With the rapid advance of spatial multi-omics technologies, it has become possible to simultaneously profile transcripts, proteins and chromatin states at their native spatial coordinates, thereby uncovering molecular architecture that transcends any single-omics perspective. However, the resulting data matrices are often highly sparse and suffer from unstable dimensionality. Graph-based neural methods capture only local neighborhood information, whereas conventional Transformers, although capable of modelling long-range dependencies, incur prohibitive computational costs on such data. To overcome these limitations, we propose TLAGC—a Taylor-Linear-Attention-Guided Graph Convolutional framework that couples a Taylor-expanded linear attention (TLA) mechanism with graph convolutional networks. By eliminating the soft-max operation and linking the LocalGCN via residual connections, TLA preserves local structural information while enabling the integration of global and local contexts, thereby alleviating ineffective information propagation between spatially distant yet transcriptionally similar regions. Theoretical analysis confirms that TLA indeed reduces computational complexity, and extensive experiments on multiple spatial multi-omics benchmarks demonstrate that TLAGC consistently outperforms state-of-the-art baselines in delineating spatial domains.

Lysine crotonylation (Kcr) is an important protein modification occurring after translation in biology, serving an essential function in a range of biological processes in both plants and animals, including the regulation of gene expression, the maintenance of cellular metabolic balance, and the enhancement of photosynthesis. Exploring the detection of Kcr sites is essential for uncovering their biological functions. Nonetheless, conventional experimental approaches for detection are often time-consuming, expensive, and hindered by various technical constraints, making the precise identification of Kcr sites a significant challenge. This study seeks to develop a computational approach for the rapid and accurate prediction of Kcr sites in plant non-histone proteins. We introduce a novel deep learning framework named DeepNhKcr, which integrates the protein language model (ESM2) with a bidirectional long short-term memory (BiLSTM) network. To address the challenge of data imbalance, the model replaces the conventional cross-entropy loss with the focal loss function. In addition, DeepNhKcr combines advanced deep learning approaches with traditional protein encoding strategies to enable effective feature extraction and integration. This method not only significantly boosts the accuracy of predicting Kcr sites in non-histone proteins of plants. but also provides interpretability, shedding light on the potential links between key sequence characteristics and their biological roles. DeepNhKcr delivers outstanding results, surpassing existing machine learning and deep learning models, and demonstrating excellent performance in both five-fold cross-validation and independent test experiments. Moreover, the model integrates interpretability analysis techniques to investigate the connections between important sequence features and their biological roles. DeepNhKcr acts as a powerful method for detecting Kcr sites in plant non-histone proteins and is anticipated to greatly advance future studies in plant Kcr site prediction.

Rare tumors are generally faced with the dilemma of delayed diagnosis, lack of treatment methods and poor prognosis due to their high clinical heterogeneity, low incidence but numerous subtypes. Although the analysis of molecular mechanisms and clinical characteristics is crucial to improving the clinical research of rare tumors, current research is limited by the scattered heterogeneity of multi-center data, scarce sample size and lack of standardized integration mechanism, which seriously hinders the process of basic research to clinical transformation. In order to meet such challenges, we are committed to building a rare tumor comprehensive database website. The core goal of this platform is to aggregate and provide high-quality and reliable datasets (including genome, transcriptome, proteome and clinical information) of various rare tumor types, providing a centralized and efficient resource center for researchers around the world, thereby accelerating the basic research and clinical transformation exploration of rare tumors. The database website (RTCDB) contains$\mathbf{1 3 4}$rare tumor types and 306 selected datasets with 7912 samples. The establishment of this rare tumor database will strongly promote the collaborative cooperation and rapid development of related research. RTCDB can be accessed for free at http://www.rtedb.cn/.

Inflammatory responses may lead to tissue or organ damage, and proinflammatory peptides (PIPs) are signaling peptides that can induce such responses. Many diseases have been redefined as inflammatory diseases. To identify PIPs more efficiently, we expanded the dataset and designed an ensemble learning model with manually encoded features. Specifically, we adopted a more comprehensive feature encoding method and considered the actual impact of certain features to filter them. Identification and prediction of PIPs were performed using an ensemble learning model based on five different classifiers. The results show that the model's sensitivity, specificity, accuracy, and Matthews correlation coefficient are all higher than those of the state-of-the-art models. We named this model MultiFeatVotPIP, and both the model and the data can be accessed publicly at https://github.com/ChaoruiYan019/MultiFeatVotPIP. Additionally, we have developed a user-friendly web interface for users, which can be accessed at http://www.bioai-lab.com/MultiFeatVotPIP.