Foundation models (FMs) have shown great promise in single-cell genomics, yet current approaches, such as scGPT, Geneformer, and scFoundation, rely on centralized training and language modeling objectives that overlook the tabular nature of single-cell data and raise significant privacy concerns. We present TABULA, a foundation model designed for single-cell transcriptomics, which integrates a novel tabular modeling objective and federated learning framework to enable privacy-preserving pretraining across decentralized datasets. TABULA directly models the cell-by-gene expression matrix through column-wise gene reconstruction and row-wise cell contrastive learning, capturing both gene-level relationships and cell-level heterogeneity without imposing artificial gene sequence order. Extensive experiments demonstrate the effectiveness of TABULA: despite using only half the pretraining data, TABULA achieves state-of-the-art performance across key tasks, including gene imputation, perturbation prediction, cell type annotation, and multi-omics integration. It is important to note that as public single-cell datasets continue to grow, TABULA provides a scalable and privacy-aware foundation that not only validates the feasibility of federated tabular modeling but also establishes a generalizable framework for training future models under similar privacy-preserving settings.

With the development of spatially resolved transcriptomics technologies, it is now possible to explore the gene expression profiles of single cells while preserving their spatial context. Spatial clustering plays a key role in spatial transcriptome data analysis. In the past 2 years, several graph neural network-based methods have emerged, which significantly improved the accuracy of spatial clustering. However, accurately identifying the boundaries of spatial domains remains a challenging task. In this article, we propose stAA, an adversarial variational graph autoencoder, to identify spatial domain. stAA generates cell embedding by leveraging gene expression and spatial information using graph neural networks and enforces the distribution of cell embeddings to a prior distribution through Wasserstein distance. The adversarial training process can make cell embeddings better capture spatial domain information and more robust. Moreover, stAA incorporates global graph information into cell embeddings using labels generated by pre-clustering. Our experimental results show that stAA outperforms the state-of-the-art methods and achieves better clustering results across different profiling platforms and various resolutions. We also conducted numerous biological analyses and found that stAA can identify fine-grained structures in tissues, recognize different functional subtypes within tumors and accurately identify developmental trajectories.

MOTIVATION: Single-cell RNA sequencing has emerged as a powerful technology for studying gene expression at the individual cell level. Clustering individual cells into distinct subpopulations is fundamental in scRNA-seq data analysis, facilitating the identification of cell types and exploration of cellular heterogeneity. Despite the recent development of many deep learning-based single-cell clustering methods, few have effectively exploited the correlations among genes, resulting in suboptimal clustering outcomes. RESULTS: Here, we propose a novel masked autoencoder-based method, scMAE, for cell clustering. scMAE perturbs gene expression and employs a masked autoencoder to reconstruct the original data, learning robust and informative cell representations. The masked autoencoder introduces a masking predictor, which captures relationships among genes by predicting whether gene expression values are masked. By integrating this masking mechanism, scMAE effectively captures latent structures and dependencies in the data, enhancing clustering performance. We conducted extensive comparative experiments using various clustering evaluation metrics on 15 scRNA-seq datasets from different sequencing platforms. Experimental results indicate that scMAE outperforms other state-of-the-art methods on these datasets. In addition, scMAE accurately identifies rare cell types, which are challenging to detect due to their low abundance. Furthermore, biological analyses confirm the biological significance of the identified cell subpopulations. AVAILABILITY AND IMPLEMENTATION: The source code of scMAE is available at: https://zenodo.org/records/10465991.

MOTIVATION: Spatial clustering is essential and challenging for spatial transcriptomics' data analysis to unravel tissue microenvironment and biological function. Graph neural networks are promising to address gene expression profiles and spatial location information in spatial transcriptomics to generate latent representations. However, choosing an appropriate graph deep learning module and graph neural network necessitates further exploration and investigation. RESULTS: In this article, we present GRAPHDeep to assemble a spatial clustering framework for heterogeneous spatial transcriptomics data. Through integrating 2 graph deep learning modules and 20 graph neural networks, the most appropriate combination is decided for each dataset. The constructed spatial clustering method is compared with state-of-the-art algorithms to demonstrate its effectiveness and superiority. The significant new findings include: (i) the number of genes or proteins of spatial omics data is quite crucial in spatial clustering algorithms; (ii) the variational graph autoencoder is more suitable for spatial clustering tasks than deep graph infomax module; (iii) UniMP, SAGE, SuperGAT, GATv2, GCN, and TAG are the recommended graph neural networks for spatial clustering tasks; and (iv) the used graph neural network in the existent spatial clustering frameworks is not the best candidate. This study could be regarded as desirable guidance for choosing an appropriate graph neural network for spatial clustering. AVAILABILITY AND IMPLEMENTATION: The source code of GRAPHDeep is available at https://github.com/narutoten520/GRAPHDeep. The studied spatial omics data are available at https://zenodo.org/record/8141084.

Advancing spatially resolved transcriptomics (ST) technologies help biologists comprehensively understand organ function and tissue microenvironment. Accurate spatial domain identification is the foundation for delineating genome heterogeneity and cellular interaction. Motivated by this perspective, a graph deep learning (GDL) based spatial clustering approach is constructed in this paper. First, the deep graph infomax module embedded with residual gated graph convolutional neural network is leveraged to address the gene expression profiles and spatial positions in ST. Then, the Bayesian Gaussian mixture model is applied to handle the latent embeddings to generate spatial domains. Designed experiments certify that the presented method is superior to other state-of-the-art GDL-enabled techniques on multiple ST datasets. The codes and dataset used in this manuscript are summarized at https://github.com/narutoten520/SCGDL.

In single-cell RNA-seq (scRNA-seq) data analysis, a fundamental problem is to determine the number of cell clusters based on the gene expression profiles. However, the performance of current methods is still far from satisfactory, presumably due to their limitations in capturing the expression variability among cell clusters. Batch effects represent the undesired variability between data measured in different batches. When data are obtained from different labs or protocols batch effects occur. Motivated by the practice of batch effect removal, we considered cell clusters as batches. We hypothesized that the number of cell clusters (i.e. batches) could be correctly determined if the variances among clusters (i.e. batch effects) were removed. We developed a new method, namely, removal of batch effect and testing (REBET), for determining the number of cell clusters. In this method, cells are first partitioned into k clusters. Second, the batch effects among these k clusters are then removed. Third, the quality of batch effect removal is evaluated with the average range of normalized mutual information (ARNMI), which measures how uniformly the cells with batch-effects-removal are mixed. By testing a range of k values, the k value that corresponds to the lowest ARNMI is determined to be the optimal number of clusters. We compared REBET with state-of-the-art methods on 32 simulated datasets and 14 published scRNA-seq datasets. The results show that REBET can accurately and robustly estimate the number of cell clusters and outperform existing methods. Contact: H.D.L. ([email protected]) or Q.S.X. ([email protected]).