Multi-Trait Genomic Selection Modeling for Correlated Phenotype Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current genomic selection models primarily focus on predicting a single trait, ignoring genetic and environmental correlations between multiple traits, leading to limited prediction accuracy and increased computational burden with additional auxiliary traits.
Innovation Solution
A method is developed to construct a genomic selection model based on multi-trait phenotyping modeling, combining machine learning models with genomic selection to capture linear or nonlinear relationships between traits, utilizing multi-trait phenotypic data for improved prediction accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If single-trait genomic selection models are used, then the model complexity is low and computational requirements are reduced, but the prediction accuracy is limited due to ignoring genetic and environmental correlations between multiple traits
Solution Approach 1:
The patent combines multiple single-trait genomic selection models into a unified multi-trait phenotyping model that simultaneously analyzes multiple traits. This merging approach captures genetic and environmental correlations between traits, improving prediction accuracy while managing model complexity through integrated analysis framework
Solution Approach 2:
The patent creates a composite modeling approach by integrating phenotypic data from multiple traits with genomic information. This composite model structure allows simultaneous consideration of multiple traits and their correlations, enhancing predictive power without requiring excessively complex individual trait models
2Measurement precision
If multiple auxiliary traits are added to improve prediction accuracy, then the prediction accuracy improves, but the computational burden increases significantly
Solution Approach 1:
The patent develops a universal multi-trait phenotyping model that serves multiple functions simultaneously: it analyzes multiple traits, captures genetic correlations, captures environmental correlations, and provides predictions for all traits within a single computational framework. This multi-functionality reduces the need for separate analyses and lowers overall computational burden
Solution Approach 2:
The patent transforms the computational approach by changing parameters from separate single-trait analyses to integrated multi-trait analysis. This parameter change allows the model to utilize correlations between traits efficiently, improving prediction accuracy while reducing redundant computations that would occur with multiple separate models
3Adaptability or versatility
If selection index-based auxiliary prediction is used, then the genetic correlation between traits is utilized for joint selection, but the prediction effect is limited for high heritability traits and requires strict selection of auxiliary traits
Solution Approach 1:
The patent implements a dynamic multi-trait phenotyping model that adaptively captures both genetic and environmental correlations between traits. Unlike static selection index methods, this dynamic model can adjust to different trait combinations and correlation structures, providing improved prediction accuracy across various heritability levels without strict requirements for auxiliary trait selection
Data Source
AI summary
A method and system for constructing a genomic selection model based on a multi-trait phenotypic model are provided, the multi-trait model founded on phenotypic data, a predicted value or an estimated breeding value obtained by the genomic selection model is used as input data of a machine learning phenotypic prediction model to predict a final phenotypic value for line selection; a multi-trait machine learning phenotypic model is established to capture a linear or non-linear relationship between plant phenotypic traits, and on this basis, a predicted value and an estimated breeding value of each trait are obtained by combining it with the genomic selection model. The method enhances the prediction accuracy of target traits and accelerates the breeding process, improves the selection efficiency of the target traits and saves breeding costs, which is widely employed in the field of agricultural animal and plant breeding.