Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models

Breeding for grain yield, biotic and abiotic stress resistance, and end-use quality are important goals of wheat breeding programs. Screening for end-use quality traits is usually secondary to grain yield due to high labor needs, cost of testing, and large seed requirements for phenotyping. Hence, testing is delayed until later stages in the breeding program. Delayed phenotyping results in advancement of inferior end-use quality lines into the program. Genomic selection provides an alternative to predict performance using genome-wide markers. Due to large datasets in breeding programs, we explored the potential of the machine and deep learning models to predict fourteen end-use quality traits in a winter wheat breeding program. The population used consisted of 666 wheat genotypes screened for five years (2015-19) at two locations (Pullman and Lind, WA, USA). Nine different models, including two machine learning (random forest and support vector machine) and two deep learning models (convolutional neural network and multilayer perceptron), were explored for cross-validation, forward, and across locations predictions. The prediction accuracies for different traits varied from 0.45-0.81, 0.29-0.55, and 0.27-0.50 under cross-validation, forward, and across location predictions. In general, forward prediction accuracies kept increasing over time due to increments in training data size and was more evident for machine and deep learning models. Deep learning models performed superior over the traditional ridge regression best linear unbiased prediction (RRBLUP) and Bayesian models under all prediction scenarios. The high accuracy observed for end-use quality traits in this study support predicting them in early generations, leading to the advancement of superior genotypes to more extensive grain yield trailing. Furthermore, the superior performance of machine and deep learning models strengthen the idea to include them in large scale breeding programs for predicting complex traits.

Multi-Trait Machine and Deep Learning Models for Genomic Selection using Spectral Information in a Wheat Breeding Program

Prediction of breeding values and phenotypes is central to plant breeding and has been revolutionized by the adoption of genomic selection (GS). Use of machine and deep learning algorithms applied to complex traits in plants can improve prediction accuracies in the context of GS. Spectral reflectance indices further provide information about various physiological parameters previously undetectable in plants. This research explores the potential of multi-trait (MT) machine and deep learning models for predicting grain yield and grain protein content in wheat using spectral information in GS models. This study compares the performance of four machine and deep learning-based uni-trait (UT) and MT models with traditional GBLUP and Bayesian models. The dataset consisted of 650 recombinant inbred lines from a spring wheat breeding program, grown for three years (2014-2016), and spectral data were collected at heading and grain filling stages. MT-GS models performed 0-28.5% and −0.04-15% superior to the UT-GS models for predicting grain yield and grain protein content. Random forest and multilayer perceptron were the best performing machine and deep learning models to predict both traits. These two models performed similarly under UT and MT-GS models. Four explored Bayesian models gave similar accuracies, which were less than machine and deep learning-based models, and required increased computational time. Green normalized difference vegetation index best predicted grain protein content in seven out of the nine MT-GS models. Overall, this study concluded that machine and deep learning-based MT-GS models increased prediction accuracy and should be employed in large-scale breeding programs.Core IdeasPotential for combining high throughput phenotyping, machine and deep learning in breeding.Multi-trait models exploit information from secondary correlated traits efficiently.Spectral information improves genomic selection models.Deep learning can aid plant breeders owing to increased data generated in breeding programs

Deep Learning for Predicting Complex Traits in Spring Wheat Breeding Program

Genomic selection (GS) is transforming the field of plant breeding and implementing models that improve prediction accuracy for complex traits is needed. Analytical methods for complex datasets traditionally used in other disciplines represent an opportunity for improving prediction accuracy in GS. Deep learning (DL) is a branch of machine learning (ML) which focuses on densely connected networks using artificial neural networks for training the models. The objective of this research was to evaluate the potential of DL models in the Washington State University spring wheat breeding program. We compared the performance of two DL algorithms, namely multilayer perceptron (MLP) and convolutional neural network (CNN), with ridge regression best linear unbiased predictor (rrBLUP), a commonly used GS model. The dataset consisted of 650 recombinant inbred lines (RILs) from a spring wheat nested association mapping (NAM) population planted from 2014–2016 growing seasons. We predicted five different quantitative traits with varying genetic architecture using cross-validations (CVs), independent validations, and different sets of SNP markers. Hyperparameters were optimized for DL models by lowering the root mean square in the training set, avoiding model overfitting using dropout and regularization. DL models gave 0 to 5% higher prediction accuracy than rrBLUP model under both cross and independent validations for all five traits used in this study. Furthermore, MLP produces 5% higher prediction accuracy than CNN for grain yield and grain protein content. Altogether, DL approaches obtained better prediction accuracy for each trait, and should be incorporated into a plant breeder’s toolkit for use in large scale breeding programs.

Strategies Using Genomic Selection to Increase Genetic Gain in Breeding Programs for Wheat

Conventional wheat-breeding programs involve crossing parental lines and subsequent selfing of the offspring for several generations to obtain inbred lines. Such a breeding program takes more than 8 years to develop a variety. Although wheat-breeding programs have been running for many years, genetic gain has been limited. However, the use of genomic information as selection criterion can increase selection accuracy and that would contribute to increased genetic gain. The main objective of this study was to quantify the increase in genetic gain by implementing genomic selection in traditional wheat-breeding programs. In addition, we investigated the effect of genetic correlation between different traits on genetic gain. A stochastic simulation was used to evaluate wheat-breeding programs that run simultaneously for 25 years with phenotypic or genomic selection. Genetic gain and genetic variance of wheat-breeding program based on phenotypes was compared to the one with genomic selection. Genetic gain from the wheat-breeding program based on genomic estimated breeding values (GEBVs) has tripled compared to phenotypic selection. Genomic selection is a promising strategy for improving genetic gain in wheat-breeding programs.

Multi-Year Dynamics of Single-Step Genomic Prediction in an Applied Wheat Breeding Program

The availability of cost-efficient genotyping technologies has facilitated the implementation of genomic selection into numerous breeding programs. However, some studies reported a superiority of pedigree over genomic selection in line breeding, and as, aside from systematic record keeping, no additional costs are incurring in pedigree-based prediction, the question about the actual benefit of fingerprinting several hundred lines each year might suggest itself. This study aimed thus on shedding some light on this question by comparing pedigree, genomic, and single-step prediction models using phenotypic and genotypic data that has been collected during a time period of ten years in an applied wheat breeding program. The mentioned models were for this purpose empirically tested in a multi-year forward prediction as well as a supporting simulation study. Given the availability of deep pedigree records, pedigree prediction performed similar to genomic prediction for some of the investigated traits if preexisting information of the selection candidates was available. Notwithstanding, blending both information sources increased the prediction accuracy and thus the selection gain substantially, especially for low heritable traits. Nevertheless, the largest advantage of genomic predictions can be seen for breeding scenarios where such preexisting information is not systemically available or difficult and costly to obtain.

Breeding Program Optimization for Genomic Selection in Winter Wheat

Developing methodologies in the fields of phenomics and genomic prediction have the potential to increase the production of crop species by accelerating germplasm improvement. The integration of these technologies into germplasm improvement and breeding programs requires evidence that there will be a direct economic benefit to the program. We determined a basic set of parameters, such as prediction accuracy greater than 0.3, the ability to genotype over 7 lines for the cost of one phenotypic evaluation, and heritability levels below 0.4, at which the use of genomic selection would be of economic benefit in terms of genetic gain and operational costs to the Kansas State University (KSU) winter wheat breeding program. The breeding program was then examined to determine whether the parameters benefitting genomic selection were observed or achievable in a practical sense. Our results show that the KSU winter wheat breeding program is at a decision point with regards to their primary means of selection. A few operational changes to increase prediction accuracy would place the program in the parameter space where genomic selection is expected to outpace the current phenotypic selection methodology at a parity of the operation cost and would be of greatest benefit to the program.