:The summary-data-based Mendelian randomization (SMR) method is gaining popularity in estimating the causal effect of an exposure on an outcome. In practice, the instrument SNP is often selected from the genome-wide association study (GWAS) on the exposure but no correction is made for such selection in downstream analysis, leading to a biased estimate of the effect size and invalid inference. We address this issue by using the likelihood derived from the sampling distribution of the estimated SNP effects in the exposure GWAS and the outcome GWAS. This likelihood takes into account how the instrument SNPs are selected. Since the effective sample size is 1, the asymptotic theory does not apply. We use a support for a profile likelihood as an interval estimate of the causal effect. Simulation studies indicate that this support has robust coverage while the confidence interval implied by the SMR method has lower-than-nominal coverage. Furthermore, the variance of the two-stage least squares estimate of the causal effect is shown to be the same as the variance used for SMR for one-sample data when there is no selection.
| S-EPMC9859138 | biostudies-literature
Project description:Over the last decade the availability of SNP-trait associations from genome-wide association studies has led to an array of methods for performing Mendelian randomization studies using only summary statistics. A common feature of these methods, besides their intuitive simplicity, is the ability to combine data from several sources, incorporate multiple variants and account for biases due to weak instruments and pleiotropy. With the advent of large and accessible fully-genotyped cohorts such as UK Biobank, there is now increasing interest in understanding how best to apply these well developed summary data methods to individual level data, and to explore the use of more sophisticated causal methods allowing for non-linearity and effect modification. In this paper we describe a general procedure for optimally applying any two sample summary data method using one sample data. Our procedure first performs a meta-analysis of summary data estimates that are intentionally contaminated by collider bias between the genetic instruments and unmeasured confounders, due to conditioning on the observed exposure. These estimates are then used to correct the standard observational association between an exposure and outcome. Simulations are conducted to demonstrate the method's performance against naive applications of two sample summary data MR. We apply the approach to the UK Biobank cohort to investigate the causal role of sleep disturbance on HbA1c levels, an important determinant of diabetes. Our approach can be viewed as a generalization of Dudbridge et al. (Nat. Comm. 10: 1561), who developed a technique to adjust for index event bias when uncovering genetic predictors of disease progression based on case-only data. Our work serves to clarify that in any one sample MR analysis, it can be advantageous to estimate causal relationships by artificially inducing and then correcting for collider bias.
| S-EPMC8376220 | biostudies-literature
Project description:BackgroundTwo-sample Mendelian randomization (MR) allows the use of freely accessible summary association results from genome-wide association studies (GWAS) to estimate causal effects of modifiable exposures on outcomes. Some GWAS adjust for heritable covariables in an attempt to estimate direct effects of genetic variants on the trait of interest. One, both or neither of the exposure GWAS and outcome GWAS may have been adjusted for covariables.MethodsWe performed a simulation study comprising different scenarios that could motivate covariable adjustment in a GWAS and analysed real data to assess the influence of using covariable-adjusted summary association results in two-sample MR.ResultsIn the absence of residual confounding between exposure and covariable, between exposure and outcome, and between covariable and outcome, using covariable-adjusted summary associations for two-sample MR eliminated bias due to horizontal pleiotropy. However, covariable adjustment led to bias in the presence of residual confounding (especially between the covariable and the outcome), even in the absence of horizontal pleiotropy (when the genetic variants would be valid instruments without covariable adjustment). In an analysis using real data from the Genetic Investigation of ANthropometric Traits (GIANT) consortium and UK Biobank, the causal effect estimate of waist circumference on blood pressure changed direction upon adjustment of waist circumference for body mass index.ConclusionsOur findings indicate that using covariable-adjusted summary associations in MR should generally be avoided. When that is not possible, careful consideration of the causal relationships underlying the data (including potentially unmeasured confounders) is required to direct sensitivity analyses and interpret results with appropriate caution.
| S-EPMC8580279 | biostudies-literature
Project description:Mendelian randomization (MR) is the use of genetic variants to assess the existence of a causal relationship between a risk factor and an outcome of interest. Here, we focus on two-sample summary-data MR analyses with many correlated variants from a single gene region, particularly on cis-MR studies which use protein expression as a risk factor. Such studies must rely on a small, curated set of variants from the studied region; using all variants in the region requires inverting an ill-conditioned genetic correlation matrix and results in numerically unstable causal effect estimates. We review methods for variable selection and estimation in cis-MR with summary-level data, ranging from stepwise pruning and conditional analysis to principal components analysis, factor analysis, and Bayesian variable selection. In a simulation study, we show that the various methods have comparable performance in analyses with large sample sizes and strong genetic instruments. However, when weak instrument bias is suspected, factor analysis and Bayesian variable selection produce more reliable inferences than simple pruning approaches, which are often used in practice. We conclude by examining two case studies, assessing the effects of low-density lipoprotein-cholesterol and serum testosterone on coronary heart disease risk using variants in the HMGCR and SHBG gene regions, respectively.
| S-EPMC7614127 | biostudies-literature
Project description:BackgroundMendelian randomization (MR) is a powerful tool in epidemiology that can be used to estimate the causal effect of an exposure on an outcome in the presence of unobserved confounding, by utilizing genetic variants that are instrumental variables (IVs) for the exposure. This has been extended to multivariable MR (MVMR) to estimate the effect of two or more exposures on an outcome.Methods and resultsWe use simulations and theory to clarify the interpretation of estimated effects in a MVMR analysis under a range of underlying scenarios, where a secondary exposure acts variously as a confounder, a mediator, a pleiotropic pathway and a collider. We then describe how instrument strength and validity can be assessed for an MVMR analysis in the single-sample setting, and develop tests to assess these assumptions in the popular two-sample summary data setting. We illustrate our methods using data from UK Biobank to estimate the effect of education and cognitive ability on body mass index.ConclusionMVMR analysis consistently estimates the direct causal effect of an exposure, or exposures, of interest and provides a powerful tool for determining causal effects in a wide range of scenarios with either individual- or summary-level data.
| S-EPMC6734942 | biostudies-literature
Project description:Recently, in genetic epidemiology, Mendelian randomization (MR) has become a popular approach to estimate causal exposure effects by using single nucleotide polymorphisms from genome-wide association studies (GWAS) as instruments. The most popular type of MR study, a two-sample summary-data MR study, relies on having summary statistics from two independent GWAS and using parametric methods for estimation. However, little is understood about using a nonparametric bound-based analysis, a popular approach in traditional instrumental variables frameworks, to study causal effects in two-sample MR. In this article, we explore using a nonparametric, bound-based analysis in two-sample MR studies, focusing primarily on implications for practice. We also propose a framework to assess how likely one can obtain more informative bounds if we used a different MR design, notably a one-sample MR design. We conclude by demonstrating our findings through two real data analyses concerning the causal effect of smoking on lung cancer and the causal effect of high cholesterol on heart attacks. Overall, our results suggest that while a bound-based analysis may be appealing due to its nonparametric nature, it is far more conservative in two-sample settings than in one-sample settings to get informative bounds on the causal exposure effect.
| S-EPMC9314714 | biostudies-literature
Project description:BackgroundTwo-sample summary-data Mendelian randomization (MR) incorporating multiple genetic variants within a meta-analysis framework is a popular technique for assessing causality in epidemiology. If all genetic variants satisfy the instrumental variable (IV) and necessary modelling assumptions, then their individual ratio estimates of causal effect should be homogeneous. Observed heterogeneity signals that one or more of these assumptions could have been violated.MethodsCausal estimation and heterogeneity assessment in MR require an approximation for the variance, or equivalently the inverse-variance weight, of each ratio estimate. We show that the most popular 'first-order' weights can lead to an inflation in the chances of detecting heterogeneity when in fact it is not present. Conversely, ostensibly more accurate 'second-order' weights can dramatically increase the chances of failing to detect heterogeneity when it is truly present. We derive modified weights to mitigate both of these adverse effects.ResultsUsing Monte Carlo simulations, we show that the modified weights outperform first- and second-order weights in terms of heterogeneity quantification. Modified weights are also shown to remove the phenomenon of regression dilution bias in MR estimates obtained from weak instruments, unlike those obtained using first- and second-order weights. However, with small numbers of weak instruments, this comes at the cost of a reduction in estimate precision and power to detect a causal effect compared with first-order weighting. Moreover, first-order weights always furnish unbiased estimates and preserve the type I error rate under the causal null. We illustrate the utility of the new method using data from a recent two-sample summary-data MR analysis to assess the causal role of systolic blood pressure on coronary heart disease risk.ConclusionsWe propose the use of modified weights within two-sample summary-data MR studies for accurately quantifying heterogeneity and detecting outliers in the presence of weak instruments. Modified weights also have an important role to play in terms of causal estimation (in tandem with first-order weights) but further research is required to understand their strengths and weaknesses in specific settings.
| S-EPMC6659376 | biostudies-literature
Project description:Mendelian randomization analyses are often performed using summarized data. The causal estimate from a one-sample analysis (in which data are taken from a single data source) with weak instrumental variables is biased in the direction of the observational association between the risk factor and outcome, whereas the estimate from a two-sample analysis (in which data on the risk factor and outcome are taken from non-overlapping datasets) is less biased and any bias is in the direction of the null. When using genetic consortia that have partially overlapping sets of participants, the direction and extent of bias are uncertain. In this paper, we perform simulation studies to investigate the magnitude of bias and Type 1 error rate inflation arising from sample overlap. We consider both a continuous outcome and a case-control setting with a binary outcome. For a continuous outcome, bias due to sample overlap is a linear function of the proportion of overlap between the samples. So, in the case of a null causal effect, if the relative bias of the one-sample instrumental variable estimate is 10% (corresponding to an F parameter of 10), then the relative bias with 50% sample overlap is 5%, and with 30% sample overlap is 3%. In a case-control setting, if risk factor measurements are only included for the control participants, unbiased estimates are obtained even in a one-sample setting. However, if risk factor data on both control and case participants are used, then bias is similar with a binary outcome as with a continuous outcome. Consortia releasing publicly available data on the associations of genetic variants with continuous risk factors should provide estimates that exclude case participants from case-control samples.
| S-EPMC5082560 | biostudies-literature
Project description: Not available
| S-EPMC9632630 | biostudies-literature
Project description:BackgroundTwo-sample Mendelian randomization (2SMR) is an increasingly popular epidemiological method that uses genetic variants as instruments for making causal inferences. Clear reporting of methods employed in such studies is important for evaluating their underlying quality. However, the quality of methodological reporting of 2SMR studies is currently unclear. We aimed to assess the reporting quality of studies that used MR-Base, one of the most popular platforms for implementing 2SMR analysis.MethodsWe created a bespoke reporting checklist to evaluate reporting quality of 2SMR studies. We then searched Web of Science Core Collection, PsycInfo, MEDLINE, EMBASE and Google Scholar citations of the MR-Base descriptor paper to identify published MR studies that used MR-Base for any component of the MR analysis. Study screening and data extraction were performed by at least two independent reviewers.ResultsIn the primary analysis, 87 studies were included. Reporting quality was generally poor across studies, with a mean of 53% (SD = 14%) of items reported in each study. Many items required for evaluating the validity of key assumptions made in MR were poorly reported: only 44% of studies provided sufficient details for assessing if the genetic variant associates with the exposure ('relevance' assumption), 31% for assessing if there are any variant-outcome confounders ('independence' assumption), 89% for the assessing if the variant causes the outcome independently of the exposure ('exclusion restriction' assumption) and 32% for assumptions of falsification tests. We did not find evidence of a change in reporting quality over time or a difference in reporting quality between studies that used MR-Base and a random sample of MR studies that did not use this platform.ConclusionsThe quality of reporting of two-sample Mendelian randomization studies in our sample was generally poor. Journals and researchers should consider using the STROBE-MR guidelines to improve reporting quality.
| S-EPMC9749715 | biostudies-literature