Molecular Plant Breeding 2024, Vol.15, No.1, 15-26 http://genbreedpublisher.com/index.php/mpb 20 The study “Machine Learning and Ensemble Learning for Transcriptome Data: Principles and Advances” delved into the latest machine learning studies on ensemble learning, RNA-seq technology, and plant genomics and transcriptome analysis. The study has shown that ensemble learning frameworks perform well in machine learning, outperforming traditional statistical methods, and have wide applications in plant attribute classification, gene importance assessment, and molecular breeding. (Wang et al., 2022). The study “Traits Expansion and Storage of Soybean Phenotypic Data in Computer Vision-Based Test”, based on computer vision (CV) technology, collected phenotypic data of soybeans, and expanded four trait types in the “Guidelines for Testing Plant Variety Specificity, Consistency, and Stability: Soybeans”. The study highlighted the potential of computer vision (CV) technology in large-scale, low-cost, and precise analysis of crop phenotypes, providing accurate phenotype data for breeding program design (Xing et al., 2022). The study “Computational Intelligence to Study the Importance of Characteristics in Flood-Irrigated Rice” demonstrated the effectiveness of computational intelligence and machine learning in determining the relative importance of variables in flood-irrigated rice. The study has shown the importance of using multiple regression, computational intelligence, and machine learning to predict rice characteristics, especially under flooded irrigation conditions (Silva Júnior et al., 2023). The study “Perspective for Genomic-Enabled Prediction Against Black Sigatoka Disease and Drought Stress in Polyploid Species” reviewed the challenges and prospects of genomic selection (GS) in polyploid plants, emphasizing the two major threats to banana production: black spot disease and drought. The study proposed bioinformatics tools and artificial intelligence methods, including machine learning, as well as GS schemes applied to banana BSD and drought (Nkoulou et al., 2022). Through the development of genomic prediction and selection, the application of high-throughput phenotypic determination, and the utilization of artificial intelligence and machine learning, Breeding 4.0 has achieved revolutionary progress in genetic information integration and editing. These innovations and advancements provide breeders with more accurate and efficient tools and methods, driving rapid development and continuous progress in crop breeding. 4 Breeding 4.0 Applications and Benefits 4.1 Examples and advantages of transgenic breeding Transgenic breeding is a significant application area within Breeding 4.0. By introducing foreign genes into crops, transgenic breeding can confer new traits and advantages to the crops. For instance, herbicide-resistant soybeans and BT cotton are successful examples of transgenic breeding, representing landmark achievements in this field. Herbicide-resistant soybeans possess the characteristic of tolerance to herbicides, enabling farmers to more effectively control weeds (Biotechnology Progress, 1985). On the other hand, BT cotton, through the incorporation of insecticidal genes, exhibits resistance to pests, reducing the need for pesticides (Wilson et al., 1994). Transgenic breeding can improve crop production efficiency and economic benefits by introducing specific genes to enhance disease resistance, stress tolerance, yield, and quality. In recent years, landmark achievements in transgenic breeding have emerged in the field of plant breeding. For example, Shailani et al. (2020) explored the improvement of rice tolerance to drought and salinity stress through gene stacking technology. This approach achieves transgenic improvement of rice by combining multiple genes with different tolerance mechanisms. Anwar and Kim (2020) investigated the progress of transgenic breeding in enhancing plant tolerance to abiotic stressors such as temperature, drought, and salinity. Their research emphasized the potential of transgenic technology in plant genetic improvement. Galán-Ávila et al. (2021) developed a novel method for transgenic breeding in Cannabis sativa L. This study provides an efficient gene transformation approach with significant implications for Cannabis breeding, especially concerning targeted genome editing by using the CRISPR/Cas system. These research papers demonstrate the significant progress and applications of transgenic breeding technologies in the field of plant breeding in recent years. Each study has overcome the limitations of traditional breeding, opening up new possibilities for plant breeding.
RkJQdWJsaXNoZXIy MjQ4ODYzMg==