A joint learning approach for genomic prediction in polyploid grasses

Autor(es):Mostrar menos -

Aono, Alexandre Hild ; Ulbricht Ferreira, Rebecca Caroline ; Lima Moraes, Aline da Costa ; de Castro Lara, Leticia Aparecida ; Gonzaga Pimenta, Ricardo Jose ; Costa, Estela Araujo ; Pinto, Luciana Rossini ; de Andrade Landell, Marcos Guimaraes ; Santos, Mateus Figueiredo ; Jank, Liana ; Lima Barrios, Sanzio Carvalho ; do Valle, Cacilda Borges ; Chiari, Lucimara ; Franco Garcia, Antonio Augusto ; Kuroshu, Reginaldo Massanobu ; Lorena, Ana Carolina ; Gorjanc, Gregor ; de Souza, Anete Pereira

• Tipo de documento: Artigo Científico
• Fonte: SCIENTIFIC REPORTS; v. 12, n. 1, p. 17-pg., 2022-07-21.

Resumo

Poaceae, among the most abundant plant families, includes many economically important polyploid species, such as forage grasses and sugarcane (Saccharum spp.). These species have elevated genomic complexities and limited genetic resources, hindering the application of marker-assisted selection strategies. Currently, the most promising approach for increasing genetic gains in plant breeding is genomic selection. However, due to the polyploidy nature of these polyploid species, more accurate models for incorporating genomic selection into breeding schemes are needed. This study aims to develop a machine learning method by using a joint learning approach to predict complex traits from genotypic data. Biparental populations of sugarcane and two species of forage grasses (Urochloa decumbens, Megathyrsus maximus) were genotyped, and several quantitative traits were measured. High-quality markers were used to predict several traits in different cross-validation scenarios. By combining classification and regression strategies, we developed a predictive system with promising results. Compared with traditional genomic prediction methods, the proposed strategy achieved accuracy improvements exceeding 50%. Our results suggest that the developed methodology could be implemented in breeding programs, helping reduce breeding cycles and increase genetic gains. (AU)

• Processo FAPESP: 19/26858-8 - Simulação de arquiteturas de características complexas de plantas usando redes neurais profundas
• Beneficiário: Alexandre Hild Aono
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado Direto
• Processo FAPESP: 18/19219-6 - Detecção de genes de interesse agronômico e envolvidos na heterose em Urochloa spp.
• Beneficiário: Rebecca Caroline Ulbricht Ferreira
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 19/21682-9 - Mapeamento associativo e transcriptômica na investigação da resistência da cana-de-açúcar ao vírus do amarelecimento foliar
• Beneficiário: Ricardo José Gonzaga Pimenta
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto
• Processo FAPESP: 19/03232-6 - Seleção genômica ampla em cana-de-açúcar via aprendizado de máquina e redes complexas para caracteres de importância econômica
• Beneficiário: Alexandre Hild Aono
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto