Xiaodong Duan

Spatial transcriptomics (ST) helps us understand cell interactions, developmental processes, and disease progression within tissues by analyzing gene expression while preserv ing spatial information on tissue sections. However, the spatial distribution patterns of the same cell population may differ in different slice samples, and a single slice is difficult to adapt to spatial changes, making multi-slice integration methods a research hotspot in recent years. Traditional graph convolution relies on a fixed graph structure, whose adjacency relationships remain fixed during training. It cannot be adaptively updated according to feature changes and is difficult to reflect the spatial distribution differences between different slices. Dynamic graph convolutional neural networks (DGCNN), on the other hand, adaptively update based on node embeddings or features during training to capture complex spatial relationships. Therefore, we propose DGAE, a framework based on DGCNN for multi-slice ST data alignment and data enhancement. DGAE consists of two modules: DGAE_align and DGAE_recog. DGAE_align combines K-nearest neighbor (KNN) and r-radius to build a hybrid graph, and integrates the spatial information of different slices to achieve accurate spatial alignment. DGAE_recog aggregates the information of adjacent slices into the target slice for data enhancement, achieving effective transmission of information between different slices. Experimental results show that DGAE outperforms existing methods in multi-slice ST data alignment and also demonstrates superior performance in data enhancement tasks. In addition, DGAE has shown well adaptability and stability in spatial domain recognition, denoising and disease research, demonstrating the wide applicability and scalability of DGAE as a method for multi-slice ST data alignment and data enhancement.

Predicting potential drug-disease associations (RDAs) plays a pivotal role in elucidating therapeutic strategies for diseases and facilitating drug repositioning, making it of paramount importance. However, existing methods are constrained and rely heavily on limited domain-specific knowledge, impeding their ability to effectively predict candidate associations between drugs and diseases. Moreover, the simplistic definition of unknown information pertaining to drug-disease relationships as negative samples presents inherent limitations. To overcome these challenges, we introduce a novel hierarchical negative sampling-based graph contrastive model, termed HSGCLRDA, which aims to forecast latent associations between drugs and diseases. In this study, HSGCLRDA integrates the association information as well as similarity between drugs, diseases and proteins. Meanwhile, the model constructs a drug-disease-protein heterogeneous network. Subsequently, employing a hierarchical structural sampling technique, we establish reliable negative drug-disease samples utilizing PageRank algorithms. Utilizing meta-path aggregation within the heterogeneous network, we derive low-dimensional representations for drugs and diseases, thereby constructing global and local feature graphs that capture their interactions comprehensively. To obtain representation information, we adopt a self-supervised graph contrastive approach that leverages graph convolutional networks (GCNs) and second-order GCNs to extract feature graph information. Furthermore, we integrate a contrastive cost function derived from the cross-entropy cost function, facilitating holistic model optimization. Experimental results obtained from benchmark datasets not only showcase the superior performance of HSGCLRDA compared to various baseline methods in predicting RDAs but also emphasize its practical utility in identifying novel potential diseases associated with existing drugs through meticulous case studies.

Due to the complexity and variability of the relationships between objects, it becomes very difficult to detect the relationships between them. Scene graph generation (SGG) has been receiving attention as a challenging task in computer vision. Most of the existing scene graph generation methods use two-stage or point-based single-stage methods, but these methods usually suffer from excessive time complexity or poor design assumptions. In this paper, we adopt a single-stage generation method inspired by the transformer. In this, the main body still uses Convolutional Neural Network (CNN) for image feature extraction, and then the extracted features are given to the transformer decoder for encoding and decoding, and then processed to obtain the scene graph. The work in this paper lies in 1) adding a predicate generator to the traditional transformer decoder, and 2) evaluating it on some improved visual genome-based datasets, and the results show that the method improves the SGG's relationship recognition ability.