The application of pangenomics and machine learning in genomic selection in plants

• Published in: The plant genome Vol. 14; no. 3; pp. e20112 - n/a
• Main Authors: Bayer, Philipp E., Petereit, Jakob, Danilevicz, Monica Furaste, Anderson, Robyn, Batley, Jacqueline, Edwards, David
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01-11-2021; Wiley
• Subjects: Agricultural production; Barley; Canola; Cereals; Climate change; Crop improvement; Crop production; Crop yield; Crops; Domestication; Genes; Genome, Plant; Genomes; Genomics; Genomics - methods; Learning algorithms; Machine Learning; Plant breeding; Plant Breeding - methods; Population growth; Seeds; Trends; Wheat; Montenegro
• ISSN: 1940-3372; 1940-3372
• DOI: 10.1002/tpg2.20112

Genomic selection approaches have increased the speed of plant breeding, leading to growing crop yields over the last decade. However, climate change is impacting current and future yields, resulting in the need to further accelerate breeding efforts to cope with these changing conditions. Here we present approaches to accelerate plant breeding and incorporate nonadditive effects in genomic selection by applying state‐of‐the‐art machine learning approaches. These approaches are made more powerful by the inclusion of pangenomes, which represent the entire genome content of a species. Understanding the strengths and limitations of machine learning methods, compared with more traditional genomic selection efforts, is paramount to the successful application of these methods in crop breeding. We describe examples of genomic selection and pangenome‐based approaches in crop breeding, discuss machine learning‐specific challenges, and highlight the potential for the application of machine learning in genomic selection. We believe that careful implementation of machine learning approaches will support crop improvement to help counter the adverse outcomes of climate change on crop production.
Core Ideas
Genomic selection (GS) has been successful in plant breeding, leading to increased yield.
Machine learning has been applied in GS based on the ever‐growing amount of genomic data.
Some machine learning outcomes are difficult to assess for plant breeders.
Pangenome references are a valuable resource for GS.
Novel methods assist in interpreting the outcomes of machine learning algorithms.