Larue Florian, Rouan Lauriane, Pot David, Rami Jean-François, Luquet Delphine, Beurier Grégory
Centre de Coopération Internationale en Recherche Agronomique pour le Développement (CIRAD), Unité Mixte de Recherche, Institut Amélioration Génétique et Adaptation des Plantes méditerranéennes et Tropicales (UMR AGAP), Montpellier, France.
Unité Mixte de Recherche, Institut Amélioration Génétique et Adaptation des Plantes méditerranéennes et Tropicales (UMR AGAP), Université Montpellier, Centre de Coopération Internationale en Recherche Agronomique pour le Développement (CIRAD), Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (INRA), Institut Agro, Montpellier, France.
Front Plant Sci. 2024 Jul 30;15:1393965. doi: 10.3389/fpls.2024.1393965. eCollection 2024.
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.
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.
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.
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.
预测栽培植物的性能（产量或其他综合性状）很复杂，因为这不仅涉及估计候选选择对象的遗传价值、基因型与环境之间的相互作用（GxE），还涉及给定性状的基因组区域之间的上位性相互作用，以及构成综合性状的各个性状之间的相互作用。经典基因组预测（GP）模型大多考虑加性效应，不适用于估计上位性等非加性效应。因此，此前有人提出使用机器学习和深度学习方法来对这些非线性效应进行建模。
在本研究中，我们提出了一种名为卷积神经网络（CNN）的人工神经网络（ANN）类型，并将其与两种经典的GP回归方法进行比较，以评估它们预测高粱综合性状地上鲜重积累的能力。我们还提出，使用作物生长模型（CGM）可以通过将综合性状分解为更具遗传性的中间性状来提高对综合性状的预测。
结果表明，在预测准确性方面，CNN优于LASSO和贝叶斯C方法，这表明CNN更适合预测综合性状。此外，无论使用何种回归方法，CGM-GP组合方法的预测能力都超过了未整合CGM的GP方法。
这些结果与近期旨在开发从基因组到表型模型的研究一致，支持使用非线性预测方法，以及使用CGM-GP组合方法来提高作物性能的预测。
