In graph based multiview clustering methods, the ultimate partition result is usually achieved by spectral embedding of the consistent graph using some traditional clustering methods, such as -means. However, optimal performance will be reduced by this multistep procedure since it cannot unify graph learning with partition generation closely. In this article, we propose a one-step multiview clustering method through adaptive graph learning and spectral rotation (AGLSR). For every view, AGLSR adaptively learns affinity graphs to capture similar relationships of samples. Then, a spectral embedding is designed to take advantage of the potential feature space shared by different views. In addition, AGLSR utilizes a spectral rotation strategy to obtain the discrete clustering labels from the learned spectral embeddings directly. An effective updating algorithm with proven convergence is derived to optimize the optimization problem. Sufficient experiments on benchmark datasets have clearly demonstrated the effectiveness of the proposed method in six metrics. The code of AGLSR is uploaded at https://github.com/tangchuan2000/AGLSR.

Hyperspectral image (HSI) encompasses a wealth of spectral-spatial information, offering a sufficient foundation for classification. However, the presence of redundancy poses challenges for achieving accurate classification. In this letter, we design a spectral-spatial interactive transformer (S2IT) for HSI classification (HSIC). S2IT commences with a meticulously designed spectral-spatial reconstruction (S2R) module, which aims to augment the representation of shallow features. Subsequently, an adaptive asymmetric gating mechanism transformer (AGM-Former) aims to delve into and extract comprehensive local-global features from HSI. Ultimately, the spectral-spatial interactive attention (S2IA) synergizes the spectral-spatial features and enhances classification prowess. S2IT demonstrates rigorous experiments on three renowned datasets: Houston2013 (HU), Indian Pines (IP), and the University of Pavia (UP), which validates its effectiveness in enhancing HSIC accuracy.

Transformers are increasingly popular in computer vision, which treat an image as a sequence of image patches and learn robust global features from the sequence. However, pure transformers are not entirely suitable for hyperspectral and light detection and ranging (LiDAR) image classification because image classification requires both robust global features and discriminative local features. Therefore, this article introduces a novel convolution interaction transformer network (CITNet) for jointly classifying hyperspectral and LiDAR images. The process begins with a carefully designed multiscale asymmetric depthwise convolution (MADC) module that exploits the local–global correlations of shallow features. On this basis, a novel local–global transformer (LGTM) is equipped with a local–global feed-forward (LGF) network to extract in-depth local–global joint features from the multimodal data. Then, an optimization convolution cross-attention (OCA) module, incorporating a convolutional layer, is developed to simulate the spatial relationships of semantic tokens. Finally, extensive experiments are conducted on the well-known Trento (TR), Augsburg (AU), MUUFL (MU), and Houston2013 (HU) datasets. The overall accuracy (OA) reaches 99.76%, 97.40%, 91.06%, and 99.90%, respectively, which are 0.2%–1.66%, 0.32%–7.37%, 1.52%–12.71%, and 0.14%–93.79% higher than the state-of-the-art (SOTA) methods, demonstrating the effectiveness of CITNet in improving the joint classification accuracy of hyperspectral and LiDAR images.

In the realm of biomedicine, the prediction of associations between drugs and diseases holds significant importance. Yet, conventional wet lab experiments often fall short of meeting the stringent demands for prediction accuracy and efficiency. Many prior studies have predominantly focused on drug and disease similarities to predict drug-disease associations, but overlooking the crucial interactions between drugs and diseases that are essential for enhancing prediction accuracy. Hence, in this paper, a resilient and effective model named Hierarchical and Dynamic Graph Attention Network (HDGAT) has been proposed to predict drug-disease associations. Firstly, it establishes a heterogeneous graph by leveraging the interplay of drug and disease similarities and associations. Subsequently, it harnesses the capabilities of graph convolutional networks and bidirectional long short-term memory networks (Bi-LSTM) to aggregate node-level information within the heterogeneous graph comprehensively. Furthermore, it incorporates a hierarchical attention mechanism between convolutional layers and a dynamic attention mechanism between nodes to learn embeddings for drugs and diseases. The hierarchical attention mechanism assigns varying weights to embeddings learned from different convolutional layers, and the dynamic attention mechanism efficiently prioritizes inter-node information by allocating each node with varying rankings of attention coefficients for neighbour nodes. Moreover, it employs residual connections to alleviate the over-smoothing issue in graph convolution operations. The latent drug-disease associations are quantified through the fusion of these embeddings ultimately. By conducting 5-fold cross-validation, HDGAT's performance surpasses the performance of existing state-of-the-art models across various evaluation metrics, which substantiates the exceptional efficacy of HDGAT in predicting drug-disease associations.

The accuracy of hyperspectral image (HSI) classification relies on lots of labeled training samples. However, the existing HSI data can be used for training with extremely limited labeled samples. In this letter, we propose a semisupervised HSI classification network based on pseudo-label and spatial-spectral convolution (PS3DN), which can improve classification accuracy with limited labeled samples. First, we design an asymmetric dense residual network (ARDN), which uses asymmetric convolution kernels instead of square kernels to reduce the number of parameters. Then we use the Center-Focus loss function to update the network parameters, aiming to improve the robustness of the network. Further, we generate high-confidence pseudo-labels by this network, which reduces the need for labeled samples for the classification network. Finally, we propose a joint spatial-spectral convolutional (SSCNN) classification network, the fusion of spatial-spectral separation convolution and self-learning attention mechanism, to achieve more accurate classification. We conducted experiments on four public datasets, and the experimental results show that the classification accuracy of Pavia University (UP), Salinas (SA), Kennedy Space Center (KSC), and Indian Pines (IP) datasets is 92.45%, 96.91%, 98.38%, and 90.43%, respectively.

HSI has abundant spectral–spatial information. Using this information to improve the accuracy of HSI classification is a hot issue in the industry. This letter proposes an end-to-end multilevel hybrid attention network (DMCN). It is composed of a dense 3-D convolutional neural network (3D-CNN), grouped residual 2D-CNN, and coordinate attention that can perceive categories. In the case of a small number of training samples, DMCN can still extract spectral–spatial fusion information and learn spatial features more deeply for classification. Experiments are conducted on three well-known hyperspectral datasets, i.e., Indian Pines (IP), University of Pavia (UP), and Salinas (SA). The results show that DMCN achieved 92.39%, 97.28%, and 98.40% classification accuracy in IP, UP, and SA.

The full set of T cell receptors (TCRs) in an individual is known as his or her TCR repertoire. Defining TCR repertoires under physiological conditions and in response to a disease or vaccine may lead to a better understanding of adaptive immunity and thus has great biological and clinical value. In the past decade, several high-throughput sequencing-based tools have been developed to assign TCRs to germline genes and to extract complementarity-determining region 3 (CDR3) sequences using different algorithms. Although these tools claim to be able to perform the full range of fundamental TCR repertoire analyses, there is no clear consensus of which tool is best suited to particular projects. Here, we present a systematic analysis of 12 available TCR repertoire analysis tools using simulated data, with an emphasis on fundamental analysis functions. Our results shed light on the detailed functions of TCR repertoire analysis tools and may therefore help researchers in the field to choose the right tools for their particular experimental design.

Light detection and ranging (LiDAR) data is a very important type of data used for terrain classification. The traditional convolutional neural network (CNN) has insufficient effective transmission of features and gradients in feature classification and can only set a fixed input size by experience. In this paper, spatial transformation network (STN) and densely connected convolutional network (DenseNet) are combined to form STN-DenseNet, which makes the input data adaptively deform according to the network needs, making full use of all information from the front layers of the network. Thus the transmission of features and gradients are more effective. The proposed framework performs experiments on two LiDAR-DSM datasets (i.e. Bayview Park and Recology datasets). The results show that, comparing with the traditional deep convolution model, STN-DenseNet can improve the classification accuracy of LiDAR-DSM data.