Long noncoding RNAs (lncRNAs) play critical roles in regulating stemness signature genes (SSGs) and tumor immunity, thereby shaping the tumor microenvironment and antitumor immune responses. Increasing evidence suggests that cancer stem cell traits are closely associated with immune evasion and therapeutic resistance, underscoring the need to systematically characterize the pan-cancer interplay among SSGs, lncRNAs, and tumor immunity. Here, we developed an integrative analytical framework that combines network-based modeling with Bayesian network inference to identify core regulatory triplets (STEM-LncCRTs), each consisting of an lncRNA, an SSG, and an immune gene. We demonstrate that specific stemness-related lncRNAs can distinguish cancer subtypes, and that common stemness-related lncRNAs correlate significantly with immune cell infiltration. Notably, the ATAD5/PRR11-AS1/SKP2 triplet exhibits favorable prognostic potential across multiple cancers and consistently outperforms individual gene markers in predicting 1-, 3-, and 5-year overall survival. Furthermore, using four machine learning algorithms across three independent immunotherapy cohorts, we validate the predictive value of STEM-LncCRTs for immune checkpoint inhibitor response. Importantly, integrating STEM-LncCRTs with tumor mutation burden further improves predictive accuracy. Collectively, this study provides a systems-level view of stemness-related lncRNA regulation in tumor immunity and offers practical biomarkers for predicting immunotherapy efficacy.

BACKGROUND: MicroRNAs are key biomarkers for human diseases; however, experimentally identifying miRNA-disease associations was costly and inefficient. To improve the robustness and interpretability of computational models, we developed a multi-order adaptive graph-based miRNA-disease association model (MAGMDA). RESULTS: MAGMDA introduced an adaptive moment-order selection mechanism and a dynamic threshold network, which replaced the fixed moment orders and manually defined thresholds commonly used in traditional high-order statistical modeling with learnable components. By integrating numerically stable high-order moment computation with cross-order attention aggregation, MAGMDA enhanced model robustness and interpretability while maintaining computational efficiency. Five-fold cross-validation on the HMDD v2.0 dataset showed that MAGMDA achieved an AUC of 93.58% and an AUPR of 93.48%. Across multiple evaluation metrics, MAGMDA outperformed representative existing methods, exhibiting particularly consistent advantages on ranking-related metrics such as the area under the receiver operating characteristic curve (AUC) and the area under the precision–recall curve (AUPR), while maintaining smaller performance variations across different cross-validation folds, indicating stable predictive ability under different data partitions. Mechanistic diagnostic analysis further verified the stable utilization of the adaptive modules across different training folds. To demonstrate biological utility, we applied MAGMDA to hepatocellular carcinoma research. Based on the model predictions and analysis of the TCGA-LIHC cohort, we constructed a seven-gene prognostic signature, which was successfully validated in independent datasets and showed strong prognostic stratification ability, highlighting its potential for clinical translation. CONCLUSIONS: MAGMDA effectively improved miRNA-disease association prediction through an adaptive multi-order moment modeling framework and, supported by systematic biological validation, provided a powerful tool for translational research from computational discovery to clinical application. The MAGMDA framework and data resources are publicly available at https://github.com/zhangclbio/MAGMDA .

Low-rank tensor completion (LRTC) restores missing elements in multidimensional visual data; the challenge is representing the inherent structures within this data. Typical methods either suffer from inefficiency owing to the combination of multiple regularizers or perform suboptimally using inappropriate priors. In this study, we further investigated LRTC using tensor singular value decomposition (t-SVD). Inspired by the tensor-tensor product (t-product), we proposed a unified transformed t-SVD method that employs an invertible linear transform with a unitary transform matrix. However, the t-SVD-based framework lacks the flexibility necessary to represent different inherent relations along the tensor modes. To address this issue, we propose a tensor represented by a series of multidimensional unfolding tensors to fully explore the hidden structure of the original data. Furthermore, the proposed model can be solved efficiently using the alternate-direction method of the multiplier (ADMM) approach. Extensive experimental results on multidimensional visual data (multispectral images, hyperspectral images, and videos) demonstrated the superiority of the proposed method over other state-of-the-art LRTC-related methods.

Event-based semantic segmentation in traffic scenes has attracted considerable attention in autonomous driving systems due to the advantages of event cameras such as high dynamic range, low latency, and low energy consumption. However, existing Artificial Neural Network (ANN)-based methods rely on conventional image frames, often neglecting the spatial-temporal dynamics inherent in event streams and consuming higher energy costs, significantly limiting their applicability in energy-constrained environments. In this study, we introduce Spike-BRGNet, a Spike-driven Boundary Region-Guided Network that efficiently extracts boundary information utilizing only events to guide the segmentation encoder, while preserving the energy efficiency of Spiking Neural Networks (SNNs). Specifically, to explore the implicit information from events, we design a three-branch spiking encoder that consists of semantic detail (SD), context aggregation (CA), and boundary aware (BA) branches to capture specific features. Then, a spiking multi-scale context aggregation (SMSCA) module is proposed to enhance the semantics of the CA branch. Finally, a novel boundary region-guided loss function and a dynamic surrogate gradient function, EvAF, are designed to optimize the model. Extensive experiments show that our model outperforms state-of-the-art (SOTA) SNN-based methods on DDD17 (+1.57%) and DSEC dataset (+1.91%). Furthermore, Spike-BRGNet consumes$17.76\times $less energy than ANN-based models, showing superior energy-saving performance.

Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator.

Systematic investigation of tumor-infiltrating immune (TII) cells is important to the development of immunotherapies, and the clinical response prediction in cancers. There exists complex transcriptional regulation within TII cells, and different immune cell types display specific regulation patterns. To dissect transcriptional regulation in TII cells, we first integrated the gene expression profiles from single-cell datasets, and proposed a computational pipeline to identify TII cell type-specific transcription factor (TF) mediated activity immune modules (TF-AIMs). Our analysis revealed key TFs, such as BACH2 and NFKB1 play important roles in B and NK cells, respectively. We also found some of these TF-AIMs may contribute to tumor pathogenesis. Based on TII cell type-specific TF-AIMs, we identified eight CD8+ T cell subtypes. In particular, we found the PD1 + CD8+ T cell subset and its specific TF-AIMs associated with immunotherapy response. Furthermore, the TII cell type-specific TF-AIMs displayed the potential to be used as predictive markers for immunotherapy response of cancer patients. At the pan-cancer level, we also identified and characterized six molecular subtypes across 9680 samples based on the activation status of TII cell type-specific TF-AIMs. Finally, we constructed a user-friendly web interface CellTF-AIMs (http://bio-bigdata.hrbmu.edu.cn/CellTF-AIMs/) for exploring transcriptional regulatory pattern in various TII cell types. Our study provides valuable implications and a rich resource for understanding the mechanisms involved in cancer microenvironment and immunotherapy.

Aberrant DNA methylation is a fundamental characterization of epigenetics for carcinogenesis. Abnormality of DNA methylation-related functional elements (DMFEs) may lead to dysfunction of regulatory genes in the progression of cancers, contributing to prognosis of many cancers. There is an urgent need to construct a tool to comprehensively assess the impact of DMFEs on prognosis. Therefore, we developed SurvivalMeth (http://bio-bigdata.hrbmu.edu.cn/survivalmeth) to explore the prognosis-related DMFEs, which documented many kinds of DMFEs, including 309,465 CpG island-related elements, 104,748 transcript-related elements, 77,634 repeat elements, as well as cell-type specific 1,689,653 super enhancers (SE) and 1,304,902 CTCF binding regions for analysis. SurvivalMeth is a convenient tool which collected DNA methylation profiles of 36 cancers and allowed users to query their genes of interest in different datasets for prognosis. Furthermore, SurvivalMeth not only integrated different combinations, including single DMFE, multiple DMFEs, SEs and clinical data, to perform survival analysis on preupload data but also allowed for uploading customized DNA methylation profile of DMFEs from various diseases to analyze. SurvivalMeth provided a comprehensive resource and automated analysis for prognostic DMFEs, including DMFE methylation level, correlation analysis, clinical analysis, differential analysis, DMFE annotation, survival-related detailed result and visualization of survival analysis. In summary, we believe that SurvivalMeth will facilitate prognostic research of DMFEs in diverse cancers.

Drug sensitivity has always been at the core of individualized cancer chemotherapy. However, we have been overwhelmed by large-scale pharmacogenomic data in the era of next-generation sequencing technology, which makes it increasingly challenging for researchers, especially those without bioinformatic experience, to perform data integration, exploration and analysis. To bridge this gap, we developed RNAactDrug, a comprehensive database of RNAs associated with drug sensitivity from multi-omics data, which allows users to explore drug sensitivity and RNA molecule associations directly. It provides association data between drug sensitivity and RNA molecules including mRNAs, long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) at four molecular levels (expression, copy number variation, mutation and methylation) from integrated analysis of three large-scale pharmacogenomic databases (GDSC, CellMiner and CCLE). RNAactDrug currently stores more than 4 924 200 associations of RNA molecules and drug sensitivity at four molecular levels covering more than 19 770 mRNAs, 11 119 lncRNAs, 438 miRNAs and 4155 drugs. A user-friendly interface enriched with various browsing sections augmented with advance search facility for querying the database is offered for users retrieving. RNAactDrug provides a comprehensive resource for RNA molecules acting in drug sensitivity, and it could be used to prioritize drug sensitivity-related RNA molecules, further promoting the identification of clinically actionable biomarkers in drug sensitivity and drug development more cost-efficiently by making this knowledge accessible to both basic researchers and clinical practitioners. Database URL: http://bio-bigdata.hrbmu.edu.cn/RNAactDrug.

Alterations of biological pathways can lead to oncogenesis. An overview of these oncogenic pathways would be highly valuable for researchers to reveal the pathogenic mechanism and develop novel therapeutic approaches for cancers. Here, we reviewed approximately 8500 literatures and documented experimentally validated cancer-pathway associations as benchmarking data set. This data resource includes 4709 manually curated relationships between 1557 paths and 49 cancers with 2427 upstream regulators in 7 species. Based on this resource, we first summarized the cancer-pathway associations and revealed some commonly deregulated pathways across tumor types. Then, we systematically analyzed these oncogenic pathways by integrating TCGA pan-cancer data sets. Multi-omics analysis showed oncogenic pathways may play different roles across tumor types under different omics contexts. We also charted the survival relevance landscape of oncogenic pathways in 26 tumor types, identified dominant omics features and found survival relevance for oncogenic pathways varied in tumor types and omics levels. Moreover, we predicted upstream regulators and constructed a hierarchical network model to understand the pathogenic mechanism of human cancers underlying oncogenic pathway context. Finally, we developed `CPAD' (freely available at http://bio-bigdata.hrbmu.edu.cn/CPAD/), an online resource for exploring oncogenic pathways in human cancers, that integrated manually curated cancer-pathway associations, TCGA pan-cancer multi-omics data sets, drug-target data, drug sensitivity and multi-omics data for cancer cell lines. In summary, our study provides a comprehensive characterization of oncogenic pathways and also presents a valuable resource for investigating the pathogenesis of human cancer.

Numerous studies have shown that copy number variation (CNV) in lncRNA regions play critical roles in the initiation and progression of cancer. However, our knowledge about their functionalities is still limited. Here, we firstly provided a computational method to identify lncRNAs with copy number variation (lncRNAs-CNV) and their driving transcriptional perturbed subpathways by integrating multidimensional omics data of cancer. The high reliability and accuracy of our method have been demonstrated. Then, the method was applied to 14 cancer types, and a comprehensive characterization and analysis was performed. LncRNAs-CNV had high specificity in cancers, and those with high CNV level may perturb broad biological functions. Some core subpathways and cancer hallmarks widely perturbed by lncRNAs-CNV were revealed. Moreover, subpathways highlighted the functional diversity of lncRNAs-CNV in various cancers. Survival analysis indicated that functional lncRNAs-CNV could be candidate prognostic biomarkers for clinical applications, such as ST7-AS1, CDKN2B-AS1 and EGFR-AS1. In addition, cascade responses and a functional crosstalk model among lncRNAs-CNV, impacted genes, driving subpathways and cancer hallmarks were proposed for understanding the driving mechanism of lncRNAs-CNV. Finally, we developed a user-friendly web interface-LncCASE (http://bio-bigdata.hrbmu.edu.cn/LncCASE/) for exploring lncRNAs-CNV and their driving subpathways in various cancer types. Our study identified and systematically characterized lncRNAs-CNV and their driving subpathways and presented valuable resources for investigating the functionalities of non-coding variations and the mechanisms of tumorigenesis.

An activity-diary system, named Healthy, is presented in this paper. Healthy can infer users diary of physical activities and energy expenditure based on METS (Metabolic Equivalents) values via recognizing general human activities. In this system, we design a two-layer classifier which costs less energy and memory with satisfactory accuracy. Our classifier divides the activities into two categories: periodic and nonperiodic. And a different sub-classifier is applied for each category. Meanwhile, We design a state listener to recognize more complicated activities. To further improve recognition accuracy, in the second layer sub-classifier, we put forward an adaptive framing algorithm based on the period length of periodical activities to determine the time during which features are extracted. By testing Healthy in real situation, we obtained an average recognition accuracy of 98.0%.

MOTIVATION: The accurate prediction of disease status is a central challenge in clinical cancer research. Microarray-based gene biomarkers have been identified to predict outcome and outperform traditional clinical parameters. However, the robustness of the individual gene biomarkers is questioned because of their little reproducibility between different cohorts of patients. Substantial progress in treatment requires advances in methods to identify robust biomarkers. Several methods incorporating pathway information have been proposed to identify robust pathway markers and build classifiers at the level of functional categories rather than of individual genes. However, current methods consider the pathways as simple gene sets but ignore the pathway topological information, which is essential to infer a more robust pathway activity. RESULTS: Here, we propose a directed random walk (DRW)-based method to infer the pathway activity. DRW evaluates the topological importance of each gene by capturing the structure information embedded in the directed pathway network. The strategy of weighting genes by their topological importance greatly improved the reproducibility of pathway activities. Experiments on 18 cancer datasets showed that the proposed method yielded a more accurate and robust overall performance compared with several existing gene-based and pathway-based classification methods. The resulting risk-active pathways are more reliable in guiding therapeutic selection and the development of pathway-specific therapeutic strategies. AVAILABILITY: DRW is freely available at http://210.46.85.180:8080/DRWPClass/