Legume Genomics and Genetics 2024, Vol.15, No.6, 270-279 http://cropscipublisher.com/index.php/lgg 276 7.3 Potential solutions and future directions To address these challenges, several potential solutions and future directions can be considered. Advances in machine learning and big data analytics offer promising avenues for enhancing the integration of GWAS and GS. Machine learning algorithms, such as SVR and RF, have demonstrated superior performance in identifying relevant QTL compared to traditional methods (Yoosefzadeh-Najafabadi et al., 2021a; Yoosefzadeh-Najafabadi et al., 2023). Additionally, the development of hierarchical data integration strategies, such as the hyperspectral wide association study (HypWAS), can improve the efficiency of phenome-genome association analyses and provide deeper insights into the genetic architecture of complex traits (Yoosefzadeh-Najafabadi et al., 2021b). Furthermore, the adoption of phenomics and high-throughput phenotyping tools can alleviate some of the bottlenecks in data acquisition and analysis. These tools enable the collection of large-scale, high-quality phenotypic data, which is essential for accurate genomic predictions (Sandhu et al., 2022). The integration of phenomics with GS and machine learning can accelerate the breeding cycle and enhance genetic gains. 8 Concluding Remarks This study has explored the integration of Genome-Wide Association Studies (GWAS) and Genomic Selection (GS) to enhance soybean breeding. GWAS has been instrumental in identifying genetic variants associated with complex traits by examining genome-wide genetic variants across diverse genetic materials. On the other hand, GS facilitates the rapid selection of superior genotypes and accelerates the breeding cycle by leveraging genomic-enabled prediction models. The integration of these two approaches can significantly enhance the efficiency and effectiveness of soybean breeding programs. Integrating GWAS and GS holds immense potential for future soybean breeding. GWAS provides a robust framework for identifying genetic variants associated with important agronomic traits, which can then be used to inform GS models. This combined approach allows for more accurate prediction of phenotypic outcomes based on genetic data, thereby accelerating the breeding process and improving the selection of high-yield, disease-resistant soybean varieties. Additionally, the integration of these methods can help in understanding the genetic basis of complex traits, leading to more targeted and efficient breeding strategies. To fully realize the benefits of integrating GWAS and GS in soybean breeding, continued research and development are essential. Future studies should focus on optimizing GWAS models to reduce false positives and improve statistical power. Additionally, advancements in genomic technologies, such as hyperspectral imaging and genotype imputation, should be leveraged to enhance the accuracy and efficiency of GS models. Collaborative efforts to curate and integrate high-quality GWAS data, as exemplified by resources like the GWAS Atlas, will also be crucial for advancing genetic research and breeding applications. By investing in these areas, we can unlock the full potential of GWAS and GS to drive innovation in soybean breeding and ensure sustainable agricultural practices. Acknowledgments The authors extend sincere thanks to two anonymous peer reviewers for their feedback on the manuscript of this study. Funding This work was supported by Major Science and Technology Special Project for New Variety Breeding in Agriculture of Zhejiang Province (2021C02064-5) and Science and Technology Innovative Team in Fujian Academy of Agricultural Sciences (CXTD2021011-2). Conflict of Interest Disclosure The authors affirm that this research was conducted without any commercial or financial relationships that could be construed as a potential conflict of interest.
RkJQdWJsaXNoZXIy MjQ4ODYzNA==