A Framework Integrating GWAS and Genomic Selection to Enhance Prediction Accuracy of Economical Traits in Common Carp

文献类型： 外文期刊

第一作者： Sun, Zhipeng

作者： Sun, Zhipeng;Fu, Yuhan;Zhu, Xiaoyue;Zhang, Ruixin;Zheng, Xianhu;Hu, Guo;Zhu, Xiaoyue;Zhang, Ruixin;Shu, Yongjun

作者机构：

关键词： common carp; GWAS; GS; FarmCPU; heritability

期刊名称：INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES （ 影响因子：4.9； 五年影响因子：5.7 ）

ISSN： 1661-6596

年卷期： 2025 年 26 卷 14 期

页码：

收录情况： SCI

摘要： Common carp (Cyprinus carpio) is one of the most significant fish species worldwide, with its natural distribution spanning Europe and Asia. To conduct a genome-wide association study (GWAS) and compare the prediction accuracy of genomic selection (GS) models for the growth traits of common carp in spring and autumn at 2 years of age, a total of 325 carp individuals were re-sequenced and phenotypic measurements were taken. Three GWAS methods (FarmCPU, GEMMA, and GLM) were applied and their performance was evaluated in conjunction with various GS models, using significance levels based on p-values. GWAS analyses were performed on eight traits (including the body length, body weight, fat content of fillet, and condition factor) for both spring and autumn seasons. Eleven different GS models (such as Bayes A, Bayes B, and SVR-linear) were combined to evaluate their performance in genomic selection. The results demonstrate that the FarmCPU method consistently exhibits superior stability and predictive accuracy across most traits, particularly under higher SNP densities (e.g., 5K), where prediction accuracies frequently exceed 0.8. Notably, when integrated with Bayesian approaches, FarmCPU achieves a substantial performance boost, with the prediction accuracy reaching as high as 0.95 for the autumn body weight, highlighting its potential for high-resolution genomic prediction. In contrast, GEMMA and GLM exhibited a more variable performance at lower SNP densities. Overall, the integration of FarmCPU with genomic selection (GS) models offers one of the most reliable and efficient frameworks for trait prediction, particularly for complex traits with substantial genetic variation. This approach proves especially powerful when coupled with Bayesian methodologies, further enhancing its applicability in advanced breeding programs.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序