Performance prediction of crosses in plant breeding through genotype by environment interactions

Abstract

Performance prediction of potential crosses plays a significant role in plant breeding, which aims to produce new crop varieties that have higher yields, require fewer resources, and are more adaptable to the changing environments. In the 2020 Syngenta crop challenge, Syngenta challenged participants to predict the yield performance of a list of potential breeding crosses of inbreds and testers based on their historical yield data in different environments. They released a dataset that contained the observed yields for 294,128 corn hybrids through the crossing of 593 unique inbreds and 496 unique testers across multiple environments between 2016 and 2018. To address this challenge, we designed a new predictive approach that integrates random forest and an optimization model for G E interaction detection. Our computational experiment found that our approach achieved a relative root-mean-square-error (RMSE) of 0.0869 for the validation data, outperforming other state-of-the-art models such as factorization machine and extreme gradient boosting tree. Our model was also able to detect genotype by environment interactions that are potentially biologically insightful. This model won the first place in the 2020 Syngenta crop challenge in analytics.

Evaluación de híbridos F1 de chile (Capsicum annuum) provenientes de cruces entre parentales enfocados en obtener variedades tipo “Blocky o Bell Pepper”

“…Por esta razón un progenitor se elige casi siempre por su comportamiento comprobado en las zonas en las cuales se va a cultivar y el otro porque complementa algún defecto específico del primero (Vallejo y Estrada, 2006). Además, los progenitores deben tener promedios altos en el carácter de interés y se desea que su origen genético sea muy distante para aprovechar al máximo el valor heterótico o la segregación transgresiva (Ansarifar et al, 2020). Cuando el componente genético aditivo es el más importante, el promedio general es un buen indicativo para la producción de líneas buenas en generaciones avanzadas.…”

Metabolomics-Guided Elucidation of Plant Abiotic Stress Responses in the 4IR Era: An Overview

“…In omics sciences, RF has aided in extracting biological insights by detecting genotype from environment interactions [183]. RFs are, however, relatively new to metabolomics studies and are proving to be powerful classifiers due to their high classification accuracy, ability to determine the variable/feature importance (i.e., identifying variables that contribute to the prediction results) (Figure 3), avoidance of overfitting and tolerance to outliers and missing values [184][185][186].…”

Ready, Steady, Go AI: A practical tutorial on fundamentals of artificial intelligence and its applications in phenomics image analysis

“…The remarkable flexibility and adaptability of EL helped the proliferation of its application in plant phenotyping where it has been used for various tasks, including biotic stress identification and classification, 65 , 66 aboveground biomass estimation, 67 , 68 and performance prediction of crosses in breeding. 69 , 70 …”