A GIBBS SAMPLING APPROACH TO LINKAGE ANALYSIS
A GIBBS SAMPLING APPROACH TO LINKAGE ANALYSIS
复制标题
DOI：
10.1159/000154046
复制
发表时间：
1992-01-01
期刊：
影响因子：
1.8
通讯作者：
CORTESSIS, V
中科院分区：
文献类型：
--
作者：
THOMAS, DC;CORTESSIS, V
我们提出了一个Monte Carlo方法来估计重组分数θ和二分性状和一个单一的标记基因与2个等位基因的档案可能性。 该方法是一种被称为“吉布斯抽样”的技术的应用，其中每个未知数（这里是基因型，θ和滋扰参数，包括等位基因频率和等位基因频率）的随机样本是从它们的后验分布中提取的，给定所有其他未知数的数据和当前值。 在收敛时，所得到的样本来自所有未知数的边际分布，仅给出数据，使得滋扰参数的规格中的不确定性反映在θ的后验分布的方差中。 可以使用贝叶斯方法来结合关于θ和滋扰参数的分布的先验知识，但是采用用于θ的平坦先验和用于滋扰参数的点先验将对应于标准似然方法。 该方法易于编程，在微机上运行速度快，并可推广到多等位基因，多点连锁，连续表型和更复杂的疾病病因学模型。 的基本方法是说明应用程序的胆固醇水平和低密度脂蛋白受体基因在一个单一的大谱系的数据。
We present a Monte Carlo approach to estimation of the recombination fraction theta and the profile likelihood for a dichotomous trait and a single marker gene with 2 alleles. The method is an application of a technique known as 'Gibbs sampling', in which random samples of each of the unknowns (here genotypes, theta and nuisance parameters, including the allele frequencies and the penetrances) are drawn from their posterior distributions, given the data and the current values of all the other unknowns. Upon convergence, the resulting samples derive from the marginal distribution of all the unknowns, given only the data, so that the uncertainty in the specification of the nuisance parameters is reflected in the variance of the posterior distribution of theta. Prior knowledge about the distribution of theta and the nuisance parameters can be incorporated using a Bayesian approach, but adoption of a flat prior for theta and point priors for the nuisance parameters would correspond to the standard likelihood approach. The method is easy to program, runs quickly on a microcomputer, and could be generalized to multiple alleles, multipoint linkage, continuous phenotypes and more complex models of disease etiology. The basic approach is illustrated by application to data on cholesterol levels and an a low-density lipoprotein receptor gene in a single large pedigree.