Medical images exhibit latent anatomical groupings, such as organs, tissues, and pathological regions, that standard Vision Transformers (ViTs) fail to exploit. While recent work like SBM-Transformer attempts to incorporate such structures through stochastic binary masking, they suffer from non-differentiability, training instability, and the inability to model complex community structure. We present DCMM-Transformer, a novel ViT architecture for medical image analysis that incorporates a Degree-Corrected Mixed-Membership (DCMM) model as an additive bias in self-attention. Unlike prior approaches that rely on multiplicative masking and binary sampling, our method introduces community structure and degree heterogeneity in a fully differentiable and interpretable manner. Comprehensive experiments across diverse medical imaging datasets, including brain, chest, breast, and ocular modalities, demonstrate the superior performance and generalizability of the proposed approach. Furthermore, the learned group structure and structured attention modulation substantially enhance interpretability by yielding attention maps that are anatomically meaningful and semantically coherent.

As spatial transcriptomics (ST) datasets increasingly span multiple adjacent or replicated slices, effective joint analysis across slices is needed to reconstruct tissue structures and identify consistent spatial gene expression patterns. This requires resolving spatial correspondences between slices while capturing shared transcriptomic features, two tasks that are typically addressed in isolation. Multi-slice analysis remains challenging due to physical distortions, technical variability, and batch effects. To address these challenges, we introduce Joint Alignment and Deep Embedding for multi-slice ST (JADE), a unified computational framework that simultaneously learns spot-wise alignments and shared low-dimensional embeddings across tissue slices. Unlike existing methods, JADE adopts a roundtrip framework in which each iteration alternates between alignment and embedding refinement. To infer alignment, we employ attention mechanisms that dynamically assess and weight the importance of different embedding dimensions, allowing the model to focus on the most alignment-relevant features while suppressing noise. To the best of our knowledge, JADE is the first method that jointly optimizes alignment and representation learning in a shared latent space, enabling robust multi-slice integration. We demonstrate that JADE outperforms existing alignment and embedding methods across multiple evaluation metrics in the 10x Visium human dorsolateral prefrontal cortex (DLPFC) and Stereo-seq axolotl brain datasets. By bridging spatial alignment and feature integration, JADE provides a scalable and accurate solution for cross-slice analysis of ST data.

Graphon models provide a flexible nonparametric framework for estimating latent connectivity probabilities in networks, enabling a range of downstream applications such as link prediction and data augmentation. However, accurate graphon estimation typically requires a large graph, whereas in practice, one often only observes a small-sized network. One approach to addressing this issue is to adopt a transfer learning framework, which aims to improve estimation in a small target graph by leveraging structural information from a larger, related source graph. In this paper, we propose a novel method, namely GTRANS, a transfer learning framework that integrates neighborhood smoothing and Gromov-Wasserstein optimal transport to align and transfer structural patterns between graphs. To prevent negative transfer, GTRANS includes an adaptive debiasing mechanism that identifies and corrects for target-specific deviations via residual smoothing. We provide theoretical guarantees on the stability of the estimated alignment matrix and demonstrate the effectiveness of GTRANS in improving the accuracy of target graph estimation through extensive synthetic and real data experiments. These improvements translate directly to enhanced performance in downstream applications, such as the graph classification task and the link prediction task.

Social relationships among students at campus are closely related to their mental health and academic performance. Therefore, it is a very important task for educators to analyze students’ social relationships. However, existing studies have focused on one-to-one social relationships between students, few ones have explored the high-order community relationships hidden in social networks, especially in a visual manner. To solve this problem, a visual analysis system called ViSSR is proposed in this paper, which utilizes the Louvain algorithm to detect the hierarchical community structure of students’ social network at campus, and then provides four coordinated views to visualize the detection results. Among the views, the hierarchical hypergraph view is to visualize the hierarchical community structure that greatly breaks through the limitations of first-order relationships available in a traditional node-link social network, the community analysis view and individual analysis view show the social characteristics of a community and individual student respectively, and the matrix view displays the behavioral features of students. Case studies and experts evaluation have been conducted to demonstrate the usability of the system.

In the field of object detection, particularly in medical imaging, the scarcity of data often poses a significant challenge to model performance. To address this issue, this study proposes a semi-supervised learning approach based on a generative model. We begin by fine-tuning a pre-trained generative model using our dataset to better adapt the generative model to our specific data distribution. The fine-tuned generative model is then used to generate additional unlabeled data. These generated unlabeled data, combined with the original dataset, are employed in a semi-supervised training process. Experimental results demonstrate that our method significantly enhances the performance of the object detection model, especially in scenarios with limited labeled data, such as medical imaging. By incorporating the generated unlabeled training data into the semi-supervised framework, we observed a notable improvement in model accuracy. Specifically, our experiments showed an increase of up to $6.92 \%$ after adding the generated iamges. Moreover, it is foreseeable that incorporating a higher proportion of generated unlabeled data could lead to even more significant improvements in performance.

Conventional community detection methods often categorize all nodes into clusters. However, the presumed community structure of interest may only be valid for a subset of nodes (named as `tight nodes'), while the rest of the network may consist of noninformative ``scattered nodes''. For example, a protein-protein network often contains proteins that do not belong to specific biological functional modules but are involved in more general processes, or act as bridges between different functional modules. Forcing each of these proteins into a single cluster introduces unwanted biases and obscures the underlying biological implication. To address this issue, we propose a tight community detection (TCD) method to identify tight communities excluding scattered nodes. The algorithm enjoys a strong theoretical guarantee of tight node identification accuracy and is scalable for large networks. The superiority of the proposed method is demonstrated by various synthetic and real experiments.

Rapid and accurate detection and localization of electronic disturbances simultaneously are important for preventing its potential damages and determining potential remedies. The existing anomaly detection methods are severely limited by the low accuracy, expensive computational cost, and the need for highly trained personnel. There is an urgent need for a scalable online algorithm for the in-field analysis of large-scale power electronics networks. In this article, we propose a fast and accurate algorithm for anomaly detection and localization of power electronics networks: the stratified colored-node graph (CONGO). This algorithm hierarchically models the change of correlated waveforms and then correlated sensors using the CONGO. By aggregating the change of each sensor with its neighbors’ inputs, we can spontaneously identify and localize the anomaly that cannot be detected by data collected from a single sensor. As our proposed method only focuses on the changes within a short time frame, it is highly computational efficient and only needs small data storage. Thus, our method is ideal for online and reliable anomaly detection and localization of large-scale power electronic networks. Compared to the existing anomaly detection methods, our method is entirely data driven without training data, highly accurate and reliable for wide-spectrum anomalies detection, and more importantly, capable of both detection and localization. Thus, it is ideal for the in-field deployment for large-scale power electronic networks. As illustrated by a distributed energy resources (DERs) power grid with 37-node, our method can effectively detect and localize various cyber and physical attacks.

BACKGROUND: Protein kinases are a large family of druggable proteins that are genomically and proteomically altered in many human cancers. Kinase-targeted drugs are emerging as promising avenues for personalized medicine because of the differential response shown by altered kinases to drug treatment in patients and cell-based assays. However, an incomplete understanding of the relationships connecting genome, proteome and drug sensitivity profiles present a major bottleneck in targeting kinases for personalized medicine. RESULTS: In this study, we propose a multi-component Quantitative Structure-Mutation-Activity Relationship Tests (QSMART) model and neural networks framework for providing explainable models of protein kinase inhibition and drug response ([Formula: see text]) profiles in cell lines. Using non-small cell lung cancer as a case study, we show that interaction terms that capture associations between drugs, pathways, and mutant kinases quantitatively contribute to the response of two EGFR inhibitors (afatinib and lapatinib). In particular, protein-protein interactions associated with the JNK apoptotic pathway, associations between lung development and axon extension, and interaction terms connecting drug substructures and the volume/charge of mutant residues at specific structural locations contribute significantly to the observed [Formula: see text] values in cell-based assays. CONCLUSIONS: By integrating multi-omics data in the QSMART model, we not only predict drug responses in cancer cell lines with high accuracy but also identify features and explainable interaction terms contributing to the accuracy. Although we have tested our multi-component explainable framework on protein kinase inhibitors, it can be extended across the proteome to investigate the complex relationships connecting genotypes and drug sensitivity profiles.