Computomics receives BMEL project grant

Collaborative project: An AI-based, resource-efficient approach using multiple genomic and phenotypic data to introduce novel alleles into barley breeding - TP MLU (HEB-KI) - subproject B

The importance of artificial intelligence (AI) and genomics has increased dramatically in recent years and is increasingly being applied in many forms to agriculture as well. This includes the breeding of barley, one of the world's most important cereals. The European Union (EU) accounts for about 40% of global barley production (which is about 60 million tons per year). Advances in high-throughput sequencing have made it possible not only to access elite varieties by molecular genetics, but also to decipher the genetic potential of wild barley and make it accessible for breeding. Crossing wild barley varieties with elite lines is seen as an important way to breed cultivars with improved traits, especially in terms of drought resistance, making varieties ready for climate change, and thus to expand the greatly reduced diversity in the gene pool of elite cultivars caused by domestication and breeding.

Using artificial intelligence, high-throughput sequencing and the speed-breeding concept, the establishment of a wild barley population HEX-35 ('Halle extended exotic barley') including molecular genetic and initial phenotypic analysis is aimed to be achieved within only 3 years. HEX-35 is an extension of HEB-25, a barley population derived from crosses between wild barley and the spring barley variety Barke, and will add a total of 600 lines, which will be selected for maximum genetic diversity using AI. In the future, AI selection will allow HEX-35 to be studied extremely resource-efficiently in the field at multiple sites in parallel, to record plant development in phenotyping systems under controlled conditions, and to transfer the results to the entire population. HEX-35 is being developed with the goal of additionally increasing genetic diversity for breeding using additional wild barley accessions to provide improved resources for changing climatic challenges. This is a goal that, just a few years ago, would have taken far longer and required many times the financial outlay. Plant breeding in the fast lane!

• Project name: HEB-KI — an AI-based, resource-efficient approach using multiple genome and phenome datasets to introduce novel alleles into barley breeding.
• Goal: Accelerate variety development through more resource-efficient plant breeding with AI and genomics.
• Approach: improved breeding decisions through the use of AI models.
• Main location: Halle (Saale), Saxony-Anhalt
• Project coordination: Martin Luther University Halle-Wittenberg, Institute of Agricultural and Food Sciences
• Project participants: Martin Luther University Halle-Wittenberg, Computomics GmbH
  
  

The collaborative project is funded by the German Federal Ministry of Food and Agriculture (BMEL), supervised by the Federal Agency for Agriculture and Food (BLE/ptble).

More information: HEB-KI project description and practice report by the German Federal Ministry of Food and Agriculture (BMEL)