Multi-trait genomic selection for weevil resistance, growth, and wood quality in Norway spruce

Abstract

Plantation-grown trees have to cope with an increasing pressure of pest and disease in the context of climate change, and breeding approaches using genomics may offer efficient and flexible tools to face this pressure. In the present study, we targeted genetic improvement of resistance of an introduced conifer species in Canada, Norway spruce (Picea abies (L.) Karst.), to the native white pine weevil (Pissodes strobi Peck). We developed single- and multi-trait genomic selection (GS) models and selection indices considering the relationships between weevil resistance, intrinsic wood quality, and growth traits. Weevil resistance, acoustic velocity as a proxy for mechanical wood stiffness, and average wood density showed moderate-to-high heritability and low genotype-by-environment interactions. Weevil resistance was genetically positively correlated with tree height, height-to-diameter at breast height (DBH) ratio, and acoustic velocity. The accuracy of the different GS models tested (GBLUP, threshold GBLUP, Bayesian ridge regression, BayesCπ) was high and did not differ among each other. Multi-trait models performed similarly as single-trait models when all trees were phenotyped. However, when weevil attack data were not available for all trees, weevil resistance was more accurately predicted by integrating genetically correlated growth traits into multi-trait GS models. A GS index that corresponded to the breeders' priorities achieved near maximum gains for weevil resistance, acoustic velocity, and height growth, but a small decrease for DBH. The results of this study indicate that it is possible to breed for high-quality, weevil-resistant Norway spruce reforestation stock with high accuracy achieved from single-trait or multi-trait GS.

Keywords: Norway spruce; breeding; conifers; index selection; insect resistance; multi‐trait genomic selection; white pine weevil; wood quality.

Figure 1

[Box 1] . Genomic selection modeling and integration in tree breeding

Figure 2

[Box 1] . Estimated time for completing a breeding cycle in (sub‐)boreal conifers such as spruces

Figure 3

Location of the test sites Saint‐Modeste (STM) and Grandes‐Piles (GPI) in the province of Québec, Canada

Figure 4

(a) Predictive ability (PA) and (b) predictive accuracy (PACC) of the single‐trait genomic selection models (GBLUP, BRR, BayesCπ) and the conventional pedigree‐based model (ABLUP) tested in this study. For the cumulative number of weevil attacks (CWA), three models accounted for ordinal data type, namely the threshold GBLUP model (TGBLUP), BRR, and BayesCπ, while ABLUP and GBLUP assumed that errors were normally distributed. Error bars indicate the standard errors of the estimates. The PACC of models for the trait DBH₁₅ was not calculated because the estimated heritability was null. See Table 1 for full description of traits

Figure 5

Predictive accuracy (PACC) of GBLUP multi‐trait genomic selection models for predicting the target traits: (a) the cumulative number of weevil attacks (CWA); (b) Density₁₅; and (c) MFA₁₅. The different colored lines represent different multi‐trait models with different indicator traits. The dashed gray line is the single‐trait GBLUP model. The percentage of missing phenotypic data for the target trait in the training sets was varied from 0% to 90% (x‐axis), while 100% of the training data was retained for the indicator traits. See Table 1 for full description of traits