科研之友
微信
新浪微博
Facebook
分享链接
摘要
Several genome wide selection (GWS) statistical methods have been proposed in the last years, and among these stands out the Bayesian LASSO (BL), which is a penalized regression method based on the regularization parameter (gimel) estimates. In general, the posterior mean values for gimel are those that minimize the residual sum of squares (RSS) while controlling the L1 norm (absolute values) of the regression coefficients. However, another option is to use fixed values of gimel, which is independent of this minimization process. Nevertheless, the most important aim of GWS is to make predictions about genomic breeding values (GBV = u) for individuals that have not been measured directly for the trait, and for this reason the parameter to maximize should be the accuracy (r(u),((u) over cap),). Thus, a question can arise as to whether such estimated gimel values that minimize RSS are the same as that which maximize r(u,(u) over cap). In order to answer this question, this paper aims to provide methodological and computational resources in order to evaluate the influence of BL regularization parameter estimates on the correlation between true and estimated GBV (accuracy) depending on genetic structure of the target trait (few or many QTLs and low or medium heritability). In general, it is possible to report, on average, that GBV prediction is robust in relation to the gimel estimation, since the different values for gimel lead to similar accuracy values. Moreover, the fixed gimel values grid request high computational costs, implying that the random gimel method is more attractive, since it is much faster to use just one Gibbs sampler run, while the grid must to use one run for each fixed X value.
- 出版日期2011-12
