EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating machine learning with single-step GBLUP for enhanced genomic prediction in white spruce

Eduardo Pablo Cappa, Charles Chen, Andy Benowicz, Barb R. Thomas, Yousry A. El-Kassaby

Tree Genetics & Genomes · 2026-08 · 22 (4)

DOI: 10.1007/s11295-026-01746-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tree Genetics & Genomes, online erschienen am 10.07.2026. Verfasst von Eduardo Pablo Cappa und 4 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, The Extreme Science and Engineering Discovery, Genome Canada.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We evaluated the predictive performance of machine learning-augmented single- and multi-trait single-step genomic best linear prediction (ssGBLUP) models for 30 complex traits spanning productivity, chemical defense, and climate adaptability in white spruce ( Picea glauca ) from Alberta, Canada, genotyped at 211,061 SNPs. We extend a novel integration of the ssGBLUP with non-linear kernels for forest tree improvement. Using the conventional ssGBLUP model with VanRaden’s linear genomic relationship matrix as baseline, we compared two non-linear extensions: an averaged Gaussian kernel (GK) with trait-specific bandwidths and an arc-cosine kernel (AK) with 1–20 layers (depth). To relate prediction gains to genetic architecture, we also fitted an extended GBLUP model explicitly including additive, dominance, and epistatic (additive × additive and additive × dominance) effects. Additive effects predominated in 21 traits, dominance contributed > 50% of variance in several chemical-defense traits, and epistasis explained ~ 25% in key physiological traits. Predictive performance varied by kernel type and trait architecture. AK achieved the highest accuracy in 29 traits, improving prediction by up to 27% (predictive differences up to ~ 0.10), particularly for traits with more complex genetic architectures. GK yielded modest gains (< 7%; predictive differences < 0.03), while linear G kernel remained competitive for core productivity traits. In multi-trait models, non-linear kernels performed similar to the linear alternatives. Notably, low-heritability traits such as drought resistance improved from 0.446-0.517 to 0.461-0.547 accuracy with multi-trait integration. These findings suggest that matching kernel complexity to genetic architecture may enhance genomic prediction and highlight the potential of non-linear kernels, particularly AK, in forest tree breeding.

Förderung

  • National Science Foundation
  • The Extreme Science and Engineering Discovery
  • Genome Canada
  • Genome Alberta
  • University of Alberta/Faculty ALES/Dept RR
  • Alberta Innovates – BioSolutions
  • Forest Resource Improvement Association of Alberta
  • Genome British Columbia

Zitieren

APA

Cappa, E. P., Chen, C., Benowicz, A., Thomas, B. R., & El-Kassaby, Y. A. (2026). Integrating machine learning with single-step GBLUP for enhanced genomic prediction in white spruce. Tree Genetics & Genomes, 22(4). https://doi.org/10.1007/s11295-026-01746-9

Vancouver

Cappa EP, Chen C, Benowicz A, Thomas BR, El-Kassaby YA. Integrating machine learning with single-step GBLUP for enhanced genomic prediction in white spruce. Tree Genetics & Genomes. 2026;22(4). doi:10.1007/s11295-026-01746-9

BibTeX
@article{Cappa2026,
  author = {Cappa, Eduardo Pablo and Chen, Charles and Benowicz, Andy and Thomas, Barb R. and El-Kassaby, Yousry A.},
  title = {Integrating machine learning with single-step GBLUP for enhanced genomic prediction in white spruce},
  journal = {Tree Genetics & Genomes},
  year = {2026},
  volume = {22},
  number = {4},
  doi = {10.1007/s11295-026-01746-9}
}
Kostenlos starten →