GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield
The expression of quantitative traits of a line of a crop depends on its genetics, the environment where it is sown and the interaction between the genetic information and the environment known as GxE. Thus to maximize food production, new varieties are developed by selecting superior lines of seeds...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
KeAi Communications Co., Ltd.
2023-06-01
|
Series: | Artificial Intelligence in Agriculture |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2589721723000168 |
_version_ | 1797791905828831232 |
---|---|
author | Sheikh Jubair Olivier Tremblay-Savard Mike Domaratzki |
author_facet | Sheikh Jubair Olivier Tremblay-Savard Mike Domaratzki |
author_sort | Sheikh Jubair |
collection | DOAJ |
description | The expression of quantitative traits of a line of a crop depends on its genetics, the environment where it is sown and the interaction between the genetic information and the environment known as GxE. Thus to maximize food production, new varieties are developed by selecting superior lines of seeds suitable for a specific environment. Genomic selection is a computational technique for developing a new variety that uses whole genome molecular markers to identify top lines of a crop. A large number of statistical and machine learning models are employed for single environment trials, where it is assumed that the environment does not have any effect on the quantitative traits. However, it is essential to consider both genomic and environmental data to develop a new variety, as these strong assumptions may lead to failing to select top lines for an environment. Here we devised three novel deep learning frameworks incorporating GxE within the deep learning model and predicted line-specific yield for an environment. In the process, we also developed a new technique for identifying environment-specific markers that can be useful in many applications of environment-specific genomic selection. The result demonstrates that our best framework obtains 1.75 to 1.95 times better correlation coefficients than other deep learning models that incorporate environmental data depending on the test scenario. Furthermore, the feature importance analysis shows that environmental information, followed by genomic information, is the driving factor in predicting environment-specific yield for a line. We also demonstrate a way to extend our framework for new data types, such as text or soil data. The extended model also shows the potential to be useful in genomic selection. |
first_indexed | 2024-03-13T02:25:28Z |
format | Article |
id | doaj.art-c5ba390e14ef4fa3b0f7d8870ffae016 |
institution | Directory Open Access Journal |
issn | 2589-7217 |
language | English |
last_indexed | 2024-03-13T02:25:28Z |
publishDate | 2023-06-01 |
publisher | KeAi Communications Co., Ltd. |
record_format | Article |
series | Artificial Intelligence in Agriculture |
spelling | doaj.art-c5ba390e14ef4fa3b0f7d8870ffae0162023-06-30T04:22:40ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172023-06-0186076GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yieldSheikh Jubair0Olivier Tremblay-Savard1Mike Domaratzki2Department of Computer Science, University of Manitoba, 66 Chancellors Cir, Winnipeg, MB, R3T 2N2, Canada; Corresponding author.Department of Computer Science, University of Manitoba, 66 Chancellors Cir, Winnipeg, MB, R3T 2N2, CanadaDepartment of Computer Science, University of Western Ontario, 1151 Richmond St, London, ON, N6A 3K7, CanadaThe expression of quantitative traits of a line of a crop depends on its genetics, the environment where it is sown and the interaction between the genetic information and the environment known as GxE. Thus to maximize food production, new varieties are developed by selecting superior lines of seeds suitable for a specific environment. Genomic selection is a computational technique for developing a new variety that uses whole genome molecular markers to identify top lines of a crop. A large number of statistical and machine learning models are employed for single environment trials, where it is assumed that the environment does not have any effect on the quantitative traits. However, it is essential to consider both genomic and environmental data to develop a new variety, as these strong assumptions may lead to failing to select top lines for an environment. Here we devised three novel deep learning frameworks incorporating GxE within the deep learning model and predicted line-specific yield for an environment. In the process, we also developed a new technique for identifying environment-specific markers that can be useful in many applications of environment-specific genomic selection. The result demonstrates that our best framework obtains 1.75 to 1.95 times better correlation coefficients than other deep learning models that incorporate environmental data depending on the test scenario. Furthermore, the feature importance analysis shows that environmental information, followed by genomic information, is the driving factor in predicting environment-specific yield for a line. We also demonstrate a way to extend our framework for new data types, such as text or soil data. The extended model also shows the potential to be useful in genomic selection.http://www.sciencedirect.com/science/article/pii/S2589721723000168Genomic predictionMulti-environment trialDeep learningGxEEnviromics |
spellingShingle | Sheikh Jubair Olivier Tremblay-Savard Mike Domaratzki GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield Artificial Intelligence in Agriculture Genomic prediction Multi-environment trial Deep learning GxE Enviromics |
title | GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield |
title_full | GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield |
title_fullStr | GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield |
title_full_unstemmed | GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield |
title_short | GxENet: Novel fully connected neural network based approaches to incorporate GxE for predicting wheat yield |
title_sort | gxenet novel fully connected neural network based approaches to incorporate gxe for predicting wheat yield |
topic | Genomic prediction Multi-environment trial Deep learning GxE Enviromics |
url | http://www.sciencedirect.com/science/article/pii/S2589721723000168 |
work_keys_str_mv | AT sheikhjubair gxenetnovelfullyconnectedneuralnetworkbasedapproachestoincorporategxeforpredictingwheatyield AT oliviertremblaysavard gxenetnovelfullyconnectedneuralnetworkbasedapproachestoincorporategxeforpredictingwheatyield AT mikedomaratzki gxenetnovelfullyconnectedneuralnetworkbasedapproachestoincorporategxeforpredictingwheatyield |