our abilities to solve critical, and technically challenging, problems. Data availability All data used in this manuscript are publicly available at https:// doi.org/10.25739/tq5e-ak26. Code from all teams is publicly avail able as follows: AgAdaptAR: https://github.com/EcoEvoInfo/maize-gxe-pre diction-challenge-2023 AIMaize: https://github.com/ksegaba/Genomes2Field_Competition All Models are Wrong: https://zenodo.org/record/7830071 arulrich: https://github.com/mwylerCH/GxEcompetition CLAC: https://github.com/alenxav/Lectures/tree/master/MGC_2023 DataJanitors: https://github.com/qchen33/g2fcompetition2022 DeepCropVision: https://github.com/Ved-Piyush/DeepCrop Vision_maizegxeprediction2022 E
Open resource ↗ksegaba/Genomes2Field_Competition · pdf-raw-page:13 lines:1-91Unverified paper record
Global genotype by environment prediction competition reveals that diverse modeling strategies can deliver satisfactory maize yield estimates.
Genetics · 1 Feb 2025 · 10.1093/genetics/iyae195
Abstract
Predicting phenotypes from a combination of genetic and environmental factors is a grand challenge of modern biology. Slight improvements in this area have the potential to save lives, improve food and fuel security, permit better care of the planet, and create other positive outcomes. In 2022 and 2023, the first open-to-the-public Genomes to Fields initiative Genotype by Environment prediction competition was held using a large dataset including genomic variation, phenotype and weather measurements, and field management notes gathered by the project over 9 years. The competition attracted registrants from around the world with representation from academic, government, industry, and nonprofit institutions as well as unaffiliated. These participants came from diverse disciplines, including plant science, animal science, breeding, statistics, computational biology, and others. Some participants had no formal genetics or plant-related training, and some were just beginning their graduate education. The teams applied varied methods and strategies, providing a wealth of modeling knowledge based on a common dataset. The winner's strategy involved 2 models combining machine learning and traditional breeding tools: 1 model emphasized environment using features extracted by random forest, ridge regression, and least squares, and 1 focused on genetics. Other high-performing teams' methods included quantitative genetics, machine learning/deep learning, mechanistic models, and model ensembles. The dataset factors used, such as genetics, weather, and management data, were also diverse, demonstrating that no single model or strategy is far superior to all others within the context of this competition.
Plant phenotyping relevance
遺伝・環境情報からトウモロコシ収量という植物形質を予測するモデルを競争形式で比較・評価しており、計算的形質推定とベンチマークが中心である。
titleGlobal genotype by environment prediction competition reveals that diverse modeling strategies can deliver satisfactory maize yield estimates.
abstractThe teams applied varied methods and strategies, providing a wealth of modeling knowledge based on a common dataset.
abstractThe winner's strategy involved 2 models combining machine learning and traditional breeding tools
Code and data availability
The paper is the G2F maize G×E prediction competition report. Its curated phenotype/genotype/weather/EC dataset is public (DOI 10.25739/tq5e-ak26), but that DOI is not among the allowed URLs, so it cannot be listed. However, the authors explicitly state that code from all participating teams is publicly available, and
ta availability All data used in this manuscript are publicly available at https:// doi.org/10.25739/tq5e-ak26. Code from all teams is publicly avail able as follows: AgAdaptAR: https://github.com/EcoEvoInfo/maize-gxe-pre diction-challenge-2023 AIMaize: https://github.com/ksegaba/Genomes2Field_Competition All Models are Wrong: https://zenodo.org/record/7830071 arulrich: https://github.com/mwylerCH/GxEcompetition CLAC: https://github.com/alenxav/Lectures/tree/master/MGC_2023 DataJanitors: https://github.com/qchen33/g2fcompetition2022 DeepCropVision: https://github.com/Ved-Piyush/DeepCrop Vision_maizegxeprediction2022 EnBiSys: https://github.com/dperondi/maizegxeprediction2022 gartyboi
Open resource ↗pdf-raw-page:13 lines:1-91ript are publicly available at https:// doi.org/10.25739/tq5e-ak26. Code from all teams is publicly avail able as follows: AgAdaptAR: https://github.com/EcoEvoInfo/maize-gxe-pre diction-challenge-2023 AIMaize: https://github.com/ksegaba/Genomes2Field_Competition All Models are Wrong: https://zenodo.org/record/7830071 arulrich: https://github.com/mwylerCH/GxEcompetition CLAC: https://github.com/alenxav/Lectures/tree/master/MGC_2023 DataJanitors: https://github.com/qchen33/g2fcompetition2022 DeepCropVision: https://github.com/Ved-Piyush/DeepCrop Vision_maizegxeprediction2022 EnBiSys: https://github.com/dperondi/maizegxeprediction2022 gartybois: https://github.com/Thyra/g2f-maize-challenge-202
Open resource ↗mwylerCH/GxEcompetition · pdf-raw-page:13 lines:1-910.25739/tq5e-ak26. Code from all teams is publicly avail able as follows: AgAdaptAR: https://github.com/EcoEvoInfo/maize-gxe-pre diction-challenge-2023 AIMaize: https://github.com/ksegaba/Genomes2Field_Competition All Models are Wrong: https://zenodo.org/record/7830071 arulrich: https://github.com/mwylerCH/GxEcompetition CLAC: https://github.com/alenxav/Lectures/tree/master/MGC_2023 DataJanitors: https://github.com/qchen33/g2fcompetition2022 DeepCropVision: https://github.com/Ved-Piyush/DeepCrop Vision_maizegxeprediction2022 EnBiSys: https://github.com/dperondi/maizegxeprediction2022 gartybois: https://github.com/Thyra/g2f-maize-challenge-2022 Kernel of Truth: https://github.com/robertkhu/m
Open resource ↗alenxav/Lectures · pdf-raw-page:13 lines:1-91This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.