Selection-aware metrics provide complementary decision-level information in plant genomic prediction
- 1Frontiers Science Center for Molecular Design Breeding, State Key Laboratory of Maize Bio-Breeding, National Maize Improvement Center, College of Agronomy and Biotechnology, China Agricultural University , ,
Abstract
Breeding programs increasingly need prediction systems that support reliable candidate selection across heterogeneous environments, which makes cross-environment genomic prediction an important component of multienvironment crop improvement. However, model evaluation still relies heavily on Pearson’s correlation coefficient ( r ), a global summary that may not fully capture which top-ranked candidates would be advanced. Using maize and switchgrass datasets as focused case studies, we compared global predictive ability with phenotype-referenced candidate diagnostics across within-environment and directed cross-environment evaluations of rrBLUP/ridge, Light Gradient Boosting Machine (LightGBM), a multilayer perceptron, and mixed-effect deep neural network (MeNet). Rather than proposing a new selection metric, we used a conditional comparison framework that distinguishes nominal metric reversal from strict decision-level discordance among models with similar Pearson’s r . The r -best and candidate-metric-best models disagreed in 25%–55% of evaluation contexts, but large differences in candidate metrics among near- r models (|Δ r | ≤ 0.02) were uncommon. Nevertheless, models with nearly identical r did not always prioritize the same candidates: LightGBM and rrBLUP/ridge shared, on average, 72.9% of the top 5% candidates in maize and 68.8% in switchgrass. These results indicate that Pearson’s r remains informative for broad model comparison but does not fully describe decision-level behavior. Phenotype-referenced candidate diagnostics are therefore best used as targeted complements when models have similar predictive ability, selection intensity is high, or candidate identity is consequential across environments.
Related
- EnsPlex: Integrative Protein Complex Prediction through Multi-source Complementary Structural Sampling and Topology-Aware Candidate Selection
- A unified decision framework combines phenotypic and genomic information for nonlinear selection in plant breeding
- Integrating complementary biological information for multi-objective enzyme engineering
- Cell-level integration of gene expression and B cell receptor data captures complementary B cell information
- RAxML-NG 2: Automatic model selection, novel tree search heuristics, and fast branch support metrics
BibTeX
@article{wang2026selectionaware,
title = {{Selection-aware metrics provide complementary decision-level information in plant genomic prediction}},
author = {Xueyang Wang and Jun Yan},
journal = {Frontiers in plant science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1951182},
url = {https://europepmc.org/article/PMC/PMC13668517},
note = {CC BY},
}
RIS
TY - JOUR
TI - Selection-aware metrics provide complementary decision-level information in plant genomic prediction
AU - Xueyang Wang
AU - Jun Yan
PY - 2026
DA - 2026/10/01
JO - Frontiers in plant science
DO - 10.3389/fpls.2026.1951182
UR - https://europepmc.org/article/PMC/PMC13668517
AB - Breeding programs increasingly need prediction systems that support reliable candidate selection across heterogeneous environments, which makes cross-environment genomic prediction an important component of multienvironment crop improvement. However, model evaluation still relies heavily on Pearson’s correlation coefficient ( r ), a global summary that may not fully capture which top-ranked candidates would be advanced. Using maize and switchgrass datasets as focused case studies, we compared global predictive ability with phenotype-referenced candidate diagnostics across within-environment and directed cross-environment evaluations of rrBLUP/ridge, Light Gradient Boosting Machine (LightGBM), a multilayer perceptron, and mixed-effect deep neural network (MeNet). Rather than proposing a new selection metric, we used a conditional comparison framework that distinguishes nominal metric reversal from strict decision-level discordance among models with similar Pearson’s r . The r -best and candidate-metric-best models disagreed in 25%–55% of evaluation contexts, but large differences in candidate metrics among near- r models (|Δ r | ≤ 0.02) were uncommon. Nevertheless, models with nearly identical r did not always prioritize the same candidates: LightGBM and rrBLUP/ridge shared, on average, 72.9% of the top 5% candidates in maize and 68.8% in switchgrass. These results indicate that Pearson’s r remains informative for broad model comparison but does not fully describe decision-level behavior. Phenotype-referenced candidate diagnostics are therefore best used as targeted complements when models have similar predictive ability, selection intensity is high, or candidate identity is consequential across environments.
SN - 1664-462X
ER -