An adaptive threshold determination method of feature screening for genomic selection

BMC Bioinformatics

Methodology Article

Gang Wang¹  Xiaotian Dai¹  Guifang Fu¹ 

[1] Department of Mathematics and Statistics, Utah State University, 84322, Logan, UT, USA;

关键词: Genomic selection;    Feature screening;    Backward elimination;    FRIGIDA;   

DOI  :  10.1186/s12859-017-1617-9

 received in 2016-11-09, accepted in 2017-03-28,  发布年份 2017

来源: Springer

【 摘 要 】

BackgroundAlthough the dimension of the entire genome can be extremely large, only a parsimonious set of influential SNPs are correlated with a particular complex trait and are important to the prediction of the trait. Efficiently and accurately selecting these influential SNPs from millions of candidates is in high demand, but poses challenges. We propose a backward elimination iterative distance correlation (BE-IDC) procedure to select the smallest subset of SNPs that guarantees sufficient prediction accuracy, while also solving the unclear threshold issue for traditional feature screening approaches.ResultsVerified through six simulations, the adaptive threshold estimated by the BE-IDC performed uniformly better than fixed threshold methods that have been used in the current literature. We also applied BE-IDC to an Arabidopsis thaliana genome-wide data. Out of 216,130 SNPs, BE-IDC selected four influential SNPs, and confirmed the same FRIGIDA gene that was reported by two other traditional methods.ConclusionsBE-IDC accommodates both the prediction accuracy and the computational speed that are highly demanded in the genomic selection.

【 授权许可】

CC BY   
© The Author(s) 2017

【 图 表 】

12864_2017_3492_Article_IEq20.gif

12864_2015_2297_Article_IEq19.gif

12864_2017_3492_Article_IEq19.gif

12864_2017_3733_Article_IEq63.gif

12864_2016_2789_Article_IEq42.gif

12864_2016_2789_Article_IEq41.gif

12864_2017_3733_Article_IEq60.gif

12864_2016_3098_Article_IEq29.gif

12864_2017_3733_Article_IEq59.gif

12864_2016_2463_Article_IEq1.gif

12864_2017_3777_Article_IEq18.gif

12864_2017_3487_Article_IEq63.gif

12864_2017_3777_Article_IEq17.gif

12864_2017_3487_Article_IEq62.gif

12894_2015_Article_5_TeX2GIF_IEq1.gif

12864_2017_3487_Article_IEq60.gif

12864_2015_2137_Article_IEq5.gif

12864_2017_4133_Article_IEq38.gif

12864_2017_3655_Article_IEq6.gif

12864_2017_4133_Article_IEq37.gif

12864_2017_4133_Article_IEq36.gif

12864_2017_3605_Article_IEq16.gif

12864_2017_4190_Article_IEq8.gif

12864_2017_3676_Article_IEq7.gif

12864_2017_4190_Article_IEq7.gif

12864_2017_3609_Article_IEq9.gif

12864_2017_3609_Article_IEq8.gif

12864_2017_3492_Article_IEq11.gif

12864_2017_3676_Article_IEq4.gif

12864_2017_3609_Article_IEq6.gif

12864_2017_3492_Article_IEq8.gif

12864_2017_3492_Article_IEq7.gif

12864_2016_2848_Article_IEq1.gif

12864_2017_3990_Article_IEq18.gif

12864_2016_3440_Article_IEq76.gif

12864_2017_3521_Article_IEq2.gif

12864_2017_3733_Article_IEq48.gif

12864_2017_4132_Article_IEq33.gif

12864_2017_3733_Article_IEq47.gif

12864_2015_2129_Article_IEq36.gif

12864_2015_2199_Article_IEq12.gif

12864_2015_2242_Article_IEq1.gif

12864_2015_2129_Article_IEq33.gif

12864_2017_3920_Article_IEq6.gif

12864_2016_2388_Article_IEq4.gif