Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits
Introduction: Predicting the performance (yield or other integrative traits) of cultivated plants is complex because it involves not only estimating the genetic value of the candidates to selection, the interactions between the genotype and the environment (GxE) but also the epistatic interactions between genomic regions for a given trait, and the interactions between the traits contributing to the integrative trait. Classical Genomic Prediction (GP) models mostly account for additive effects and are not suitable to estimate non-additive effects such as epistasis. Therefore, the use of machine learning and deep learning methods has been previously proposed to model those non-linear effects. Methods: In this study, we propose a type of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN) and compare it to two classical GP regression methods for their ability to predict an integrative trait of sorghum: aboveground fresh weight accumulation. We also suggest that the use of a crop growth model (CGM) can enhance predictions of integrative traits by decomposing them into more heritable intermediate traits. Results: The results show that CNN outperformed both LASSO and Bayes C methods in accuracy, suggesting that CNN are better suited to predict integrative traits. Furthermore, the predictive ability of the combined CGM-GP approach surpassed that of GP without the CGM integration, irrespective of the regression method used. Discussion: These results are consistent with recent works aiming to develop Genome-to-Phenotype models and advocate for the use of non-linear prediction methods, and the use of combined CGM-GP to enhance the prediction of crop performances.
id |
dig-cirad-fr-610090 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-6100902024-08-05T13:50:16Z http://agritrop.cirad.fr/610090/ http://agritrop.cirad.fr/610090/ Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits. Larue Florian, Rouan Lauriane, Pot David, Rami Jean-François, Luquet Delphine, Beurier Grégory. 2024. Frontiers in Plant Science, 15:1393965, 13 p.https://doi.org/10.3389/fpls.2024.1393965 <https://doi.org/10.3389/fpls.2024.1393965> Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits Larue, Florian Rouan, Lauriane Pot, David Rami, Jean-François Luquet, Delphine Beurier, Grégory eng 2024 Frontiers in Plant Science F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 Introduction: Predicting the performance (yield or other integrative traits) of cultivated plants is complex because it involves not only estimating the genetic value of the candidates to selection, the interactions between the genotype and the environment (GxE) but also the epistatic interactions between genomic regions for a given trait, and the interactions between the traits contributing to the integrative trait. Classical Genomic Prediction (GP) models mostly account for additive effects and are not suitable to estimate non-additive effects such as epistasis. Therefore, the use of machine learning and deep learning methods has been previously proposed to model those non-linear effects. Methods: In this study, we propose a type of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN) and compare it to two classical GP regression methods for their ability to predict an integrative trait of sorghum: aboveground fresh weight accumulation. We also suggest that the use of a crop growth model (CGM) can enhance predictions of integrative traits by decomposing them into more heritable intermediate traits. Results: The results show that CNN outperformed both LASSO and Bayes C methods in accuracy, suggesting that CNN are better suited to predict integrative traits. Furthermore, the predictive ability of the combined CGM-GP approach surpassed that of GP without the CGM integration, irrespective of the regression method used. Discussion: These results are consistent with recent works aiming to develop Genome-to-Phenotype models and advocate for the use of non-linear prediction methods, and the use of combined CGM-GP to enhance the prediction of crop performances. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/610090/1/fpls-15-1393965.pdf text cc_by info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ https://doi.org/10.3389/fpls.2024.1393965 10.3389/fpls.2024.1393965 info:eu-repo/semantics/altIdentifier/doi/10.3389/fpls.2024.1393965 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.3389/fpls.2024.1393965 info:eu-repo/semantics/reference/purl/https://github.com/GBeurier/GenomicPrediction_Frontier info:eu-repo/grantAgreement///ANR-11-BTBR-0006//(FRA) Biomasse pour le futur/BFF |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 |
spellingShingle |
F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 Larue, Florian Rouan, Lauriane Pot, David Rami, Jean-François Luquet, Delphine Beurier, Grégory Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
description |
Introduction: Predicting the performance (yield or other integrative traits) of cultivated plants is complex because it involves not only estimating the genetic value of the candidates to selection, the interactions between the genotype and the environment (GxE) but also the epistatic interactions between genomic regions for a given trait, and the interactions between the traits contributing to the integrative trait. Classical Genomic Prediction (GP) models mostly account for additive effects and are not suitable to estimate non-additive effects such as epistasis. Therefore, the use of machine learning and deep learning methods has been previously proposed to model those non-linear effects. Methods: In this study, we propose a type of Artificial Neural Network (ANN) called Convolutional Neural Network (CNN) and compare it to two classical GP regression methods for their ability to predict an integrative trait of sorghum: aboveground fresh weight accumulation. We also suggest that the use of a crop growth model (CGM) can enhance predictions of integrative traits by decomposing them into more heritable intermediate traits. Results: The results show that CNN outperformed both LASSO and Bayes C methods in accuracy, suggesting that CNN are better suited to predict integrative traits. Furthermore, the predictive ability of the combined CGM-GP approach surpassed that of GP without the CGM integration, irrespective of the regression method used. Discussion: These results are consistent with recent works aiming to develop Genome-to-Phenotype models and advocate for the use of non-linear prediction methods, and the use of combined CGM-GP to enhance the prediction of crop performances. |
format |
article |
topic_facet |
F30 - Génétique et amélioration des plantes U10 - Informatique, mathématiques et statistiques modélisation des cultures génotype modèle mathématique rendement des cultures réseau de neurones adaptation aux changements climatiques prévision de rendement méthode statistique génétique intégrative technique de prévision apprentissage machine génomique http://aims.fao.org/aos/agrovoc/c_9000024 http://aims.fao.org/aos/agrovoc/c_3225 http://aims.fao.org/aos/agrovoc/c_24199 http://aims.fao.org/aos/agrovoc/c_10176 http://aims.fao.org/aos/agrovoc/c_37467 http://aims.fao.org/aos/agrovoc/c_1374567058134 http://aims.fao.org/aos/agrovoc/c_8486 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_331345 http://aims.fao.org/aos/agrovoc/c_3041 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_92382 |
author |
Larue, Florian Rouan, Lauriane Pot, David Rami, Jean-François Luquet, Delphine Beurier, Grégory |
author_facet |
Larue, Florian Rouan, Lauriane Pot, David Rami, Jean-François Luquet, Delphine Beurier, Grégory |
author_sort |
Larue, Florian |
title |
Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
title_short |
Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
title_full |
Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
title_fullStr |
Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
title_full_unstemmed |
Linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
title_sort |
linking genetic markers and crop model parameters using neural networks to enhance genomic prediction of integrative traits |
url |
http://agritrop.cirad.fr/610090/ http://agritrop.cirad.fr/610090/1/fpls-15-1393965.pdf |
work_keys_str_mv |
AT larueflorian linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits AT rouanlauriane linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits AT potdavid linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits AT ramijeanfrancois linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits AT luquetdelphine linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits AT beuriergregory linkinggeneticmarkersandcropmodelparametersusingneuralnetworkstoenhancegenomicpredictionofintegrativetraits |
_version_ |
1807170510030635008 |