ML Project B: Identifying genetic contributors to crop stress tolerance in the presence of environmental effects

This tender consists of seven interrelated procurements. The applicant may apply for all seven Projects A-G, but successful applicants will only be contracted for Project A alone, any combination of Projects B-G, or all Projects B-G.

For full details, including links to relevant documents and information on any Questions and Answers, visit:

https://grdc.com.au/research/applying-and-reporting/current-procurement/open-tenders

Background:

Grains pre-breeding could be accelerated by unravelling the mechanisms underpinning complex quantitative crop traits e.g. pathogen resistance, yield potential in heat stress/frost-prone environments, and water productivity. Phenomics, genomics, transcriptomics, proteomics, and metabolomics studies of these phenomena are complicated by the dense and disparate nature of ‘omics’ data, rapid flux in observed signals, and environmental factors. Thus, linking complex traits to molecular mechanisms has been difficult – it is hoped machine learning (ML) can go beyond analyses of individual signals to identify systems-level, trait-associated, patterns (e.g. genomic selection markers) that can be used by plant breeders.

Application of ML could help the grains industry more-effectively:

• Understand genetic control of canola blackleg resistance

• Understand genetic and environmental factors leading to necrotrophic fungal pathogen resistance in wheat, barley, and/or canola

• Identify genetic contributors to improved wheat/barley yield under frost-prone conditions

• Identify genetic contributors to disease resistance in pulses

Evaluation Criteria, Outcomes and Outputs:

Applications must address the evaluation criteria, outcomes, and outputs relevant to the specific procurement being applied for.

For details visit:

https://grdc.com.au/research/applying-and-reporting/current-procurement/open-tenders