Washburn Jacob D, Varela José Ignacio, Xavier Alencar, Chen Qiuyue, Ertl David, Gage Joseph L, Holland James B, Lima Dayane Cristina, Romay Maria Cinta, Lopez-Cruz Marco, de Los Campos Gustavo, Barber Wesley, Zimmer Cristiano, Trucillo Silva Ignacio, Rocha Fabiani, Rincent Renaud, Ali Baber, Hu Haixiao, Runcie Daniel E, Gusev Kirill, Slabodkin Andrei, Bax Phillip, Aubert Julie, Gangloff Hugo, Mary-Huard Tristan, Vanrenterghem Theodore, Quesada-Traver Carles, Yates Steven, Ariza-Suárez Daniel, Ulrich Argeo, Wyler Michele, Kick Daniel R, Bellis Emily S, Causey Jason L, Soriano Chavez Emilio, Wang Yixing, Piyush Ved, Fernando Gayara D, Hu Robert K, Kumar Rachit, Timon Annan J, Venkatesh Rasika, Segura Abá Kenia, Chen Huan, Ranaweera Thilanka, Shiu Shin-Han, Wang Peiran, Gordon Max J, Amos B Kirtley, Busato Sebastiano, Perondi Daniel, Gogna Abhishek, Psaroudakis Dennis, Chen Chun-Peng James, Al-Mamun Hawlader A, Danilevicz Monica F, Upadhyaya Shriprabha R, Edwards David, de Leon Natalia
USDA-ARS, MWA-PGRU, 302-A Curtis Hall, University of Missouri, Columbia, MO 65211, USA.
Department of Plant and Agroecosystem Sciences, University of Wisconsin-Madison, 1575 Linden Drive, Madison, WI 53706, USA.
Genetics. 2025 Feb 5;229(2). doi: 10.1093/genetics/iyae195.
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.
从遗传和环境因素的组合中预测表型是现代生物学的一项重大挑战。这一领域的微小改进都有可能挽救生命、改善粮食和燃料安全、更好地保护地球并创造其他积极成果。在2022年和2023年，首次面向公众的“从基因组到田间”倡议环境基因型预测竞赛举行，该竞赛使用了一个大型数据集，其中包括项目在9年时间里收集的基因组变异、表型和气象测量数据以及田间管理记录。该竞赛吸引了来自世界各地的注册者，他们来自学术、政府、行业和非营利机构以及无所属机构。这些参与者来自不同学科，包括植物科学、动物科学、育种、统计学、计算生物学等。一些参与者没有接受过正规的遗传学或植物相关培训，还有一些人刚刚开始研究生学习。各团队应用了不同的方法和策略，基于一个共同的数据集提供了丰富的建模知识。获胜者的策略涉及将机器学习和传统育种工具相结合的2个模型：一个模型利用随机森林、岭回归和最小二乘法提取的特征强调环境，另一个则侧重于遗传学。其他表现出色的团队的方法包括数量遗传学、机器学习/深度学习、机理模型和模型集成。所使用的数据集因素，如遗传学、天气和管理数据，也各不相同，这表明在本次竞赛的背景下，没有单一的模型或策略远远优于所有其他模型或策略。
