Identifying multicellular spatiotemporal organization of cells with SpaceFlow

ONTraC characterizes spatially continuous variations of tissue microenvironment through niche trajectory analysis

Recent technological advances enable mapping of tissue spatial organization at single-cell resolution, but methods for analyzing spatially continuous microenvironments are still lacking. We introduce ONTraC, a graph neural network-based framework for constructing spatial trajectories at niche-level. Through benchmarking analyses using multiple simulated and real datasets, we show that ONTraC outperforms existing methods. ONTraC captures both normal anatomical structures and disease-associated tissue microenvironment changes. In addition, it identifies tissue microenvironment-dependent shifts in gene expression, regulatory network, and cell-cell interaction patterns. Taken together, ONTraC provides a useful framework for characterizing the structural and functional organization of tissue microenvironments.

Unravelling tumour spatiotemporal heterogeneity using spatial multimodal data

Analysing the genome, epigenome, transcriptome, proteome, and metabolome within the spatial context of cells has transformed our understanding of tumour spatiotemporal heterogeneity. Advances in spatial multi-omics technologies now reveal complex molecular interactions shaping cellular behaviour and tissue dynamics. This review highlights key technologies and computational methods that have advanced spatial domain identification and their pseudo-relations, as well as inference of intra- and inter-cellular molecular networks that drive disease progression. We also discuss strategies to address major challenges, including data sparsity, high-dimensionality, scalability, and heterogeneity. Furthermore, we outline how spatial multi-omics enables novel insights into disease mechanisms, advancing precision medicine and informing targeted therapies. KEY POINTS: Advancements in spatial multi-omics facilitate our understanding of tumour spatiotemporal heterogeneity. AI-driven multimodal models uncover complex molecular interactions that underlie cellular behaviours and tissue dynamics. Combining multi-omics technologies and AI-enabled bioinformatics tools helps predict critical disease stages, such as pre-cancer, advancing precision medicine, and informing targeted therapeutic strategies.

Exploring the Latent Information in Spatial Transcriptomics Data via Multi-View Graph Convolutional Network Based on Implicit Contrastive Learning

Latest developments in spatial transcriptomics enable thoroughly profiling of gene expression while preserving tissue microenvironment. Connecting gene expression with spatial arrangement is key for precise spatial domain identification, enhancing the comprehension of tissue microenvironments and biological processes. However, accurately analyzing spatial domains with similar gene expression and histological features is still challenging. This study introduces STMIGCL, a novel framework that leverages a multi-view graph convolutional network and implicit contrastive learning. First, it creates neighbor graphs from gene expression and spatial coordinates, and then combines these with gene expression through multi-view learning to learn low-dimensional representations. To further refine the obtained low-dimensional representations, a graph contrastive learning method with contrastive enhancement in the latent space is employed, aiming to better capture critical information in the data and improve the accuracy and discriminative power of the embeddings. Finally, an attention mechanism is used to adaptively integrate different views, capturing the importance of spots in various views to obtain the final spot representation. Experimental data confirms that STMIGCL significantly enhances spatial domain recognition precision and outperforms all baseline methods in tasks such as trajectory inference and Spatially Variable Genes (SVGs) recognition.

Temporal and spatial omics technologies for 4D profiling

Cells have distinct molecular repertoires on their surfaces and unique intracellular biomolecular profiles that play pivotal roles in orchestrating a myriad of biological responses in the context of growth, development and disease. A persistent challenge in the deep exploration of these cues has been in our inability to effectively and precisely capture the temporal and spatial characteristics of living cells. In this Perspective, we delve into techniques for temporal and two- and three-dimensional spatial omics analyses and underscore how their harmonious fusion promises to unlock insights into the dynamics and diversity of individual cells within biological systems such as tissues and organoids. We then explore four-dimensional profiling, a nascent but promising frontier that adds a temporal (fourth-dimension) component to three-dimensional omics; highlight the advancements, challenges and gaps in the field; and discuss potential strategies for further technological development.

Benchmarking computational methods for detecting spatial domains and domain-specific spatially variable genes from spatial transcriptomics data

Advances in spatially resolved transcriptomics (SRT) have led to the emergence of numerous computational methods for identifying spatial domains and spatially variable genes (SVGs); however, a comprehensive assessment of existing methods is lacking. We comprehensively benchmarked 19 methods for detecting spatial domains and domain-specific SVGs from SRT data, using 30 real-world datasets covering six SRT technologies and 27 synthetic datasets. We first evaluated the performance of these methods on spatial domain identification in terms of accuracy, stability, generalizability, and scalability. Results reveal that there is no single method that works best for all datasets, and the optimal method depends on the data, especially the SRT platform. Further, we proposed a quantitative strategy to evaluate domain-specific SVG recognition results and assessed the impact of spatial domains on SVG detection. We found that SVG detection based on spatial domains identified by different GNN methods have high accuracy but low concordance. Generally, the more accurate the recognized spatial domains, the higher the number and accuracy of domain-specific SVGs detected. Moreover, integrating spatial clustering results from different methods can lead to more robust and better clustering and SVG results. Practical guidelines were provided for choosing appropriate methods for spatial domain and domain-specific SVG identification.

Quantitative characterization of cell niches in spatially resolved omics data

Spatial omics enable the characterization of colocalized cell communities that coordinate specific functions within tissues. These communities, or niches, are shaped by interactions between neighboring cells, yet existing computational methods rarely leverage such interactions for their identification and characterization. To address this gap, here we introduce NicheCompass, a graph deep-learning method that models cellular communication to learn interpretable cell embeddings that encode signaling events, enabling the identification of niches and their underlying processes. Unlike existing methods, NicheCompass quantitatively characterizes niches based on communication pathways and consistently outperforms alternatives. We show its versatility by mapping tissue architecture during mouse embryonic development and delineating tumor niches in human cancers, including a spatial reference mapping application. Finally, we extend its capabilities to spatial multi-omics, demonstrate cross-technology integration with datasets from different sequencing platforms and construct a whole mouse brain spatial atlas comprising 8.4 million cells, highlighting NicheCompass' scalability. Overall, NicheCompass provides a scalable framework for identifying and analyzing niches through signaling events.

Transfer learning of multicellular organization via single-cell and spatial transcriptomics

Biological tissues exhibit complex gene expression and multicellular patterns that are valuable to dissect. Single-cell RNA sequencing (scRNA-seq) provides full coverages of genes, but lacks spatial information, whereas spatial transcriptomics (ST) measures spatial locations of individual or group of cells, with more restrictions on gene information. Here we show a transfer learning method named iSORT to decipher spatial organization of cells by integrating scRNA-seq and ST data. iSORT trains a neural network that maps gene expressions to spatial locations. iSORT can find spatial patterns at single-cell scale, identify spatial-organizing genes (SOGs) that drive the patterning, and infer pseudo-growth trajectories using a concept of SpaRNA velocity. Benchmarking on a range of biological systems, such as human cortex, mouse embryo, mouse brain, Drosophila embryo, and human developmental heart, demonstrates iSORT's accuracy and practicality in reconstructing multicellular organization. We further conducted scRNA-seq and ST sequencing from normal and atherosclerotic arteries, and the functional enrichment analysis shows that SOGs found by iSORT are strongly associated with vascular structural anomalies.

Integrating multiple spatial transcriptomics data using community-enhanced graph contrastive learning

Due to the rapid development of spatial sequencing technologies, large amounts of spatial transcriptomic datasets have been generated across various technological platforms or different biological conditions (e.g., control vs. treatment). Spatial transcriptomics data coming from different platforms usually has different resolutions. Moreover, current methods do not consider the heterogeneity of spatial structures within and across slices when modeling spatial transcriptomics data with graph-based methods. In this study, we propose a community-enhanced graph contrastive learning-based method named Tacos to integrate multiple spatial transcriptomics data. We applied Tacos to several real datasets coming from different platforms under different scenarios. Systematic benchmark analyses demonstrate Tacos's superior performance in integrating different slices. Furthermore, Tacos can accurately denoise the spatially resolved transcriptomics data.

Protocol to boost the robustness and accuracy of spatial transcriptomics algorithms using ensemble techniques

Spatial transcriptomics enhances our understanding of cellular organization by mapping gene expression data to precise tissue locations. Here, we present a protocol for using weighted ensemble method for spatial transcriptomics (WEST), which uses ensemble techniques to boost the robustness and accuracy of existing algorithms. We describe steps for preprocessing data, obtaining embeddings from individual algorithms, and ensemble integrating all embeddings as a similarity matrix. We then detail procedures for using the similarity matrix to identify spatial domains and obtain new embeddings. For complete details on the use and execution of this protocol, please refer to Cai et al.1.

Accurate trajectory inference in time-series spatial transcriptomics with structurally-constrained optimal transport

New experimental and computational methods use genetic or gene expression observations with single cell resolution to study the relationship between single-cell molecular profiles and developmental trajectories. Most tissues contain spatially contiguous regions that develop as a unit, such as follicles in the ovary, or tubules and glomeruli in the kidney. We find that existing approaches designed to use time series spatial transcriptomics (ST) data produce biologically incoherent trajectories that fail to maintain these structural units over time. We present Spatiotemporal Optimal transport with Contiguous Structures (SOCS), an Optimal Transport-based trajectory inference method for time-series ST that produces trajectory inferences preserving the structural integrity of contiguous biologically meaningful units, along with gene expression similarity and global geometric structure. We show that SOCS produces more plausible trajectory estimates, maintaining the spatial coherence of biological structures across time, enabling more accurate trajectory inference and biological insight than other approaches.

Quantifying and interpreting biologically meaningful spatial signatures within tumor microenvironments

The tumor microenvironment (TME) plays a crucial role in orchestrating tumor cell behavior and cancer progression. Recent advances in spatial profiling technologies have uncovered novel spatial signatures, including univariate distribution patterns, bivariate spatial relationships, and higher-order structures. These signatures have the potential to revolutionize tumor mechanism and treatment. In this review, we summarize the current state of spatial signature research, highlighting computational methods to uncover spatially relevant biological significance. We discuss the impact of these advances on fundamental cancer biology and translational research, address current challenges and future research directions.

Graph neural networks for single-cell omics data: a review of approaches and applications

Rapid advancement of sequencing technologies now allows for the utilization of precise signals at single-cell resolution in various omics studies. However, the massive volume, ultra-high dimensionality, and high sparsity nature of single-cell data have introduced substantial difficulties to traditional computational methods. The intricate non-Euclidean networks of intracellular and intercellular signaling molecules within single-cell datasets, coupled with the complex, multimodal structures arising from multi-omics joint analysis, pose significant challenges to conventional deep learning operations reliant on Euclidean geometries. Graph neural networks (GNNs) have extended deep learning to non-Euclidean data, allowing cells and their features in single-cell datasets to be modeled as nodes within a graph structure. GNNs have been successfully applied across a broad range of tasks in single-cell data analysis. In this survey, we systematically review 107 successful applications of GNNs and their six variants in various single-cell omics tasks. We begin by outlining the fundamental principles of GNNs and their six variants, followed by a systematic review of GNN-based models applied in single-cell epigenomics, transcriptomics, spatial transcriptomics, proteomics, and multi-omics. In each section dedicated to a specific omics type, we have summarized the publicly available single-cell datasets commonly utilized in the articles reviewed in that section, totaling 77 datasets. Finally, we summarize the potential shortcomings of current research and explore directions for future studies. We anticipate that this review will serve as a guiding resource for researchers to deepen the application of GNNs in single-cell omics.

Multi-Manifolds fusing hyperbolic graph network balanced by pareto optimization for identifying spatial domains of spatial transcriptomics

Identifying spatial domains for spatial transcriptomics is crucial for achieving comprehensive insights into the pathogenesis of gene expression. Increasingly, computational methods based on graph neural networks are being developed for spatial transcriptomics. However, previous methods have solely focused on the Euclidean manifold. To effectively exploit and explore the informative and deeper topological structures of inherent manifolds, we presented a Multi-Manifolds fusing hyperbolic graph network, balanced by Pareto optimization, for identifying spatial domains in Spatial Transcriptomics (MManiST). First, we developed multi-manifolds encoders for distinct manifolds using the hyperbolic neural network. Features from different manifolds were then combined using an attention mechanism, with multiple reconstruction losses balanced by Pareto optimization. Extensive experiments on commonly used benchmark datasets show that our method consistently outperforms seven state-of-the-art methods. Additionally, we investigated the validity of each component and the impact of fusion methods in ablation experiments.

stDyer enables spatial domain clustering with dynamic graph embedding

Spatially resolved transcriptomics (SRT) data provide critical insights into gene expression patterns within tissue contexts, necessitating effective methods for identifying spatial domains. We introduce stDyer, an end-to-end deep learning framework for spatial domain clustering in SRT data. stDyer combines Gaussian Mixture Variational AutoEncoder with graph attention networks to learn embeddings and perform clustering. Its dynamic graphs adaptively link units based on Gaussian Mixture assignments, improving clustering and producing smoother domain boundaries. stDyer's mini-batch strategy and multi-GPU support facilitate scalability to large datasets. Benchmarking against state-of-the-art tools, stDyer demonstrates superior performance in spatial domain clustering, multi-slice analysis, and large-scale dataset handling.

STANCE: a unified statistical model to detect cell-type-specific spatially variable genes in spatial transcriptomics

One of the major challenges in spatial transcriptomics is to detect spatially variable genes (SVGs), whose expression patterns are non-random across tissue locations. Many SVGs correlate with cell type compositions, introducing the concept of cell type-specific SVGs (ctSVGs). Existing ctSVG detection methods treat cell type-specific spatial effects as fixed effects, leading to tissue spatial rotation-dependent results. Moreover, SVGs may exhibit random spatial patterns within cell types, meaning an SVG is not always a ctSVG, and vice versa, further complicating detection. We propose STANCE, a unified statistical model for both SVGs and ctSVGs detection under a linear mixed-effect model framework that integrates gene expression, spatial location, and cell type composition information. STANCE ensures tissue rotation-invariant results, with a two-stage approach: initial SVG/ctSVG detection followed by ctSVG-specific testing. We demonstrate its performance through extensive simulations and analyses of public datasets. Downstream analyses reveal STANCE's potential in spatial transcriptomics analysis.

Identification and characterization of cell niches in tissue from spatial omics data at single-cell resolution

Deciphering the features, structure, and functions of the cell niche in tissues remains a major challenge. Here, we present scNiche, a computational framework to identify and characterize cell niches from spatial omics data at single-cell resolution. We benchmark scNiche with both simulated and biological datasets, and demonstrate that scNiche can effectively and robustly identify cell niches while outperforming other existing methods. In spatial proteomics data from human triple-negative breast cancer, scNiche reveals the influence of the microenvironment on cellular phenotypes, and further dissects patient-specific niches with distinct cellular compositions or phenotypic characteristics. By analyzing mouse liver spatial transcriptomics data across normal and early-onset liver failure donors, scNiche uncovers disease-specific liver injury niches, and further delineates the niche remodeling from normal liver to liver failure. Overall, scNiche enables decoding the cellular microenvironment in tissues from single-cell spatial omics data.

Mapping the topography of spatial gene expression with interpretable deep learning

Spatially resolved transcriptomics technologies provide high-throughput measurements of gene expression in a tissue slice, but the sparsity of these data complicates analysis of spatial gene expression patterns. We address this issue by deriving a topographic map of a tissue slice-analogous to a map of elevation in a landscape-using a quantity called the isodepth. Contours of constant isodepths enclose domains with distinct cell type composition, while gradients of the isodepth indicate spatial directions of maximum change in expression. We develop GASTON (gradient analysis of spatial transcriptomics organization with neural networks), an unsupervised and interpretable deep learning algorithm that simultaneously learns the isodepth, spatial gradients and piecewise linear expression functions that model both continuous gradients and discontinuous variation in gene expression. We show that GASTON accurately identifies spatial domains and marker genes across several tissues, gradients of neuronal differentiation and firing in the brain, and gradients of metabolism and immune activity in the tumor microenvironment.

Dimensionality reduction for visualizing spatially resolved profiling data using SpaSNE

BACKGROUND

Spatially resolved profiling technologies to quantify transcriptomes, epigenomes, and proteomes have been emerging as groundbreaking methods for comprehensive molecular characterizations. Dimensionality reduction and visualization is an essential step to analyze and interpret spatially resolved profiling data. However, state-of-the-art dimensionality reduction methods for single-cell sequencing data, such as the t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP), were not tailored for spatially resolved profiling data.

RESULTS

Here we developed a spatially resolved t-SNE (SpaSNE) method to integrate both spatial and molecular information. We applied it to a variety of public spatially resolved profiling datasets that were generated from 3 experimental platforms and consisted of cells from different diseases, tissues, and cell types. To compare the performances of SpaSNE, t-SNE, and UMAP, we applied them to 4 spatially resolved profiling datasets obtained from 3 distinct experimental platforms (Visium, STARmap, and MERFISH) on both diseased and normal tissues. Comparisons between SpaSNE and these state-of-the-art approaches reveal that SpaSNE achieves more accurate and meaningful visualization that better elucidates the underlying spatial and molecular data structures.

CONCLUSIONS

This work demonstrates the broad application of SpaSNE for reliable and robust interpretation of cell types based on both molecular and spatial information, which can set the foundation for many subsequent analysis steps, such as differential gene expression and trajectory or pseudotime analysis on the spatially resolved profiling data.

Cooperative integration of spatially resolved multi-omics data with COSMOS

Recent advancements in biological technologies have enabled the measurement of spatially resolved multi-omics data, yet computational algorithms for this purpose are scarce. Existing tools target either single omics or lack spatial integration. We generate a graph neural network algorithm named COSMOS to address this gap and demonstrated the superior performance of COSMOS in domain segmentation, visualization, and spatiotemporal map for spatially resolved multi-omics data integration tasks.

Single-cell omics: experimental workflow, data analyses and applications

Cells are the fundamental units of biological systems and exhibit unique development trajectories and molecular features. Our exploration of how the genomes orchestrate the formation and maintenance of each cell, and control the cellular phenotypes of various organismsis, is both captivating and intricate. Since the inception of the first single-cell RNA technology, technologies related to single-cell sequencing have experienced rapid advancements in recent years. These technologies have expanded horizontally to include single-cell genome, epigenome, proteome, and metabolome, while vertically, they have progressed to integrate multiple omics data and incorporate additional information such as spatial scRNA-seq and CRISPR screening. Single-cell omics represent a groundbreaking advancement in the biomedical field, offering profound insights into the understanding of complex diseases, including cancers. Here, we comprehensively summarize recent advances in single-cell omics technologies, with a specific focus on the methodology section. This overview aims to guide researchers in selecting appropriate methods for single-cell sequencing and related data analysis.

Accurate Spatial Heterogeneity Dissection and Gene Regulation Interpretation for Spatial Transcriptomics using Dual Graph Contrastive Learning

Recent advances in spatial transcriptomics have enabled simultaneous preservation of high-throughput gene expression profiles and the spatial context, enabling high-resolution exploration of distinct regional characterization in tissue. To effectively understand the underlying biological mechanisms within tissue microenvironments, there is a requisite for methods that can accurately capture external spatial heterogeneity and interpret internal gene regulation from spatial transcriptomics data. However, current methods for region identification often lack the simultaneous characterizing of spatial structure and gene regulation, thereby limiting the ability of spatial dissection and gene interpretation. Here, stDCL is developed, a dual graph contrastive learning method to identify spatial domains and interpret gene regulation in spatial transcriptomics data. stDCL adaptively incorporates gene expression data and spatial information via a graph embedding autoencoder, thereby preserving critical information within the latent embedding representations. In addition, dual graph contrastive learning is proposed to train the model, ensuring that the latent embedding representation closely resembles the actual spatial distribution and exhibits cluster similarity. Benchmarking stDCL against other state-of-the-art clustering methods using complex cortex datasets demonstrates its superior accuracy and effectiveness in identifying spatial domains. Our analysis of the imputation matrices generated by stDCL reveals its capability to reconstruct spatial hierarchical structures and refine differential expression assessment. Furthermore, it is demonstrated that the versatility of stDCL in interpretability of gene regulation, spatial heterogeneity at high resolution, and embryonic developmental patterns. In addition, it is also showed that stDCL can successfully annotate disease-associated astrocyte subtypes in Alzheimer's disease and unravel multiple relevant pathways and regulatory mechanisms.

ImSpiRE: image feature-aided spatial resolution enhancement method

The resolution of most spatially resolved transcriptomic technologies usually cannot attain the single-cell level, limiting their applications in biological discoveries. Here, we introduce ImSpiRE, an image feature-aided spatial resolution enhancement method for in situ capturing spatial transcriptome. Taking the information stored in histological images, ImSpiRE solves an optimal transport problem to redistribute the expression profiles of spots to construct new transcriptional profiles with enhanced resolution, together with extending the gene expression profiles into unmeasured regions. Applications to multiple datasets confirm that ImSpiRE can enhance spatial resolution to the subspot level while contributing to the discovery of tissue domains, signaling communication patterns, and spatiotemporal characterization.

SpaInGNN: Enhanced clustering and integration of spatial transcriptomics based on refined graph neural networks

Recent developments in spatial transcriptomics (ST) technology have markedly enhanced the proposed capacity to comprehensively characterize gene expression patterns within tissue microenvironments while crucially preserving spatial context. However, the identification of spatial domains at the single-cell level remains a significant challenge in elucidating biological processes. To address this, SpaInGNN was developed, a sophisticated graph neural network (GNN) framework that accurately delineates spatial domains by integrating spatial location data, histological information, and gene expression profiles into low-dimensional latent embeddings. Additionally, to fully leverage spatial coordinate data, spatial integration using graph neural network (SpaInGNN) refines the graph constructed for spatial locations by incorporating both tissue image distance and Euclidean distance, following a pre-clustering of gene expression profiles. This refined graph is then embedded using a self-supervised GNN, which minimizes self-reconfiguration loss. By applying SpaInGNN to refined graphs across multiple consecutive tissue slices, this study mitigates the impact of batch effects in data analysis. The proposed method demonstrates substantial improvements in the accuracy of spatial domain recognition, providing a more faithful representation of the tissue organization in both mouse olfactory bulb and human lateral prefrontal cortex samples.

Profiling cell identity and tissue architecture with single-cell and spatial transcriptomics

Single-cell transcriptomics has broadened our understanding of cellular diversity and gene expression dynamics in healthy and diseased tissues. Recently, spatial transcriptomics has emerged as a tool to contextualize single cells in multicellular neighbourhoods and to identify spatially recurrent phenotypes, or ecotypes. These technologies have generated vast datasets with targeted-transcriptome and whole-transcriptome profiles of hundreds to millions of cells. Such data have provided new insights into developmental hierarchies, cellular plasticity and diverse tissue microenvironments, and spurred a burst of innovation in computational methods for single-cell analysis. In this Review, we discuss recent advancements, ongoing challenges and prospects in identifying and characterizing cell states and multicellular neighbourhoods. We discuss recent progress in sample processing, data integration, identification of subtle cell states, trajectory modelling, deconvolution and spatial analysis. Furthermore, we discuss the increasing application of deep learning, including foundation models, in analysing single-cell and spatial transcriptomics data. Finally, we discuss recent applications of these tools in the fields of stem cell biology, immunology, and tumour biology, and the future of single-cell and spatial transcriptomics in biological research and its translation to the clinic.

SpaGRA: Graph augmentation facilitates domain identification for spatially resolved transcriptomics

Recent advances in spatially resolved transcriptomics (SRT) have provided new opportunities for characterizing spatial structures of various tissues. Graph-based geometric deep learning has gained widespread adoption for spatial domain identification tasks. Currently, most methods define adjacency relation between cells or spots by their spatial distance in SRT data, which overlooks key biological interactions like gene expression similarities, and leads to inaccuracies in spatial domain identification. To tackle this challenge, we propose a novel method, SpaGRA (https://github.com/sunxue-yy/SpaGRA), for automatic multi-relationship construction based on graph augmentation. SpaGRA uses spatial distance as prior knowledge and dynamically adjusts edge weights with multi-head graph attention networks (GATs). This helps SpaGRA to uncover diverse node relationships and enhance message passing in geometric contrastive learning. Additionally, SpaGRA uses these multi-view relationships to construct negative samples, addressing sampling bias posed by random selection. Experimental results show that SpaGRA presents superior domain identification performance on multiple datasets generated from different protocols. Using SpaGRA, we analyze the functional regions in the mouse hypothalamus, identify key genes related to heart development in mouse embryos, and observe cancer-associated fibroblasts enveloping cancer cells in the latest Visium HD data. Overall, SpaGRA can effectively characterize spatial structures across diverse SRT datasets.

PCA-based spatial domain identification with state-of-the-art performance

MOTIVATION

The identification of biologically meaningful domains is a central step in the analysis of spatial transcriptomic data.

RESULTS

Following Occam's razor, we show that a simple PCA-based algorithm for unsupervised spatial domain identification rivals the performance of ten competing state-of-the-art methods across six single-cell spatial transcriptomic datasets. Our reductionist approach, NichePCA, provides researchers with intuitive domain interpretation and excels in execution speed, robustness, and scalability.

AVAILABILITY AND IMPLEMENTATION

The code is available at https://github.com/imsb-uke/nichepca.

A comprehensive review of approaches for spatial domain recognition of spatial transcriptomes

In current bioinformatics research, spatial transcriptomics (ST) as a rapidly evolving technology is gradually receiving widespread attention from researchers. Spatial domains are regions where gene expression and histology are consistent in space, and detecting spatial domains can better understand the organization and functional distribution of tissues. Spatial domain recognition is a fundamental step in the process of ST data interpretation, which is also a major challenge in ST analysis. Therefore, developing more accurate, efficient, and general spatial domain recognition methods has become an important and urgent research direction. This article aims to review the current status and progress of spatial domain recognition research, explore the advantages and limitations of existing methods, and provide suggestions and directions for future tool development.

A comprehensive overview of graph neural network-based approaches to clustering for spatial transcriptomics

Spatial transcriptomics technologies enable researchers to accurately quantify and localize messenger ribonucleic acid (mRNA) transcripts at a high resolution while preserving their spatial context. The identification of spatial domains, or the task of spatial clustering, plays a crucial role in investigating data on spatial transcriptomes. One promising approach for classifying spatial domains involves the use of graph neural networks (GNNs) by leveraging gene expressions, spatial locations, and histological images. This study provided a comprehensive overview of the most recent GNN-based methods of spatial clustering methods for the analysis of data on spatial transcriptomics. We extensively evaluated the performance of current methods on prevalent datasets of spatial transcriptomics by considering their accuracy of clustering, robustness, data stabilization, relevant requirements, computational efficiency, and memory use. To this end, we explored 60 clustering scenarios by extending the essential frameworks of spatial clustering for the selection of the GNNs, algorithms of downstream clustering, principal component analysis (PCA)-based reduction, and refined methods of correction. We comparatively analyzed the performance of the methods in terms of spatial clustering to identify their limitations and outline future directions of research in the field. Our survey yielded novel insights, and provided motivation for further investigating spatial transcriptomics.

Spatial domains identification in spatial transcriptomics using modality-aware and subspace-enhanced graph contrastive learning

Spatial transcriptomics (ST) technologies have emerged as an effective tool to identify the spatial architecture of tissues, facilitating a comprehensive understanding of organ function and the tissue microenvironment. Spatial domain identification is the first and most critical step in ST data analysis, which requires thoughtful utilization of tissue microenvironment and morphological priors. Here, we propose a graph contrastive learning framework, GRAS4T, which combines contrastive learning and a subspace analysis model to accurately distinguish different spatial domains by capturing the tissue microenvironment through self-expressiveness of spots within the same domain. To uncover the pertinent features for spatial domain identification, GRAS4T employs a graph augmentation based on histological image priors, preserving structural information crucial for the clustering task. Experimental results on eight ST datasets from five different platforms show that GRAS4T outperforms five state-of-the-art competing methods. Significantly, GRAS4T excels at separating distinct tissue structures and unveiling more detailed spatial domains. GRAS4T combines the advantages of subspace analysis and graph representation learning with extensibility, making it an ideal framework for ST domain identification.

Deciphering spatial domains from spatially resolved transcriptomics through spatially regularized deep graph networks

BACKGROUND

Recent advancements in spatially resolved transcriptomics (SRT) have opened up unprecedented opportunities to explore gene expression patterns within spatial contexts. Deciphering spatial domains is a critical task in spatial transcriptomic data analysis, aiding in the elucidation of tissue structural heterogeneity and biological functions. However, existing spatial domain detection methods ignore the consistency of expression patterns and spatial arrangements between spots, as well as the severe gene dropout phenomenon present in SRT data, resulting in suboptimal performance in identifying tissue spatial heterogeneity.

RESULTS

In this paper, we introduce a novel framework, spatially regularized deep graph networks (SR-DGN), which integrates gene expression profiles with spatial information to learn spatially-consistent and informative spot representations. Specifically, SR-DGN employs graph attention networks (GAT) to adaptively aggregate gene expression information from neighboring spots, considering local expression patterns between spots. In addition, the spatial regularization constraint ensures the consistency of neighborhood relationships between physical and embedded spaces in an end-to-end manner. SR-DGN also employs cross-entropy (CE) loss to model gene expression states, effectively mitigating the impact of noisy gene dropouts.

CONCLUSIONS

Experimental results demonstrate that SR-DGN outperforms state-of-the-art methods in spatial domain identification across SRT data from different sequencing platforms. Moreover, SR-DGN is capable of recovering known microanatomical structures, yielding clearer low-dimensional visualizations and more accurate spatial trajectory inferences.

MCGAE: unraveling tumor invasion through integrated multimodal spatial transcriptomics

Spatially Resolved Transcriptomics (SRT) serves as a cornerstone in biomedical research, revealing the heterogeneity of tissue microenvironments. Integrating multimodal data including gene expression, spatial coordinates, and morphological information poses significant challenges for accurate spatial domain identification. Herein, we present the Multi-view Contrastive Graph Autoencoder (MCGAE), a cutting-edge deep computational framework specifically designed for the intricate analysis of spatial transcriptomics (ST) data. MCGAE advances the field by creating multi-view representations from gene expression and spatial adjacency matrices. Utilizing modular modeling, contrastive graph convolutional networks, and attention mechanisms, it generates modality-specific spatial representations and integrates them into a unified embedding. This integration process is further enriched by the inclusion of morphological image features, markedly enhancing the framework's capability to process multimodal data. Applied to both simulated and real SRT datasets, MCGAE demonstrates superior performance in spatial domain detection, data denoising, trajectory inference, and 3D feature extraction, outperforming existing methods. Specifically, in colorectal cancer liver metastases, MCGAE integrates histological and gene expression data to identify tumor invasion regions and characterize cellular molecular regulation. This breakthrough extends ST analysis and offers new tools for cancer and complex disease research.

Deconvolution of spatial transcriptomics data via graph contrastive learning and partial least square regression

Deciphering the cellular abundance in spatial transcriptomics (ST) is crucial for revealing the spatial architecture of cellular heterogeneity within tissues. However, some of the current spatial sequencing technologies are in low resolutions, leading to each spot having multiple heterogeneous cells. Additionally, current spatial deconvolution methods lack the ability to utilize multi-modality information such as gene expression and chromatin accessibility from single-cell multi-omics data. In this study, we introduce a graph Contrastive Learning and Partial Least Squares regression-based method, CLPLS, to deconvolute ST data. CLPLS is a flexible method that it can be extended to integrate ST data and single-cell multi-omics data, enabling the exploration of the spatially epigenomic heterogeneity. We applied CLPLS to both simulated and real datasets coming from different platforms. Benchmark analyses with other methods on these datasets show the superior performance of CLPLS in deconvoluting spots in single cell level.

STMGraph: spatial-context-aware of transcriptomes via a dual-remasked dynamic graph attention model

Spatial transcriptomics (ST) technologies enable dissecting the tissue architecture in spatial context. To perceive the global contextual information of gene expression patterns in tissue, the spatial dependence of cells must be fully considered by integrating both local and non-local features by means of spatial-context-aware. However, the current ST integration algorithm ignores for ST dropouts, which impedes the spatial-aware of ST features, resulting in challenges in the accuracy and robustness of microenvironmental heterogeneity detecting, spatial domain clustering, and batch-effects correction. Here, we developed an STMGraph, a universal dual-view dynamic deep learning framework that combines dual-remask (MASK-REMASK) with dynamic graph attention model (DGAT) to exploit ST data outperforming pre-existing tools. The dual-remask mechanism masks the embeddings before encoding and decoding, establishing dual-decoding-view to share features mutually. DGAT leverages self-supervision to update graph linkage relationships from two distinct perspectives, thereby generating a comprehensive representation for each node. Systematic benchmarking against 10 state-of-the-art tools revealed that the STMGraph has the optimal performance with high accuracy and robustness on spatial domain clustering for the datasets of diverse ST platforms from multi- to sub-cellular resolutions. Furthermore, STMGraph aggregates ST information cross regions by dual-remask to realize the batch-effects correction implicitly, allowing for spatial domain clustering of ST multi-slices. STMGraph is platform independent and superior in spatial-context-aware to achieve microenvironmental heterogeneity detection, spatial domain clustering, batch-effects correction, and new biological discovery, and is therefore a desirable novel tool for diverse ST studies.

WEST is an ensemble method for spatial transcriptomics analysis

Spatial transcriptomics is a groundbreaking technology, enabling simultaneous profiling of gene expression and spatial orientation within biological tissues. Yet when analyzing spatial transcriptomics data, effective integration of expression and spatial information poses considerable analytical challenges. Although many methods have been developed to address this issue, many are platform specific and lack the general applicability to analyze diverse datasets. In this article, we propose a method called the weighted ensemble method for spatial transcriptomics (WEST) that utilizes ensemble techniques to improve the performance and robustness of spatial transcriptomics data analytics. We compare the performance of WEST with six methods on both synthetic and real-world datasets. WEST represents a significant advance in detecting spatial domains, offering improved accuracy and flexibility compared to existing methods, making it a valuable tool for spatial transcriptomics data analytics.

scGRN-Entropy: Inferring cell differentiation trajectories using single-cell data and gene regulation network-based transfer entropy

Research on cell differentiation facilitates a deeper understanding of the fundamental processes of life, elucidates the intrinsic mechanisms underlying diseases such as cancer, and advances the development of therapeutics and precision medicine. Existing methods for inferring cell differentiation trajectories from single-cell RNA sequencing (scRNA-seq) data primarily rely on static gene expression data to measure distances between cells and subsequently infer pseudotime trajectories. In this work, we introduce a novel method, scGRN-Entropy, for inferring cell differentiation trajectories and pseudotime from scRNA-seq data. Unlike existing approaches, scGRN-Entropy improves inference accuracy by incorporating dynamic changes in gene regulatory networks (GRN). In scGRN-Entropy, an undirected graph representing state transitions between cells is constructed by integrating both static relationships in gene expression space and dynamic relationships in the GRN space. The edges of the undirected graph are then refined using pseudotime inferred based on cell entropy in the GRN space. Finally, the Minimum Spanning Tree (MST) algorithm is applied to derive the cell differentiation trajectory. We validate the accuracy of scGRN-Entropy on eight different real scRNA-seq datasets, demonstrating its superior performance in inferring cell differentiation trajectories through comparative analysis with existing state-of-the-art methods.

Comprehensive multi-omics integration uncovers mitochondrial gene signatures for prognosis and personalized therapy in lung adenocarcinoma

The therapeutic efficacy of lung adenocarcinoma (LUAD), the most prevalent histological subtype of primary lung cancer, remains inadequate, with accurate prognostic assessment posing significant challenges. This study sought to elucidate the prognostic significance of mitochondrial-related genes in LUAD through an integrative multi-omics approach, aimed at developing personalized therapeutic strategies. Utilizing transcriptomic and single-cell RNA sequencing (scRNA-seq) data, alongside clinical information from publicly available databases, we first applied dimensionality reduction and clustering techniques to the LUAD single-cell dataset, focusing on the subclassification of fibroblasts, epithelial cells, and T cells. Mitochondrial-related prognostic genes were subsequently identified using TCGA-LUAD data, and LUAD cases were stratified into distinct molecular subtypes through consensus clustering, allowing for the exploration of gene expression profiles and clinical feature distributions across subtypes. By leveraging an ensemble of machine learning algorithms, we developed an Artificial Intelligence-Derived Prognostic Signature (AIDPS) model based on mitochondrial-related genes and validated its prognostic accuracy across multiple independent datasets. The AIDPS model demonstrated robust predictive power for LUAD patient outcomes, revealing significant differences in responses to immunotherapy and chemotherapy, as well as survival outcomes between risk groups. Furthermore, we conducted comprehensive analyses of tumor mutation burden (TMB), immune microenvironment characteristics, and genome-wide association study (GWAS) data, providing additional insights into the mechanistic roles of mitochondrial-related genes in LUAD pathogenesis. This study not only offers a novel approach to improving prognostic assessments in LUAD but also establishes a strong foundation for the development of personalized therapeutic interventions.

Graph attention automatic encoder based on contrastive learning for domain recognition of spatial transcriptomics

Spatial transcriptomics is an emerging technology that enables the profiling of gene expression in tissues while preserving spatial location information. This innovative approach is anticipated to provide a comprehensive understanding of the spatial distribution of different cells within tissues and facilitate in-depth analysis of tissue structure. To accurately recognize spatial domains from spatial transcriptomics, we have introduced a generalized deep learning method called GAAEST (Graph Attention-based Autoencoder for Spatial Transcriptomics). Our proposed approach effectively integrates both spatial location information and gene expression data from spatial transcriptomics. Specifically, it leverages spatial location details to construct a neighborhood graph and employs a graph attention network-based encoder to embed gene expression information into a spatially informed space. At the same time, to further optimize the learned potential embedding, self-supervised contrastive learning is introduced to capture spatial information at three levels: local, global and contextual feature of spots. Finally, the decoder reconstructs gene expressions, which are then clustered to identify spatial domains with similar expression patterns and spatial proximity. Based on our experiments conducted on multiple datasets, GAAEST consistently outperforms existing state-of-the-art methods. The proposed GAAEST demonstrates excellent capabilities in spatial domain recognition, positioning it as an ideal tool for advancing spatial transcriptomics research.

A multi-modality and multi-granularity collaborative learning framework for identifying spatial domains and spatially variable genes

MOTIVATION

Recent advances in spatial transcriptomics technologies have provided multi-modality data integrating gene expression, spatial context, and histological images. Accurately identifying spatial domains and spatially variable genes is crucial for understanding tissue structures and biological functions. However, effectively combining multi-modality data to identify spatial domains and determining SVGs closely related to these spatial domains remains a challenge.

RESULTS

In this study, we propose spatial transcriptomics multi-modality and multi-granularity collaborative learning (spaMMCL). For detecting spatial domains, spaMMCL mitigates the adverse effects of modality bias by masking portions of gene expression data, integrates gene and image features using a shared graph convolutional network, and employs graph self-supervised learning to deal with noise from feature fusion. Simultaneously, based on the identified spatial domains, spaMMCL integrates various strategies to detect potential SVGs at different granularities, enhancing their reliability and biological significance. Experimental results demonstrate that spaMMCL substantially improves the identification of spatial domains and SVGs.

AVAILABILITY AND IMPLEMENTATION

The code and data of spaMMCL are available on Github: Https://github.com/liangxiao-cs/spaMMCL.

Spatiotemporal omics for biology and medicine

The completion of the Human Genome Project has provided a foundational blueprint for understanding human life. Nonetheless, understanding the intricate mechanisms through which our genetic blueprint is involved in disease or orchestrates development across temporal and spatial dimensions remains a profound scientific challenge. Recent breakthroughs in cellular omics technologies have paved new pathways for understanding the regulation of genomic elements and the relationship between gene expression, cellular functions, and cell fate determination. The advent of spatial omics technologies, encompassing both imaging and sequencing-based methodologies, has enabled a comprehensive understanding of biological processes from a cellular ecosystem perspective. This review offers an updated overview of how spatial omics has advanced our understanding of the translation of genetic information into cellular heterogeneity and tissue structural organization and their dynamic changes over time. It emphasizes the discovery of various biological phenomena, related to organ functionality, embryogenesis, species evolution, and the pathogenesis of diseases.

Benchmarking clustering, alignment, and integration methods for spatial transcriptomics

BACKGROUND

Spatial transcriptomics (ST) is advancing our understanding of complex tissues and organisms. However, building a robust clustering algorithm to define spatially coherent regions in a single tissue slice and aligning or integrating multiple tissue slices originating from diverse sources for essential downstream analyses remains challenging. Numerous clustering, alignment, and integration methods have been specifically designed for ST data by leveraging its spatial information. The absence of comprehensive benchmark studies complicates the selection of methods and future method development.

RESULTS

In this study, we systematically benchmark a variety of state-of-the-art algorithms with a wide range of real and simulated datasets of varying sizes, technologies, species, and complexity. We analyze the strengths and weaknesses of each method using diverse quantitative and qualitative metrics and analyses, including eight metrics for spatial clustering accuracy and contiguity, uniform manifold approximation and projection visualization, layer-wise and spot-to-spot alignment accuracy, and 3D reconstruction, which are designed to assess method performance as well as data quality. The code used for evaluation is available on our GitHub. Additionally, we provide online notebook tutorials and documentation to facilitate the reproduction of all benchmarking results and to support the study of new methods and new datasets.

CONCLUSIONS

Our analyses lead to comprehensive recommendations that cover multiple aspects, helping users to select optimal tools for their specific needs and guide future method development.

Single-cell and spatial multiomic inference of gene regulatory networks using SCRIPro

MOTIVATION

The burgeoning generation of single-cell or spatial multiomic data allows for the characterization of gene regulation networks (GRNs) at an unprecedented resolution. However, the accurate reconstruction of GRNs from sparse and noisy single-cell or spatial multiomic data remains challenging.

RESULTS

Here, we present SCRIPro, a comprehensive computational framework that robustly infers GRNs for both single-cell and spatial multi-omics data. SCRIPro first improves sample coverage through a density clustering approach based on multiomic and spatial similarities. Additionally, SCRIPro scans transcriptional regulator (TR) importance by performing chromatin reconstruction and in silico deletion analyses using a comprehensive reference covering 1,292 human and 994 mouse TRs. Finally, SCRIPro combines TR-target importance scores derived from multiomic data with TR-target expression levels to ensure precise GRN reconstruction. We benchmarked SCRIPro on various datasets, including single-cell multiomic data from human B-cell lymphoma, mouse hair follicle development, Stereo-seq of mouse embryos, and Spatial-ATAC-RNA from mouse brain. SCRIPro outperforms existing motif-based methods and accurately reconstructs cell type-specific, stage-specific, and region-specific GRNs. Overall, SCRIPro emerges as a streamlined and fast method capable of reconstructing TR activities and GRNs for both single-cell and spatial multi-omic data.

AVAILABILITY

SCRIPro is available at https://github.com/wanglabtongji/SCRIPro.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Unraveling Spatial Domain Characterization in Spatially Resolved Transcriptomics with Robust Graph Contrastive Clustering

MOTIVATION

Spatial transcriptomics can quantify gene expression and its spatial distribution in tissues, thus revealing molecular mechanisms of cellular interactions underlying tissue heterogeneity, tissue regeneration, and spatially localized disease mechanisms. However, existing spatial clustering methods often fail to exploit the full potential of spatial information, resulting in inaccurate identification of spatial domains.

RESULTS

In this paper, we develop a deep graph contrastive clustering framework, stDGCC, that accurately uncovers underlying spatial domains via explicitly modeling spatial information and gene expression profiles from spatial transcriptomics data. The stDGCC framework proposes a spatially informed graph node embedding model to preserve the topological information of spots and to learn the informative and discriminative characterization of spatial transcriptomics data through self-supervised contrastive learning. By simultaneously optimizing the contrastive learning loss, reconstruction loss, and Kullback-Leibler (KL) divergence loss, stDGCC achieves joint optimization of feature learning and topology structure preservation in an end-to-end manner. We validate the effectiveness of stDGCC on various spatial transcriptomics datasets acquired from different platforms, each with varying spatial resolutions. Our extensive experiments demonstrate the superiority of stDGCC over various state-of-the-art clustering methods in accurately identifying cellular-level biological structures.

AVAILABILITY

Code and data are available from https://github.com/TimE9527/stDGCC and https://figshare.com/projects/stDGCC/186525.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Tissue module discovery in single-cell-resolution spatial transcriptomics data via cell-cell interaction-aware cell embedding

Computational methods are desired for single-cell-resolution spatial transcriptomics (ST) data analysis to uncover spatial organization principles for how individual cells exert tissue-specific functions. Here, we present ST data analysis via interaction-aware cell embedding (SPACE), a deep-learning method for cell-type identification and tissue module discovery from single-cell-resolution ST data by learning a cell representation that captures its gene expression profile and interactions with its spatial neighbors. SPACE identified spatially informed cell subtypes defined by their special spatial distribution patterns and distinct proximal-interacting cell types. SPACE also automatically discovered "cell communities"-tissue modules with discernible boundaries and a uniform spatial distribution of constituent cell types. For each cell community, SPACE outputs a characteristic proximal cell-cell interaction network associated with physiological processes, which can be used to refine ligand-receptor-based intercellular signaling analyses. We envision that SPACE can be used in large-scale ST projects to understand how proximal cell-cell interactions contribute to emergent biological functions within cell communities. A record of this paper's transparent peer review process is included in the supplemental information.

Complete spatially resolved gene expression is not necessary for identifying spatial domains

Spatially resolved transcriptomics (SRT) technologies have revolutionized the study of tissue organization. We introduce a graph convolutional network with an attention and positive emphasis mechanism, termed BINARY, relying exclusively on binarized SRT data to accurately delineate spatial domains. BINARY outperforms existing methods across various SRT data types while using significantly less input information. Our study suggests that precise gene expression quantification may not always be essential, inspiring further exploration of the broader applications of spatially resolved binarized gene expression data.

Accurate Identification of Spatial Domain by Incorporating Global Spatial Proximity and Local Expression Proximity

Accurate identification of spatial domains is essential in the analysis of spatial transcriptomics data in order to elucidate tissue microenvironments and biological functions. However, existing methods only perform domain segmentation based on local or global spatial relationships between spots, resulting in an underutilization of spatial information. To this end, we propose SECE, a deep learning-based method that captures both local and global relationships among spots and aggregates their information using expression similarity and spatial similarity. We benchmarked SECE against eight state-of-the-art methods on six real spatial transcriptomics datasets spanning four different platforms. SECE consistently outperformed other methods in spatial domain identification accuracy. Moreover, SECE produced spatial embeddings that exhibited clearer patterns in low-dimensional visualizations and facilitated a more accurate trajectory inference.

Modeling blood-brain barrier formation and cerebral cavernous malformations in human PSC-derived organoids

The human blood-brain barrier (hBBB) is a highly specialized structure that regulates passage across blood and central nervous system (CNS) compartments. Despite its critical physiological role, there are no reliable in vitro models that can mimic hBBB development and function. Here, we constructed hBBB assembloids from brain and blood vessel organoids derived from human pluripotent stem cells. We validated the acquisition of blood-brain barrier (BBB)-specific molecular, cellular, transcriptomic, and functional characteristics and uncovered an extensive neuro-vascular crosstalk with a spatial pattern within hBBB assembloids. When we used patient-derived hBBB assembloids to model cerebral cavernous malformations (CCMs), we found that these assembloids recapitulated the cavernoma anatomy and BBB breakdown observed in patients. Upon comparison of phenotypes and transcriptome between patient-derived hBBB assembloids and primary human cavernoma tissues, we uncovered CCM-related molecular and cellular alterations. Taken together, we report hBBB assembloids that mimic the core properties of the hBBB and identify a potentially underlying cause of CCMs.

HyperGCN: an effective deep representation learning framework for the integrative analysis of spatial transcriptomics data

BACKGROUND

Advances of spatial transcriptomics technologies enabled simultaneously profiling gene expression and spatial locations of cells from the same tissue. Computational tools and approaches for integration of transcriptomics data and spatial context information are urgently needed to comprehensively explore the underlying structure patterns. In this manuscript, we propose HyperGCN for the integrative analysis of gene expression and spatial information profiled from the same tissue. HyperGCN enables data visualization and clustering, and facilitates downstream analysis, including domain segmentation, the characterization of marker genes for the specific domain structure and GO enrichment analysis.

RESULTS

Extensive experiments are implemented on four real datasets from different tissues (including human dorsolateral prefrontal cortex, human positive breast tumors, mouse brain, mouse olfactory bulb tissue and Zabrafish melanoma) and technologies (including 10X visium, osmFISH, seqFISH+, 10X Xenium and Stereo-seq) with different spatial resolutions. The results show that HyperGCN achieves superior clustering performance and produces good domain segmentation effects while identifies biologically meaningful spatial expression patterns. This study provides a flexible framework to analyze spatial transcriptomics data with high geometric complexity.

CONCLUSIONS

HyperGCN is an unsupervised method based on hypergraph induced graph convolutional network, where it assumes that there existed disjoint tissues with high geometric complexity, and models the semantic relationship of cells through hypergraph, which better tackles the high-order interactions of cells and levels of noise in spatial transcriptomics data.

Spatial transition tensor of single cells

Spatial transcriptomics and messenger RNA splicing encode extensive spatiotemporal information for cell states and transitions. The current lineage-inference methods either lack spatial dynamics for state transition or cannot capture different dynamics associated with multiple cell states and transition paths. Here we present spatial transition tensor (STT), a method that uses messenger RNA splicing and spatial transcriptomes through a multiscale dynamical model to characterize multistability in space. By learning a four-dimensional transition tensor and spatial-constrained random walk, STT reconstructs cell-state-specific dynamics and spatial state transitions via both short-time local tensor streamlines between cells and long-time transition paths among attractors. Benchmarking and applications of STT on several transcriptome datasets via multiple technologies on epithelial-mesenchymal transitions, blood development, spatially resolved mouse brain and chicken heart development, indicate STT's capability in recovering cell-state-specific dynamics and their associated genes not seen using existing methods. Overall, STT provides a consistent multiscale description of single-cell transcriptome data across multiple spatiotemporal scales.

Spatial Transcriptomics in a Case of Follicular Thyroid Carcinoma Reveals Clone-Specific Dysregulation of Genes Regulating Extracellular Matrix in the Invading Front

Follicular thyroid carcinoma (FTC) is recognized by its ability to invade the tumor capsule and blood vessels, although the exact molecular signals orchestrating this phenotype remain elusive. In this study, the spatial transcriptional landscape of an FTC is detailed with comparisons between the invasive front and histologically indolent central core tumor areas. The Visium spatial gene expression platform allowed us to interrogate and visualize the whole transcriptome in 2D across formalin-fixated paraffin-embedded (FFPE) tissue sections. Four different 6 × 6 mm areas of an FTC were scrutinized, including regions with capsular and vascular invasion, capsule-near area without invasion, and a central core area of the tumor. Following successful capturing and sequencing, several expressional clusters were identified with regional variation. Most notably, invasive tumor cell clusters were significantly over-expressing genes associated with pathways interacting with the extracellular matrix (ECM) remodeling and epithelial-to-mesenchymal transition (EMT). Subsets of these genes (POSTN and DPYSL3) were additionally validated using immunohistochemistry in an independent cohort of follicular thyroid tumors showing a clear gradient pattern from the core to the periphery of the tumor. Moreover, the reconstruction of the evolutionary tree identified the invasive clones as late events in follicular thyroid tumorigenesis. To our knowledge, this is one of the first 2D global transcriptional mappings of FTC using this platform to date. Invasive FTC clones develop in a stepwise fashion and display significant dysregulation of genes associated with the ECM and EMT - thus highlighting important molecular crosstalk for further investigations.

Uncover spatially informed variations for single-cell spatial transcriptomics with STew

Motivation

The recent spatial transcriptomics (ST) technologies have enabled characterization of gene expression patterns and spatial information, advancing our understanding of cell lineages within diseased tissues. Several analytical approaches have been proposed for ST data, but effectively utilizing spatial information to unveil the shared variation with gene expression remains a challenge.

Results

We introduce STew, a Spatial Transcriptomic multi-viEW representation learning method, to jointly analyze spatial information and gene expression in a scalable manner, followed by a data-driven statistical framework to measure the goodness of model fit. Through benchmarking using human dorsolateral prefrontal cortex and mouse main olfactory bulb data with true manual annotations, STew achieved superior performance in both clustering accuracy and continuity of identified spatial domains compared with other methods. STew is also robust to generate consistent results insensitive to model parameters, including sparsity constraints. We next applied STew to various ST data acquired from 10× Visium, Slide-seqV2, and 10× Xenium, encompassing single-cell and multi-cellular resolution ST technologies, which revealed spatially informed cell type clusters and biologically meaningful axes. In particular, we identified a proinflammatory fibroblast spatial niche using ST data from psoriatic skins. Moreover, STew scales almost linearly with the number of spatial locations, guaranteeing its applicability to datasets with thousands of spatial locations to capture disease-relevant niches in complex tissues.

Availability and implementation

Source code and the R software tool STew are available from github.com/fanzhanglab/STew.