Use of a novel evolutionary algorithm for genomic selection

Julie Hamon 1, * Gaël Even 2 Romain Dassonneville 3, 4 Julien Jacques 5, 6 Clarisse Dhaenens 7
* Auteur correspondant
5 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, CERIM - Santé publique : épidémiologie et qualité des soins-EA 2694, Polytech Lille, Université de Lille 1, IUT’A
Abstract : Background: In the context of genomic selection in animal breeding, an important objective is to look for explicative markers for a phenotype under study. The challenge of this study was to propose a model, based on a small number of markers, to predict a quantitative trait. To deal with a high number of markers, we propose using combinatorial optimization to perform variable selection, associated with a multiple regression model in a first approach and a mixed model in a second, to predict the phenotype. Results:The efficiency of our two approaches, the first assuming that animals are independent and the second integrating familial relationships, was evaluated on real datasets. This reveals the importance of taking familial relationships into account as the performances of the second approach were better. For example, on PIC data the correlation is around 0.15 higher using our approach taking familial relationships into account than with the Lasso bounded to 96 selected markers. We also studied the importance of familial relationships on phenotypes with different heritabilities. Finally, we compared our approaches with classic approaches and obtained comparable results, sometimes better. Conclusion: This study shows the relevance of combining combinatorial optimization with a regression model to propose a predictive model based on a reasonable number of markers. Although this implies more parameters to be estimated and, therefore, takes longer to execute, it seems interesting to use a mixed model in order to take familial relationships between animals into account.
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger
Contributeur : Julie Hamon <>
Soumis le : mardi 6 janvier 2015 - 17:47:03
Dernière modification le : jeudi 12 avril 2018 - 11:08:15
Document(s) archivé(s) le : mardi 7 avril 2015 - 11:50:40


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01100660, version 1


Julie Hamon, Gaël Even, Romain Dassonneville, Julien Jacques, Clarisse Dhaenens. Use of a novel evolutionary algorithm for genomic selection. 2015. 〈hal-01100660〉



Consultations de la notice


Téléchargements de fichiers