Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

The Myb family of transcription factors (TFs) is a large and functionally diverse group found in all eukaryotes, but its role in fungi remains poorly understood. Here, we characterized a Myb family TF called MoMyb13 in the rice blast fungus, Magnaporthe oryzae. MoMyb13 has two Myb domains and has orthologues only in ascomycete fungi. Localization experiments confirmed that MoMyb13 is located in the nuclei, as expected for a TF. Phenotypic analysis showed that MoMyb13 mutants exhibited reduced growth, whitened colony appearance and no conidia formation. Importantly, these mutants completely lost pathogenicity, despite being able to form appressoria at their hyphae ends, suggesting that these appressoria were non-functional for causing infection. Furthermore, the mutant colonies lost hydrophobicity and had significantly reduced expression of the hydrophobin MPG1. However, overexpression of MPG1 in the mutants restored their hydrophobicity, but not pathogenicity. Stress assay showed that the mutants were more sensitive to SDS, CR and H2O2, but more tolerant to NaCl and SOR. In summary, our study revealed the essential role of the MoMyb13 in the growth, conidiation, hydrophobicity, stress response and pathogenicity of M. oryzae, and provides valuable insights into the working mechanism of Myb TFs in fungi.