Spatial transcriptomics (ST) is a powerful technology for analyzing gene activities within tissue contexts, yet existing ST techniques have limitations in resolution and transcriptome coverage. Although various computational methods have been developed to address these challenges, they generally fail to incorporate valuable spatial context information, limiting their ability to fully capture the molecular complexity of tissues. In this study, we present TSRST, a LongNet-based Transformer model, that models spatial location information through positional embeddings and imputes super-resolution spatial transcriptomic data by integrating histological features and spatial contexts. Comprehensive experiments on datasets from human glioblastoma, mouse brain, and human dorsolateral prefrontal cortex (DLPFC) demonstrate that TSRST consistently outperforms existing methods in predicting high-resolution gene expressions. Additionally, TSRST exhibits strong capabilities in annotating tissue structures at high resolution, showing high concordance with existing annotations in mouse brain and HER2ST breast cancer datasets. Overall, TSRST offers a robust framework for enhancing spatial transcriptomic data, supporting advanced research in cancer and related fields. TSRST is freely accessible at https://github.com/wppqprwe/TSRST.

Gaussian graphical models (GGMs) are a popular tool for exploring conditional dependence among high dimensional data. We consider developing an estimator for GGMs for multiple graph analysis, wherein the graphs are assumed to come from two (or more) contrastive groups, and exhibit not only major global similarity, but also substantial between-group disparity. Under this setting, inferring each group of networks separately ignores the common structure, while simply assuming a global common network structure would mask the critical disparity. We propose a novel approach to pursue simultaneous network inference using discriminative and adaptive structural regularizations. We introduce a heterogeneity ratio parameter to balance the within group similarity and the between group disparity. This formulation for the first time, to our knowledge, generalizes the existing single-group network analysis to multiple-group network analysis. In other words, our proposed multiple-group network analysis reduces to single-group network analysis, when the heterogeneity ratio equal to 1. By iteratively updating a global regularization template with individual network structures, together with a feature screening module specifying relevant dimensions to satisfy the group-level constraints, our generalized approach can recover the underlying conditional independence with greater flexibility and improved accuracy. Theoretically, we show the asymptotic consistency for the proposed method in joint reconstruction of multiple network structures. We demonstrate its superior performance via extensive simulation studies. We also illustrate its practical usage in an application to polychromatic flow cytometry data sets for protein interactions under different conditions.

With the growth of the digital advertising market, it has become more important than ever to target the desired audiences. Among various demographic traits, gender information plays a key role in precisely targeting the potential consumers in online advertising and ecommerce. However, such personal information is generally unavailable to digital media sellers. In this paper, we propose a novel task-specific multi-task learning algorithm to predict users' gender information from their video viewing behaviors. To detect as many desired users as possible, while controlling the Type I error rate at a user-specified level, we further propose Bayes testing and decision procedures to efficiently identify male and female users, respectively. Comprehensive experiments have justified the effectiveness and reliability of our framework.