Improved LASSO priors for shrinkage quantitative trait loci mapping

文献类型： 外文期刊

第一作者： Fang, Ming

作者： Fang, Ming;Jiang, Dan;Pu, Lijun;Wang, Guihua;Yu, Liyun;Li, Dandan;Yang, Runqing;Fu, Weixuan;Gao, Huijiang

作者机构：

期刊名称：THEORETICAL AND APPLIED GENETICS （ 影响因子：5.699； 五年影响因子：5.565 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Recently, the Bayesian least absolute shrinkage and selection operator (LASSO) has been successfully applied to multiple quantitative trait loci (QTL) mapping, which assigns the double-exponential prior and the Student's t prior to QTL effect that lead to the shrinkage estimate of QTL effect. However, as reported by many researchers, the Bayesian LASSO usually cannot effectively shrink the effects of zero-effect QTL very close to zero. In this study, the double-exponential prior and Student's t prior are modified so that the estimate of the effect for zero-effect QTL can be effectively shrunk toward zero. It is also found that the Student's t prior is virtually the same as the Jeffreys' prior, since both the shape and scale parameters of the scaled inverse Chi-square prior involved in the Student's t prior are estimated very close to zero. Besides the two modified Bayesian Markov chain Monte Carlo (MCMC) algorithms, an expectation-maximization (EM) algorithm with use of the modified double-exponential prior is also adapted. The results shows that the three new methods perform similarly on true positive rate and false positive rate for QTL detection, and all of them outperform the Bayesian LASSO.

分类号： R394

  • 相关文献
作者其他论文 更多>>

微信小程序