MOTIVATION: The advent of single-cell RNA sequencing (scRNA-seq) technology has allowed researchers to measure gene expression profiles at the single-cell level, providing valuable insights into cellular heterogeneity. However, due to the limitations of current sequencing platforms, scRNA-seq data often contain significant noise, particularly severe dropout events, which pose major challenges for subsequent analyses. RESULTS: In this study, we developed a new method called topology-aware contrastive learning (scTACL). This approach uses contrastive learning between a cell similarity graph and a cell embedding similarity graph, employing a zero-inflated negative binomial (ZINB) distribution to model the reconstructed data. This alignment helps the processed data better reflect true biological signals. It delivers superior results in key tasks such as data imputation, clustering, batch effect correction, and cell-cell interaction. Additionally, scTACL successfully identified two distinct subtypes of epithelial cells in lung adenocarcinoma tissues, further demonstrating its effectiveness and usefulness in complex biological settings. Notably, without relying on spatial location information, scTACL still effectively distinguished the epithelial and mesenchymal regions in the spatial transcriptome data of liver cancer and identified the COLLAGEN signaling pathway, which plays a crucial role in the epithelial-mesenchymal transition process through intercellular communication analysis.

LncRNAs have been confirmed by various studies to play an important role in the generation of a variety of diseases, making the accurate prediction of IncRNA-disease associations crucial for diagnosis and therapy. However, experimentally validated associations remain scarce. To address the limitations of existing computational methods regarding biological information coverage and model robustness, we developed HGANTLDA, a novel multimodal information fusion framework. We made three key contributions: 1) integrating the Nucleotide Transformer, a gene language pre-training model, to systematically encode IncRNA sequence semantic information, enhancing sequencelevel feature representation; 2) incorporating miRNA regulatory mechanisms by constructing a heterogeneous graph of IncRNA, miRNA, and disease nodes, and employing a HAN to learn representations from complex semantic paths among these nodes; 3) developing a function similarity-based negative sample selection strategy that significantly reduced pseudo-negative sample interference, effectively improving prediction stability. Extensive experimental results demonstrate that HGANTLDA achieves superior performance, with an AUC of 98.93% and an F1-score of 97.29%, representing a 2.7% improvement over the secondranked model. We have also developed an accessible online service system (http://62.234.10.79:80/) that allows users to perform predictions, customize models, and visualize IncRNA-disease association results interactively.

The development of spatial transcriptomics (ST) technologies has enabled researchers to better understand cells' spatial organization and functional heterogeneity within their native tissue context. Spatial domain identification plays a crucial role in ST data analysis. However, most existing spatial domain identification methods do not fully exploit spatial information, and often fail to adequately integrate both local and global features, resulting in suboptimal spatial domain identification. We propose SLGCA, a novel method based on cross-level graph contrastive learning to address these challenges. SLGCA adopts a dual-channel learning mechanism, combining local-level contrastive learning based on spatial neighborhood information and global information contrastive learning across views, thereby significantly enhancing the accuracy of spatial domain identification. SLGCA can integrate multiple tissue sections without needing pre-alignment or external tools, eliminating batch effects and accurately identifying spatial domains across multiple slices. Experimental results show that SLGCA significantly outperforms the benchmark methods in spatial domain identification accuracy on ST data generated by multiple techniques. Moreover, SLGCA enables accurate dissection of tumor heterogeneity in human breast cancer datasets and effectively uncovers the heterogeneous tumor microenvironment in liver cancer, revealing two distinct fibroblast subtypes.

Transfer learning has been widely applied to drug sensitivity prediction based on single-cell RNA sequencing, leveraging knowledge from large datasets of cancer cell lines or other sources to improve the prediction of drug responses. However, previous studies require model fine-tuning for different patient single-cell datasets, limiting their ability to meet the clinical need for high-throughput rapid prediction. In this research, we introduce single-cell Adaptive Transfer and Distillation model (scATD), a transfer learning framework leveraging large language models for high-throughput drug sensitivity prediction. Based on different large language models (scFoundation and Geneformer) and transfer strategies, scATD includes three distinct sub-models: scATD-sf, scATD-gf, and scATD-sf-dist. scATD-sf and scATD-gf employs an important bidirectional style transfer to enable predictions for new patients without model parameter training. Additionally, scATD-sf-dist uses knowledge distillation from large models to enhance prediction performance, improve efficiency, and reduce resource requirements. Benchmarking across more diverse datasets demonstrates scATD's superior accuracy, generalization and efficiency. Besides, by rigorously selecting reference background samples for feature attribution algorithms, scATD also provides more meaningful insights into the relationship between gene expression and drug resistance mechanisms. Making scATD more interpretability for addressing critical challenges in precision oncology.

Single-cell multi-omics sequencing allows researchers to simultaneously sequence multiple types of molecular information from the same individual cell, like transcriptomics and proteomics. However, the research of identifying cell types from single-cell multi-omics data is still challenging. In this article, we proposed scEAGC, an efficient anchor graph clustering for single-cell transcriptomics and proteomics data. It first constructs anchor cell graphs for every omics and then integrates separated omics-specific anchor cell graphs on a weighted multi-view clustering model with F-norm and the Orthogonal constraint, finally through the divided iterative optimization method to obtain cluster partition without any extra post-processing. Since scEAGC combines the high-efficiency property of anchor graph clustering, its efficiency is substantially higher than widely used algorithms. Extensive experiments demonstrate that, compared to other state-of-the-art clustering algorithms, scEAGC can boost clustering accuracy and robustness and detect the new cell subtypes in CITE-seq and scRNA-seq data.

Advancing in single-cell RNA sequencing techniques enhances the resolution of cell heterogeneity study. Density-based unsupervised clustering has the potential to detect the representative anchor points and the number of clusters automatically. Meanwhile, discovering the true cell type of scRNA-seq data in the unsupervised scenario is still challenging. To this end, we proposed a tensor shared nearest neighbor anchor clustering for scRNA-seq data, named scTSNN, which first makes use of the tensor affinity learning module to mine the local-global balanced topological structures among cells, next designs density-based shared nearest neighbor measurement method to automatically detect anchor cells, finally partitions the non-anchor cells to obtain the clustering results. Validated on synthetic datasets and scRNA-seq datasets, scTSNN not only exactly detects the complicated structures but also has better performance in accuracy and robustness compared with the state-of-the-art methods. Moreover, case studies on mammalian cells and cervical cancer tumor cells demonstrate the selected anchor cells of scTSNN benefit the cell pseudotime inference and rare cell identification, which show good application and research value of scTSNN.

Single-cell RNA sequencing (scRNA-seq) is a new technology that focuses on the expression levels for each cell to study cell heterogeneity. Thus, new computational methods matching scRNA-seq are designed to detect cell types among various cell groups. Herein, we propose a Multi-scale Tensor Graph Diffusion Clustering (MTGDC) for single-cell RNA sequencing data. It has the following mechanisms: 1) To mine potential similarity distributions among cells, we design a multi-scale affinity learning method to construct a fully connected graph between cells; 2) For each affinity matrix, we propose an efficient tensor graph diffusion learning framework to learn high-order information among multi-scale affinity matrices. First, the tensor graph is explicitly introduced to measure cell-cell edges with local high-order relationship information. To further preserve more global topology structure information in the tensor graph, MTGDC implicitly considers the propagation of information via a data diffusion process by designing a simple and efficient tensor graph diffusion update algorithm. 3) Finally, we mix together the multi-scale tensor graphs to obtain the fusion high-order affinity matrix and apply it to spectral clustering. Experiments and case studies showed that MTGDC had obvious advantages over the state-of-art algorithms in robustness, accuracy, visualization, and speed.

Single-cell RNA sequencing (scRNA-seq) is a new technology different from previous sequencing methods that measure the average expression level for each gene across a large population of cells. Thus, new computational methods are required to reveal cell types among cell populations. We present a clustering ensemble algorithm using optimized multiobjective particle (CEMP). It is featured with several mechanisms: 1) A multi-subspace projection method for mapping the original data to low-dimensional subspaces is applied in order to detect complex data structure at both gene level and sample level. 2) The basic partition module in different subspaces is utilized to generate clustering solutions. 3) A transforming representation between clusters and particles is used to bridge the gap between the discrete clustering ensemble optimization problem and the continuous multiobjective optimization algorithm. 4) We propose a clustering ensemble optimization. To guide the multiobjective ensemble optimization process, three cluster metrics are embedded into CEMP as objective functions in which the final clustering will be dynamically evaluated. Experiments on 9 real scRNA-seq datasets indicated that CEMP had superior performance over several other clustering algorithms in clustering accuracy and robustness. The case study conducted on mouse neuronal cells identified main cell types and cell subtypes successfully.

The ubiquitous dropout problem in single-cell RNA sequencing technology causes a large amount of data noise in the gene expression profile. For this reason, we propose an evolutionary sparse imputation (ESI) algorithm for single-cell transcriptomes, which constructs a sparse representation model based on gene regulation relationships between cells. To solve this model, we design an optimization framework based on nondominated sorting genetics. This framework takes into account the topological relationship between cells and the variety of gene expression to iteratively search the global optimal solution, thereby learning the Pareto optimal cell-cell affinity matrix. Finally, we use the learned sparse relationship model between cells to improve data quality and reduce data noise. In simulated datasets, scESI performed significantly better than benchmark methods with various metrics. By applying scESI to real scRNA-seq datasets, we discovered scESI can not only further classify the cell types and separate cells in visualization successfully but also improve the performance in reconstructing trajectories differentiation and identifying differentially expressed genes. In addition, scESI successfully recovered the expression trends of marker genes in stem cell differentiation and can discover new cell types and putative pathways regulating biological processes.

The outbreak of acute respiratory disease in 2019, namely Coronavirus Disease-2019 (COVID-19), has become an unprecedented healthcare crisis. To mitigate the pandemic, there are a lot of collective and multidisciplinary efforts in facilitating the rapid discovery of protein inhibitors or drugs against COVID-19. Although many computational methods to predict protein inhibitors have been developed [ 1- 5], few systematic reviews on these methods have been published. Here, we provide a comprehensive overview of the existing methods to discover potential inhibitors of COVID-19 virus, so-called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). First, we briefly categorize and describe computational approaches by the basic algorithms involved in. Then we review the related biological datasets used in such predictions. Furthermore, we emphatically discuss current knowledge on SARS-CoV-2 inhibitors with the latest findings and development of computational methods in uncovering protein inhibitors against COVID-19.