Soybean Dicamba Tolerance via Machine Learning GWAS Marker Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Soybean varieties lack genetic markers associated with dicamba tolerance, leading to yield losses due to off-target dicamba exposure, with existing methods failing to identify genomic regions or markers linked to dicamba sensitivity.
Innovation Solution
Identification and utilization of specific molecular markers such as ss715635349, ss715605561, and ss715632413, along with machine learning-based GWAS pipelines, to select soybean plants with increased dicamba tolerance by detecting favorable alleles associated with dicamba detoxification and transport mechanisms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional GWAS methods are used to identify genomic regions, then the process is time-consuming and lacks precision, but machine learning-based GWAS pipelines improve identification accuracy and speed
Solution Approach 1:
The patent replaces traditional statistical-based GWAS methods with machine learning algorithms (random forest, support vector machines, neural networks) to identify marker-trait associations. This substitution of analytical methodology enables more accurate prediction of dicamba tolerance while handling high-dimensional genomic data more efficiently, directly resolving the contradiction between identification accuracy and methodological complexity.
2Reliability
If soybean varieties are exposed to off-target dicamba, then yield losses occur due to lack of tolerance, but developing tolerant varieties requires identification of unknown genomic regions and markers
Solution Approach 1:
The patent performs preliminary identification and validation of genomic regions and molecular markers associated with dicamba tolerance before widespread cultivation. By conducting comprehensive GWAS studies and validating markers in multiple environments, the research establishes a foundation of known genetic determinants that can be used for marker-assisted selection, eliminating the information gap that previously prevented development of tolerant varieties.
Solution Approach 2:
The patent introduces molecular markers (SNPs, SSRs, InDels) as intermediary tools that bridge the gap between genomic information and phenotypic expression of dicamba tolerance. These markers serve as detectable proxies for tolerance traits, enabling indirect selection of tolerant plants without requiring direct exposure testing, thus resolving the information deficiency problem.
3Object-affected harmful factors
If dicamba is applied to control weeds, then weed control effectiveness is achieved, but off-target movement causes damage to non-DT soybean and other dicot plants
Solution Approach 1:
The patent identifies specific genomic regions and molecular markers that confer localized tolerance to dicamba in soybean plants. By enabling selection of plants with these specific genetic characteristics, the technology creates a population with heterogeneous tolerance properties, allowing farmers to plant varieties that are locally adapted and resistant to off-target dicamba damage, thereby protecting yield in contaminated environments.
Data Source
AI summary
Markers associated with increased dicamba tolerance in soybeans are provided herein. Also provided are methods to identify plants having said markers and breeding methods to introduce said markers into other soybean plants, as well as methods for producing soybean plants having increased dicamba tolerance.