Mostra el registre parcial de l'element
Evaluation of deep learning for predicting rice traits using structural and single-nucleotide genomic variants
dc.contributor.author | Vourlaki, Ioanna-Theoni | |
dc.contributor.author | Ramos-Onsins, Sebastián E. | |
dc.contributor.author | Pérez-Enciso, Miguel | |
dc.contributor.author | Castanera, Raúl | |
dc.contributor.other | Producció Vegetal | ca |
dc.date.accessioned | 2024-09-20T09:48:52Z | |
dc.date.available | 2024-09-20T09:48:52Z | |
dc.date.issued | 2024-08-10 | |
dc.identifier.citation | Vourlaki, Ioanna-Theoni, Sebastián E. Ramos-Onsins, Miguel Pérez-Enciso, and Raúl Castanera. 2024. Plant Methods 20 (1). doi:10.1186/s13007-024-01250-y. | ca |
dc.identifier.issn | 1746-4811 | ca |
dc.identifier.uri | http://hdl.handle.net/20.500.12327/3282 | |
dc.description.abstract | Background - Structural genomic variants (SVs) are prevalent in plant genomes and have played an important role in evolution and domestication, as they constitute a signicant source of genomic and phenotypic variability. Never‑theless, most methods in quantitative genetics focusing on crop improvement, such as genomic prediction, consider only Single Nucleotide Polymorphisms (SNPs). Deep Learning (DL) is a promising strategy for genomic prediction, but its performance using SVs and SNPs as genetic markers remains unknown. Results - We used rice to investigate whether combining SVs and SNPs can result in better trait prediction over SNPs alone and examine the potential advantage of Deep Learning (DL) networks over Bayesian Linear models. Specically, the performances of BayesC (considering additive eects) and a Bayesian Reproducible Kernel Hilbert space (RKHS) regression (considering both additive and non‑additive eects) were compared to those of two dierent DL architectures, the Multilayer Perceptron, and the Convolution Neural Network, to explore their prediction ability by using vari‑ ous marker input strategies. We found that exploiting structural and nucleotide variation slightly improved prediction ability on complex traits in 87% of the cases. DL models outperformed Bayesian models in 75% of the studied cases, considering the four traits and the two validation strategies used. Finally, DL systematically improved prediction ability of binary traits against the Bayesian models. Conclusions - Our study reveals that the use of structural genomic variants can improve trait prediction in rice, independently of the methodology used. Also, our results suggest that Deep Learning (DL) networks can perform better than Bayesian models in the prediction of binary traits, and in quantitative traits when the training and target sets are not closely related. This highlights the potential of DL to enhance crop improvement in specific scenarios and the importance to consider SVs in addition to SNPs in genomic selection. | ca |
dc.description.sponsorship | Grants PID2019-108829RB-I00 and CEX2019-000902-S funded by MICIU/AEI/https://doi.org/10.13039/501100011033. IJC2020-045949-I and BES-2017-081139 funded by MICIU/AEI/ https://doi.org/10.13039/501100011033 and by “ESF Investing in your future”. RYC2022-037459-I funded by MICIU/AEI/ https://doi.org/10.13039/501100011033 and by “FSE+ | ca |
dc.format.extent | 16 | ca |
dc.language.iso | eng | ca |
dc.publisher | BMC | ca |
dc.relation.ispartof | Plant Methods | ca |
dc.rights | Attribution 4.0 International | ca |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | * |
dc.title | Evaluation of deep learning for predicting rice traits using structural and single-nucleotide genomic variants | ca |
dc.type | info:eu-repo/semantics/article | ca |
dc.description.version | info:eu-repo/semantics/publishedVersion | ca |
dc.rights.accessLevel | info:eu-repo/semantics/openAccess | |
dc.embargo.terms | cap | ca |
dc.relation.projectID | MICIU/Programa Estatal de generación del conocimiento y fortalecimiento científico y tecnológico del sistema I+D+I y Programa Estatal de I+D+I orientada a los retos de la sociedad/PID2019-108829RB-I00/ES/La belleza de lo profundo: Aplicaciones del deep learning a la predicción genómica/ | ca |
dc.relation.projectID | MICIU/Programa Estatal de generación del conocimiento y fortalecimiento científico y tecnológico del sistema I+D+I/CEX2019-000902-S/ES/ / | ca |
dc.relation.projectID | MICINN/Programa Estatal de promoción del talento y su empleabilidad en I+D+I/IJC2020-045949-I/ES/ / | ca |
dc.relation.projectID | MICINN/ /RYC2022-037459-I/ES/ / | ca |
dc.subject.udc | 633 | ca |
dc.identifier.doi | https://doi.org/10.1186/s13007-024-01250-y | ca |
dc.contributor.group | Genòmica i Biotecnologia | ca |
Fitxers en aquest element
Aquest element apareix en la col·lecció o col·leccions següent(s)
-
ARTICLES CIENTÍFICS [2.831]