基于病例对照母子对数据的遗传关联分析中的经验贝叶斯方法

An empirical Bayes method for genetic association analysis using case-control mother-child pair data

病例对照母子对数据常用于研究母亲和子代的遗传效应以及环境风险因子对产科和早期生命表型的影响。回溯似然方法可以充分利用已有的信息,如孟德尔遗传、母亲环境因子(协变量)在给定母亲基因型下与子代基因型的条件独立性,从而有效地提高统计推断。如对母亲基因型和环境变量之间不作任何关系假设,则相应估计量比较稳健。而假设母亲基因型和环境变量独立下的估计量可以显著提高统计推断效率,但是当独立性假设不成立时会有系统偏差。本文通过对上述基于回溯似然的两个估计量进行适当的加权,得到了两个经验贝叶斯(empirical Bayes,EB)估计量,这两个EB估计量可以直观地平衡统计效率和稳健性。我们对两个EB估计量建立渐近正态性,并利用该渐近正态性构建遗传效应和基因-环境交互效应的置信区间和显著性检验。模拟和实际数据分析说明了我们新方法的表现。

Case-control mother-child pair data are often used to investigate the effects of maternal and child genetic variants and environmental risk factors on obstetric and early life phenotypes.Retrospective likelihood can fully utilize available information such as Mendelian inheritance and conditional independence between maternal environmental risk factors(covariates) and children’ s genotype given maternal genotype,thus effectively improving statistical inference.Such a method is robust to some extent if no relationship assumption is imposed between the maternal genotype and covariates.Statistical efficiency can be considerably improved by assuming independence between maternal genotype and covariates,but false-positive findings would be inflated if the independence assumption was violated.In this study,two empirical Bayes(EB) estimators are derived by appropriately weighting the above retrospective-likelihood-based estimators,which intuitively balance the statistical efficiency and robustness.The asymptotic normality of the two EB estimators is established,which can be used to construct confidence intervals and association tests of genetic effects and gene-environment interactions.Simulations and real-data analyses are conducted to demonstrate the performance of our new method.