RESUMO

In the field of plant breeding, various machine learning models have been developed and studied to evaluate the genomic prediction (GP) accuracy of unseen phenotypes. Deep learning has shown promise. However, most studies on deep learning in plant breeding have been limited to small datasets, and only a few have explored its application in moderate-sized datasets. In this study, we aimed to address this limitation by utilizing a moderately large dataset. We examined the performance of a deep learning (DL) model and compared it with the widely used and powerful best linear unbiased prediction (GBLUP) model. The goal was to assess the GP accuracy in the context of a five-fold cross-validation strategy and when predicting complete environments using the DL model. The results revealed the DL model outperformed the GBLUP model in terms of GP accuracy for two out of the five included traits in the five-fold cross-validation strategy, with similar results in the other traits. This indicates the superiority of the DL model in predicting these specific traits. Furthermore, when predicting complete environments using the leave-one-environment-out (LOEO) approach, the DL model demonstrated competitive performance. It is worth noting that the DL model employed in this study extends a previously proposed multi-modal DL model, which had been primarily applied to image data but with small datasets. By utilizing a moderately large dataset, we were able to evaluate the performance and potential of the DL model in a context with more information and challenging scenario in plant breeding.

RESUMO

Genomic selection is revolutionizing plant breeding. However, its practical implementation is still very challenging, since predicted values do not necessarily have high correspondence to the observed phenotypic values. When the goal is to predict within-family, it is not always possible to obtain reasonable accuracies, which is of paramount importance to improve the selection process. For this reason, in this research, we propose the Adversaria-Boruta (AB) method, which combines the virtues of the adversarial validation (AV) method and the Boruta feature selection method. The AB method operates primarily by minimizing the disparity between training and testing distributions. This is accomplished by reducing the weight assigned to markers that display the most significant differences between the training and testing sets. Therefore, the AB method built a weighted genomic relationship matrix that is implemented with the genomic best linear unbiased predictor (GBLUP) model. The proposed AB method is compared using 12 real data sets with the GBLUP model that uses a nonweighted genomic relationship matrix. Our results show that the proposed AB method outperforms the GBLUP by 8.6, 19.7, and 9.8% in terms of Pearson's correlation, mean square error, and normalized root mean square error, respectively. Our results support that the proposed AB method is a useful tool to improve the prediction accuracy of a complete family, however, we encourage other investigators to evaluate the AB method to increase the empirical evidence of its potential.

Assuntos

RESUMO

In plant breeding, the need to improve the prediction of future seasons or new locations and/or environments, also denoted as "leave one environment out," is of paramount importance to increase the genetic gain in breeding programs and contribute to food and nutrition security worldwide. Genomic selection (GS) has the potential to increase the accuracy of future seasons or new locations because it is a predictive methodology. However, most statistical machine learning methods used for the task of predicting a new environment or season struggle to produce moderate or high prediction accuracies. For this reason, in this study we explore the use of the partial least squares (PLS) regression methodology for this specific task, and we benchmark its performance with the Bayesian Genomic Best Linear Unbiased Predictor (GBLUP) method. The benchmarking process was done with 14 real datasets. We found that in all datasets the PLS method outperformed the popular GBLUP method by margins between 0% (in the Indica data) and 228.28% (in the Disease data) across traits, environments, and types of predictors. Our results show great empirical evidence of the power of the PLS methodology for the prediction of future seasons or new environments.

RESUMO

Genomic-enabled prediction models are of paramount importance for the successful implementation of genomic selection (GS) based on breeding values. As opposed to animal breeding, plant breeding includes extensive multienvironment and multiyear field trial data. Hence, genomic-enabled prediction models should include genotype × environment (G × E) interaction, which most of the time increases the prediction performance when the response of lines are different from environment to environment. In this chapter, we describe a historical timeline since 2012 related to advances of the GS models that take into account G × E interaction. We describe theoretical and practical aspects of those GS models, including the gains in prediction performance when including G × E structures for both complex continuous and categorical scale traits. Then, we detailed and explained the main G × E genomic prediction models for complex traits measured in continuous and noncontinuous (categorical) scale. Related to G × E interaction models this review also examine the analyses of the information generated with high-throughput phenotype data (phenomic) and the joint analyses of multitrait and multienvironment field trial data that is also employed in the general assessment of multitrait G × E interaction. The inclusion of nongenomic data in increasing the accuracy and biological reliability of the G × E approach is also outlined. We show the recent advances in large-scale envirotyping (enviromics), and how the use of mechanistic computational modeling can derive the crop growth and development aspects useful for predicting phenotypes and explaining G × E.

Assuntos

RESUMO

Genomic selection (GS) has the potential to revolutionize predictive plant breeding. A reference population is phenotyped and genotyped to train a statistical model that is used to perform genome-enabled predictions of new individuals that were only genotyped. In this vein, deep neural networks, are a type of machine learning model and have been widely adopted for use in GS studies, as they are not parametric methods, making them more adept at capturing nonlinear patterns. However, the training process for deep neural networks is very challenging due to the numerous hyper-parameters that need to be tuned, especially when imperfect tuning can result in biased predictions. In this paper we propose a simple method for calibrating (adjusting) the prediction of continuous response variables resulting from deep learning applications. We evaluated the proposed deep learning calibration method (DL_M2) using four crop breeding data sets and its performance was compared with the standard deep learning method (DL_M1), as well as the standard genomic Best Linear Unbiased Predictor (GBLUP). While the GBLUP was the most accurate model overall, the proposed deep learning calibration method (DL_M2) helped increase the genome-enabled prediction performance in all data sets when compared with the traditional DL method (DL_M1). Taken together, we provide evidence for extending the use of the proposed calibration method to evaluate its potential and consistency for predicting performance in the context of GS applied to plant breeding.

RESUMO

The rapid development of molecular markers and sequencing technologies has made it possible to use genomic prediction (GP) and selection (GS) in animal and plant breeding. However, when the number of observations (n) is large (thousands or millions), computational difficulties when handling these large genomic kernel relationship matrices (inverting and decomposing) increase exponentially. This problem increases when genomic × environment interaction and multi-trait kernels are included in the model. In this research we propose selecting a small number of lines m(m < n) for constructing an approximate kernel of lower rank than the original and thus exponentially decreasing the required computing time. First, we describe the full genomic method for single environment (FGSE) with a covariance matrix (kernel) including all n lines. Second, we select m lines and approximate the original kernel for the single environment model (APSE). Similarly, but including main effects and G × E, we explain a full genomic method with genotype × environment model (FGGE), and including m lines, we approximated the kernel method with G × E (APGE). We applied the proposed method to two different wheat data sets of different sizes (n) using the standard linear kernel Genomic Best Linear Unbiased Predictor (GBLUP) and also using eigen value decomposition. In both data sets, we compared the prediction performance and computing time for FGSE versus APSE; we also compared FGGE versus APGE. Results showed a competitive prediction performance of the approximated methods with a significant reduction in computing time. Genomic prediction accuracy depends on the decay of the eigenvalues (amount of variance information loss) of the original kernel as well as on the size of the selected lines m.

RESUMO

Stripe rust is a major disease constraint of wheat production worldwide. Resistance to stripe rust was analyzed using 131 F6 recombinant inbred lines (RILs) derived from a cross between synthetic derived wheat line Soru#1 and wheat cultivar Naxos. The phenotype was evaluated in Mexico and Norway at both seedling and adult plant stages. Linkage groups were constructed based on 90K single-nucleotide polymorphism (SNP), sequence-tagged site, and simple sequence repeat markers. Two major resistance loci conferred by Soru#1 were detected and located on chromosomes 1BL and 4DS. The 1BL quantitative trait loci explained 15.8 to 40.2 and 51.1% of the phenotypic variation at adult plant and seedling stages, respectively. This locus was identified as Yr24/Yr26 based on the flanking markers and infection types. Locus 4DS was flanked by molecular markers D_GB5Y7FA02JMPQ0_238 and BS00108770_51. It explained 8.4 to 27.8 and 5.5% of stripe rust variation at the adult plant and seedling stages, respectively. The 4DS locus may correspond to known resistance gene Yr28 based on the resistance source. All RILs that combine Yr24/Yr26 and Yr28 showed significantly reduced stripe rust severity in all four environments compared with the lines with only one of the genes. SNP marker BS00108770_51 was converted into a breeder-friendly kompetitive allele-specific polymerase chain reaction marker that will be useful to accelerate Yr28 deployment in wheat breeding programs.

Assuntos

RESUMO

It has been well documented that dwarfing genes Rht-B1b and Rht-D1b are associated with Type I susceptibility to Fusarium head blight (FHB) in wheat; but the underlying mechanism has not been well delineated. Anther extrusion (AE) has also been related to Type I resistance for initial FHB infection, where high AE renders FHB resistance. In this study, two doubled haploid populations were used to investigate the impact of the two dwarfing genes on FHB resistance and AE, and to elucidate the role of AE in Rht-mediated FHB susceptibility. Both populations were derived by crossing the FHB susceptible cultivar 'Ocoroni F86' (Rht-B1a/Rht-D1b) with an FHB resistant variety (Rht-B1b/Rht-D1a), which was 'TRAP#1/BOW//Taigu derivative' in one population (the TO population) and 'Ivan/Soru#2' in the other (the IO population). Field experiments were carried out from 2010 to 2012 in El Batán, Mexico, where spray inoculation was adopted and FHB index, plant height (PH), and AE were evaluated, with the latter two traits showing always significantly negative correlations with FHB severity. The populations were genotyped with the DArTseq GBS platform, the two dwarfing genes and a few SSRs for QTL analysis, and the results indicated that Rht-B1b and Rht-D1b collectively accounted for 0-41% of FHB susceptibility and 13-23% of reduced AE. It was also observed that three out of the four AE QTL in the TO population and four out of the five AE QTL in the IO population were associated with FHB resistance. Collectively, our results demonstrated the effects of Rht-B1b and Rht-D1b on Type I FHB susceptibility and reducing AE, and proposed that their impacts on Type I FHB susceptibility may partly be explained by their effects on reducing AE. The implication of the relationship between the two dwarfing genes and AE for hybrid wheat breeding was also discussed.

Assuntos

RESUMO

Fusarium head blight (FHB) resistant line Soru#1 was hybridized with the German cultivar Naxos to generate 131 recombinant inbred lines for QTL mapping. The population was phenotyped for FHB and associated traits in spray inoculated experiments in El Batán (Mexico), spawn inoculated experiments in Ås (Norway) and point inoculated experiments in Nanjing (China), with two field trials at each location. Genotyping was performed with the Illumina iSelect 90K SNP wheat chip, along with a few SSR and STS markers. A major QTL for FHB after spray and spawn inoculation was detected on 2DLc, explaining 15-22% of the phenotypic variation in different experiments. This QTL remained significant after correction for days to heading (DH) and plant height (PH), while another QTL for FHB detected at the Vrn-A1 locus on 5AL almost disappeared after correction for DH and PH. Minor QTL were detected on chromosomes 2AS, 2DL, 4AL, 4DS and 5DL. In point inoculated experiments, QTL on 2DS, 3AS, 4AL and 5AL were identified in single environments. The mechanism of resistance of Soru#1 to FHB was mainly of Type I for resistance to initial infection, conditioned by the major QTL on 2DLc and minor ones that often coincided with QTL for DH, PH and anther extrusion (AE). This indicates that phenological and morphological traits and flowering biology play important roles in resistance/escape of FHB. SNPs tightly linked to resistance QTL, particularly 2DLc, could be utilized in breeding programs to facilitate the transfer and selection of those QTL.

Assuntos

RESUMO

Linkage disequilibrium can be used for identifying associations between traits of interest and genetic markers. This study used mapped diversity array technology (DArT) markers to find associations with resistance to stem rust, leaf rust, yellow rust, and powdery mildew, plus grain yield in five historical wheat international multienvironment trials from the International Maize and Wheat Improvement Center (CIMMYT). Two linear mixed models were used to assess marker-trait associations incorporating information on population structure and covariance between relatives. An integrated map containing 813 DArT markers and 831 other markers was constructed. Several linkage disequilibrium clusters bearing multiple host plant resistance genes were found. Most of the associated markers were found in genomic regions where previous reports had found genes or quantitative trait loci (QTL) influencing the same traits, providing an independent validation of this approach. In addition, many new chromosome regions for disease resistance and grain yield were identified in the wheat genome. Phenotyping across up to 60 environments and years allowed modeling of genotype x environment interaction, thereby making possible the identification of markers contributing to both additive and additive x additive interaction effects of traits.

Assuntos