Plant Breeding Cross Selection Using Population Prediction Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In plant breeding, it is challenging to accurately determine the best parents to cross when selecting breeding starts, especially with a large number of options available, as not all crosses guarantee the desired traits and commercial success.
Innovation Solution
The system and method for identifying plant crosses in plant breeding involve selecting parents based on predicted commercial value, relatedness, and risks associated with potential crosses, using a breeding engine that accesses a crosses data structure to generate population prediction scores and filter crosses based on predetermined rules and thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional selective breeding methods are used to identify parent plants, then breeding decisions can be made based on plant characteristics, but the process becomes inefficient when dealing with large numbers of potential crosses
Solution Approach 1:
A computing device acts as an intermediary between breeders and the large number of potential crosses. The system uses population prediction scores generated by the computing device to objectively evaluate and rank potential crosses, replacing traditional manual assessment methods and enabling efficient handling of large cross populations.
Solution Approach 2:
The patent replaces manual mechanical selection processes with automated computational systems. The computing device calculates population prediction scores based on historical data and genetic information, substituting human judgment with algorithmic analysis to identify the most promising crosses efficiently.
2Reliability
If all potential crosses are tested to ensure desired traits are inherited, then trait accuracy is maximized, but the time and resources required increase significantly
Solution Approach 1:
The system performs preliminary evaluation of potential crosses by calculating population prediction scores before actual breeding occurs. This preliminary action uses historical performance data and genetic information to predict which crosses are most likely to succeed, allowing breeders to focus resources on the most promising candidates and avoid testing unlikely crosses.
Solution Approach 2:
Instead of testing all potential crosses equally, the patent applies partial action by focusing testing resources on crosses with the highest population prediction scores. The system identifies a subset of top-ranked crosses for detailed evaluation, reducing the overall number of crosses that need full testing while maintaining high confidence in trait inheritance.
3Reliability
If a large number of crosses are pursued to increase commercial success probability, then the likelihood of finding viable products improves, but the cost and complexity of the breeding program increases
Solution Approach 1:
The patent changes the parameter of cross evaluation by introducing population prediction scores as a new metric. This parameter transformation allows the system to objectively compare crosses based on predicted commercial performance rather than relying on traditional subjective assessments, enabling more efficient resource allocation across multiple potential crosses.
Data Source
AI summary
Exemplary methods for use in identifying crosses for use in plant breeding are disclosed. One exemplary method includes generating population prediction scores for each potential cross within a set of potential crosses, where each population prediction score is associated with a prediction of commercial success for the associated potential cross within the set of potential crosses. The method also includes selecting a subgroup of potential crosses, based on thresholds associated with the population prediction scores for the set of potential crosses. The exemplary method further includes selecting multiple target crosses from the subgroup of potential crosses based on a genetic relatedness of the parents in the subgroup of potential crosses, and directing ones of the selected target crosses into a breeding pipeline, thereby providing crosses to the breeding pipeline based, at least in part, on commercial success of parents included in the selected ones of the filtered crosses.