Prediction in high dimensional linear models and application to genomic selection under imperfect linkage disequilibrium

Charles-Elie Rabier (1, 2) , Simona Grusea (3)

1 UMR ISEM - Institut des Sciences de l'Evolution de Montpellier
2 LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
3 IMT - Institut de Mathématiques de Toulouse UMR5219

Genomic selection (GS) consists in predicting breeding values of selection candidates, using a large number of genetic markers. An important question in GS is the determination of the number of markers required for a good prediction. When the genetic map is too sparse, it is likely to observe some imperfect linkage disequilibrium: the alleles at a gene location and at a marker located nearby vary. We tackle here the problem of imperfect linkage disequilibrium and we present theoretical results regarding the accuracy criteria, the correlation between predicted value and true value. Illustrations on simulated data and on rice real data are proposed.

Mots clés: Accuracy; Genomic Selection; High Dimension; Linear Model; Prediction; Ridge Regression; Singular Value Decomposition; Sparsity; Imperfect Linkage Disequilibrium; Rice Data Analysis

Domaines: Statistiques [math.ST]

Charles-Elie Rabier, Simona Grusea. Prediction in high dimensional linear models and application to genomic selection under imperfect linkage disequilibrium. 2019. ⟨hal-01987222v3⟩