Optimization and application of genome prediction model in rapeseed: flowering time, yield components and oil content as examples

Rapeseed is the second-largest oilseed crop in the world with short domestication and breeding history. This study developed a batch of genomic prediction models for flowering time, oil content and yield components in rapeseed. Using worldwide 404 breeding lines, the optimal prediction model for flowering time, and five quality and yield traits was established by comparison with efficient traditional models and machine learning models. The results indicate that QTLs and significant variations identified by GWAS can significantly improve the prediction accuracy of complex traits, achieving over 90% accuracy in predicting flowering time and thousand grain weight. The GBLUP and Bayes-Lasso models provided the most accurate prediction overall, while machine learning models such as GBDT (Gradient Boosting Decision Trees) exhibited strong predictive performance. Our study provides genome selection solution for the high prediction accuracy and selection of complex traits in rapeseed breeding. The use of a diverse panel of 404 worldwide lines ensures that the findings are broadly applicable across different rapeseed breeding programs.