Cargando…

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

SIMPLE SUMMARY: Wheat (Triticum aestivum L.) breeding programs mainly focus on improving grain yield, biotic and abiotic stress tolerance, and end-use quality traits. End-use quality and processing traits are the combinations of various predefined parameters. Genomic selection (GS) opens the potenti...

Descripción completa

Detalles Bibliográficos
Autores principales: Sandhu, Karansher Singh, Aoun, Meriem, Morris, Craig F., Carter, Arron H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8301459/
https://www.ncbi.nlm.nih.gov/pubmed/34356544
http://dx.doi.org/10.3390/biology10070689
_version_ 1783726674771181568
author Sandhu, Karansher Singh
Aoun, Meriem
Morris, Craig F.
Carter, Arron H.
author_facet Sandhu, Karansher Singh
Aoun, Meriem
Morris, Craig F.
Carter, Arron H.
author_sort Sandhu, Karansher Singh
collection PubMed
description SIMPLE SUMMARY: Wheat (Triticum aestivum L.) breeding programs mainly focus on improving grain yield, biotic and abiotic stress tolerance, and end-use quality traits. End-use quality and processing traits are the combinations of various predefined parameters. Genomic selection (GS) opens the potential for selecting improved end-use quality lines. This study explored the potential of the machine and deep learning-based GS models for predicting end-use quality traits in wheat. Deep models were superior to traditional statistical and Bayesian models under all the 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 trails. ABSTRACT: 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. Genomic selection provides an alternative to predict performance using genome-wide markers under forward and across location predictions, where a previous year’s dataset can be used to build the models. 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 were 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 trails. Furthermore, the superior performance of machine and deep learning models strengthens the idea to include them in large scale breeding programs for predicting complex traits.
format Online
Article
Text
id pubmed-8301459
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83014592021-07-24 Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models Sandhu, Karansher Singh Aoun, Meriem Morris, Craig F. Carter, Arron H. Biology (Basel) Article SIMPLE SUMMARY: Wheat (Triticum aestivum L.) breeding programs mainly focus on improving grain yield, biotic and abiotic stress tolerance, and end-use quality traits. End-use quality and processing traits are the combinations of various predefined parameters. Genomic selection (GS) opens the potential for selecting improved end-use quality lines. This study explored the potential of the machine and deep learning-based GS models for predicting end-use quality traits in wheat. Deep models were superior to traditional statistical and Bayesian models under all the 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 trails. ABSTRACT: 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. Genomic selection provides an alternative to predict performance using genome-wide markers under forward and across location predictions, where a previous year’s dataset can be used to build the models. 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 were 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 trails. Furthermore, the superior performance of machine and deep learning models strengthens the idea to include them in large scale breeding programs for predicting complex traits. MDPI 2021-07-20 /pmc/articles/PMC8301459/ /pubmed/34356544 http://dx.doi.org/10.3390/biology10070689 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sandhu, Karansher Singh
Aoun, Meriem
Morris, Craig F.
Carter, Arron H.
Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title_full Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title_fullStr Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title_full_unstemmed Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title_short Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models
title_sort genomic selection for end-use quality and processing traits in soft white winter wheat breeding program with machine and deep learning models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8301459/
https://www.ncbi.nlm.nih.gov/pubmed/34356544
http://dx.doi.org/10.3390/biology10070689
work_keys_str_mv AT sandhukaranshersingh genomicselectionforendusequalityandprocessingtraitsinsoftwhitewinterwheatbreedingprogramwithmachineanddeeplearningmodels
AT aounmeriem genomicselectionforendusequalityandprocessingtraitsinsoftwhitewinterwheatbreedingprogramwithmachineanddeeplearningmodels
AT morriscraigf genomicselectionforendusequalityandprocessingtraitsinsoftwhitewinterwheatbreedingprogramwithmachineanddeeplearningmodels
AT carterarronh genomicselectionforendusequalityandprocessingtraitsinsoftwhitewinterwheatbreedingprogramwithmachineanddeeplearningmodels