Genomic prediction vs. gene-based crop models: a case study on rice trait prediction

Optimizing phenotypic data analysis strategies to enhance genomic prediction in winter wheat breeding

Proper analysis of phenotypic data is essential for reliable genomic prediction (GP) and sustained genetic gain in breeding programs. In this study, we used phenotypic and genotypic data generated from the winter wheat breeding program of Deutsche Saatveredelung AG (DSV), Lippstadt, Germany, comprising 1,941 genotypes and 6,335 SNP markers across three traits: grain yield, plant height, and heading date. We evaluated the impact of different two-stage analysis strategies: one using the environment (year × location combination) as the analysis unit (TS-S1) and the other using the breeding stage as the analysis unit (TS-S2), each with and without accounting for breeding-stage effects (-YesBS and -NoBS), on the computation of best linear unbiased estimates (BLUEs) and genome-wide prediction ability (PA), defined as the correlation between BLUEs and predicted values. The performance of these 4 different second stage models (TS-S1-NoBS, TS-S1-YesBS, TS-S2-NoBS, and TS-S2-YesBS) were evaluated using the extended genomic best linear prediction (EGBLUP) model under 5-fold cross validation (5-fold CV), leave one year out cross validation (LOY-CV) and leave one breeding stage out cross validation (LOBS-CV) scenarios. In the presence of the strong breeding stage effect ignoring the breeding stage in the model resulted in biased BLUEs and overestimated prediction abilities in the 5-fold CV, and underestimated prediction abilities in the LOY-CV and LOBS-CV. These unstable prediction abilities are driven by confounded environmental effects in the BLUEs due to omission of the breeding-stage effect. In contrast, models that accounted for the breeding stage produced more reliable BLUEs and more stable prediction results across all cross-validation scenarios, with TS-S1-YesBS performing best overall. Overall, our findings demonstrate that breeding stage effects mainly arise from differences in growing conditions and must be adequately considered. Therefore, including breeding stage in phenotypic models is critical to obtaining unbiased BLUEs and ensuring accurate genomic prediction and selection decisions.

Integrating predictive models and GWAS to identify candidate loci and genes for agronomic traits in rice

Rice is a staple crop whose improvement relies on breeding advances; precision agriculture demands predictive loci/genes for agronomic traits to innovate rice production. To cut experimental costs and boost efficiency, this study built predictive models using seedling leaf metabolomes to forecast rice agronomic traits and decode trait correlations. We integrated 11 agronomic traits and 840 metabolites from 524 rice germplasms, plus 17 agronomic traits of 3,000 varieties. Five algorithms (RF, LightGBM, SWR, LASSO, CART) were combined to build multi-model prediction systems, offsetting defects of single models for accurate complex trait prediction. GWAS on predicted phenotypes detected nine genetic hotspots. Results showed LASSO and CART had weak generalization, while LightGBM, RF and SWR delivered trait-specific predictive performance. Seven candidate genes within hotspots were validated via variation annotation, haplotype and tissue expression analyses. Distinct from laborious, environment-prone traditional phenotyping, these models realize rapid, stable high-throughput trait prediction via early metabolic markers. The uncovered loci and genes lay groundwork for dissecting molecular regulatory networks linking rice agronomy and metabolism.

Advances in predictive breeding for wheat: concepts, methods, and applications

Wheat is one of the world’s main crops. Its improvement is pivotal given the threat of climate change and the growing population. However, enhancing breeding efficiency and improving wheat are challenging due to strong genotype-by-environment (G×E) interactions and the biological complexity underlying the wheat genome and key agronomic traits. In this context, predictive frameworks and data-driven approaches can offer new strategies to address these challenges. This article provides a comprehensive review of the latest developments in wheat breeding, highlighting emerging predictive frameworks and their contributions to modern breeding pipelines. First, we report on genomic selection (GS) applications, emphasizing GS’s ability to improve complex traits by shortening the breeding cycle and increasing selection accuracy. We then describe the applications of phenomics in wheat breeding, including both ground- and unmanned aerial vehicle (UAVs)-based systems. We also discuss the potential for implementing multi-omics strategies to improve complex wheat traits. We debate how predictive breeding frameworks can assist in identifying the best parents and crosses in wheat breeding. Finally, we presented the latest panorama of software for predictive breeding and its integration with other technologies. This review reports recent advances demonstrating how predictive frameworks are reshaping wheat breeding methods, highlighting current progress and outlining future opportunities to accelerate genetic gain in wheat improvement.

A Public Mid-Density Genotyping Platform for Genomic Selection in Wheat

The results suggest that, in elite wheat germplasm characterized by long-range linkage disequilibrium and strong realized genomic relationships, medium-density targeted genotyping platforms can retain most of the predictability achieved by higher-density systems.

Targeted Multi-Omics Machine Learning Framework for Robust Prediction of Maize Yield and Disease Resistance

Genomic Selection Integrated with High-Throughput Phenotyping and Speed Breeding for Smart and Greener Rice (Oryza sativa) Improvement

This narrative review critically examines recent advances in genomic selection for rice and its integration with high-throughput genotyping, high-throughput phenotyping, machine learning, multi-environment prediction, and speed breeding.