Location: Corn Host Plant Resistance ResearchTitle: Target-oriented prioritization: targeted selection strategy by integrating organismal and molecular traits through predictive analytics in breeding
|YANG, WENYU - Huazhong Agricultural University|
|GUO, TINGTING - Huazhong Agricultural University|
|LUO, JINGYUN - Huazhong Agricultural University|
|ZHANG, RUYANG - Beijing Research Center For Information Technology In Agriculture, Beijing Academy Of Agriculture A|
|ZHAO, JIURAN - Beijing Research Center For Information Technology In Agriculture, Beijing Academy Of Agriculture A|
|XIAO, YINGJIE - Huazhong Agricultural University|
|YAN, JIANBING - Huazhong Agricultural University|
Submitted to: Genome Biology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/8/2022
Publication Date: 3/15/2022
Citation: Yang, W., Guo, T., Luo, J., Zhang, R., Zhao, J., Warburton, M.L., Xiao, Y., Yan, J. 2022. Target-oriented prioritization: Targeted selection strategy by integrating organismal and molecular traits through predictive analytics in breeding. Genome Biology. 23. Article 80. https://doi.org/10.1186/s13059-022-02650-w.
Interpretive Summary: New ways of doing plant breeding are letting people create new, higher yielding and stress-resistant cultivars in less time. There is so much new information available to breeders now that when they want to select the best candidates and test them as a new cultivar, they are actually hindered by all the data and determining which of the data is the most useful. This is the paradox of the big data revolution. This paper describes a computer tool called Target-Oriented Prioritization (TOP). TOP sorts through the data and allows breeders to determine which are the best candidates by using advance machine learning techniques. The breeder simply needs to put all the data available into the program, identify key plants that the breeder wishes to use as a good example, and allows the program to select other plants that are as good or better than that example plant, even if the breeder does not have all the data on every plant; this is the strength of TOP. It can identify good plants with less work.
Technical Abstract: Genomic prediction in crop breeding is hindered by modeling on limited phenotypic traits. We propose an integrative multi-trait breeding strategy via machine learning algorithm, target-oriented prioritization (TOP). Using a large hybrid maize population, we demonstrate that the accuracy for identifying a candidate that is phenotypically closest to an ideotype, or target variety, achieves up to 91%. The strength of TOP is enhanced when omics level traits are included. We show that TOP enables selection of inbreds or hybrids that outperform existing commercial varieties. It improves multiple traits and accurately identifies improved candidates for new varieties, which will greatly influence breeding.