Plant Gene and Traits 2024, Vol.15, No.4, 174-183 http://genbreedpublisher.com/index.php/pgt 180 7.2 Addressing genetic complexity in disease resistance breeding Breeding for disease resistance in wheat is inherently complex due to the polygenic nature of traits like powdery mildew resistance. The resistance conferred by MlWE74 is controlled by a single dominant gene, but integrating this gene into elite cultivars requires careful consideration of genetic background and environmental interactions (Zhu et al., 2021; Bapela et al., 2023). The use of high-throughput genotyping and marker-assisted selection (MAS) can enhance the efficiency of breeding programs by enabling the precise transfer of resistance genes with minimal linkage drag (Figure 2) (Bapela et al., 2023; Jiang, 2024). Additionally, multi-environment trials are necessary to ensure the stability and effectiveness of resistance across different growing conditions. Figure 2 Precision phenotypic analysis of wheat resistance to powdery mildew using Machine Learning (ML) and Artificial Intelligence (AI) techniques (Adapted from Bapela et al., 2023) Image caption: A: Powdery mildew colonies of the reference genome isolate Bgt_96224 on the susceptible wheat variety Chinese Spring; B: Haustoria structures of multiple powdery mildew fungi revealed in wheat epidermal cells via optical microscopy; C: Pixel classification phenotype analysis of powdery mildew leaf coverage using machine learning (ML); D: The fully automated high-throughput image acquisition system Macrobot 2.0 at IPK, Germany; E: Example of ML-assisted feature extraction from images taken by Macrobot 2.0; F: The high-performance Zeiss AxioScan.Z1 microscope used for automated microscopic phenotype acquisition; G, H: Convolutional neural network (CNN)-assisted computational visualization of powdery mildew microcolonies and associated fungal structures (Adapted from Bapela et al., 2023) Bapela et al. (2023) applied advanced machine learning (ML) and artificial intelligence (AI) technologies in precision breeding for wheat resistance to powdery mildew. With the assistance of ML and convolutional neural networks (CNN), researchers were able to accurately characterize the colony coverage and microcolony structures of powdery mildew fungi, enhancing the efficiency and accuracy of phenotypic analysis. These automated and high-throughput phenotyping tools contribute to accelerating the progress of disease-resistant breeding and provide strong technical support for improving disease resistance in crops such as wheat. 7.3 Global promotion and application of the MlWE74gene in wheat breeding To maximize the impact of the MlWE74 gene, it is crucial to promote its use in global wheat breeding programs. This involves not only the transfer of MlWE74 into diverse wheat cultivars but also the dissemination of knowledge and resources related to this gene. The co-segregated marker WGGBD425 identified in the fine
RkJQdWJsaXNoZXIy MjQ4ODYzMg==