Skip to main content
ARS Home » Pacific West Area » Pullman, Washington » WHGQ » Research » Publications at this Location » Publication #398785

Research Project: Genetic Improvement of Wheat and Barley for Environmental Resilience, Disease Resistance, and End-use Quality

Location: Wheat Health, Genetics, and Quality Research

Title: Machine learning for predicting phenotype from genotype and environment

item GUO, TINGTING - Huazhong Agricultural University
item Li, Xianran

Submitted to: Current Opinion in Biotechnology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 11/11/2022
Publication Date: 2/1/2023
Citation: Guo, T., Li, X. 2023. Machine learning for predicting phenotype from genotype and environment. Current Opinion in Biotechnology. 79. Article 102853.

Interpretive Summary: Prediction of crop phenotype, which is determined by genetic markup and environmental conditions, is critically needed to mitigate impact of changing climatic conditions. Research in other disciplines suggested the great potential of machine learning in developing predictive models for crop phenotype. This article review the progress and challenges on applications of machine learning in three interconnected scenarios, based on genotypic information, environmental information, and then both. The future direction of predicting pan-phenome with information of pan-genome and pan-envirome is also discussed.

Technical Abstract: Predicting phenotypes with genomic and environmental information is critically needed but challenging. Machine learning methods have emerged as powerful tools to make accurate predictions from large and complex biological data. Here, we review the progress of phenotype prediction models, enabled or improved by machine learning methods. We categorized the phenotype prediction models into three scenarios: prediction with genotypic information, with environmental information, and with both. In each scenario, we illustrate the practicality of prediction models, the advantages of machine learning, and the challenges of modeling complex relationships. We discuss the promise of leveraging machine learning and genetics theories to develop models that can predict phenotype and also interpret the biological consequences of changes in genotype and environment.