Grape cultivation has long been a meticulous process, typically requiring three years for a seed to germinate and bear fruit. Developing an exceptional grape variety can take even longer, posing significant challenges for farmers and breeders alike. However, a groundbreaking approach by Chinese scientists is set to transform this traditional practice.
A research team led by Zhou Yongfeng from the Agricultural Genomics Institute at Shenzhen of the Chinese Academy of Agricultural Sciences has unveiled a novel method of grape breeding that leverages artificial intelligence (AI). This innovative technique significantly shortens the breeding cycle and boasts a high prediction accuracy of 85 percent, effectively quadrupling the efficiency of traditional breeding methods.
Published on Monday in the prestigious journal Nature Genetics, the study highlights the team’s journey towards precise grape breeding. Since 2015, Zhou's team has been dedicated to grape design and breeding, achieving a major milestone in 2023 with the release of the first complete grape genome map. Building on this success, they have developed Grapepan v1.0, the first comprehensive grape pan-genome.
To deepen their understanding of the relationship between grape genes and traits, the team meticulously selected over 400 representative varieties from nearly 10,000 types of grapes. Over two years, they examined 29 agronomic traits, including cluster size, berry metabolite content, berry size, and fruit skin color, resulting in the creation of detailed genetic and trait maps for grapes.
The integration of machine learning into their research was a game-changer. By developing a predictive model, the team can now make early predictions and selections based on scoring, thereby guiding and optimizing breeding strategies. This model enables breeders to quickly and accurately assess the genetic potential of numerous breeding materials, facilitating the selection of superior varieties. Additionally, it allows for the early identification and removal of unsuitable seedlings, thereby reducing unnecessary labor and investment costs.
Zhou Yongfeng emphasized the significance of this research, stating, \"This research is expected to achieve precise breeding design for grapes, accelerate grape variety innovation, and provide a reference for breeding other perennial crops.\" The innovative breeding technology has already garnered recognition, with six national invention patents approved and one international patent applied for.
Reference(s):
Chinese scientists use AI to accelerate precise grape breeding
cgtn.com
