MOSCATO: a supervised approach for analyzing multi-Omic single-Cell data

A multi-phase approach using supervised algorithms and clinical models to generate high-accuracy signatures for pancreatic cancer.

BackgroundThe integration of multimodal single-cell data enables comprehensive organ reference atlases, yet its impact remains largely unexplored, particularly in complex tissues. Using the kidney as an emblematic example of a complex organ, we perform a systematic evaluation of multimodal single-cell integration strategies, with heart tissue used for additional methodological validation.ResultsWe generate a benchmarking dataset for the renal cortex by integrating 3' and 5' scRNA-seq with joint snRNA-seq and snATAC-seq, profiling 119,744 high-quality nuclei/cells from 19 donors. To align cell identities and enable consistent comparisons, we develop the interpretable machine learning tool scOMM (single-cell Omics Multimodal Mapping) and systematically assess integration strategies. "Horizontal" integration of scRNA and snRNA-seq improves cell-type identification, while "vertical" integration of snRNA-seq and snATAC-seq has an additive effect, enhancing resolution in homogeneous populations and difficult-to-identify states. Global integration is especially effective in identifying adaptive states and rare cell types, including WFDC2-expressing Thick Ascending Limb and Norn cells, previously undetected in kidney atlases.ConclusionsOur work establishes a robust framework for multimodal reference atlas generation, advancing single-cell analysis and extending its applicability to diverse tissues.Supplementary InformationThe online version contains supplementary material available at 10.1186/s13059-026-04002-4.

Single-cell omics enable the dissection of cellular heterogeneity, yet the high dimensionality, inherent noise, and sparsity present significant challenges. These challenges are amplified for rare cell populations, which are often difficult to annotate reliably but can be central to development and disease. As single-cell assays increasingly capture multiple molecular layers, the integrative analysis of such multimodal data further increases complexity. Here, we propose Hydra, a deep generative framework based on an ensemble of variational autoencoders for effective learning of unimodal and multimodal single-cell omics data. Hydra implements interpretable modules for capturing cell-type-specific molecular signatures. The ensemble of such interpretable modules enables reproducible feature selection and robust cell-type annotation, with particular effectiveness for rare populations. We benchmarked Hydra on a repertoire of 21 datasets, including unimodal and multimodal single-cell omics data. Our results demonstrate that Hydra offers comparable to superior performance to several state-of-the-art methods. Finally, we highlight the utility of Hydra in robustly annotating brain cellular subtypes and preserving disease-relevant signatures using our previously published dataset that profiles Alzheimer's disease.

In general, the ‘small sample (n)-large feature ( Open image in new window )’ problem of bioinformatics, image analysis, high throughput molecular screening, astronomy, and other high dimensional applications makes the features highly collinear. In this context, the paper presents a new feature extraction algorithm to address this ‘large Open image in new window small n’ issue associated with multimodal data sets. The proposed algorithm judiciously integrates the concept of both regularization and shrinkage with canonical correlation analysis to extract important features. To deal with the singularity problem, the proposed method increases the diagonal elements of covariance matrices by using regularization parameters, while the off-diagonal elements are decreased by shrinkage coefficients. The concept of hypercuboid equivalence partition matrix of rough hypercuboid approach is used to compute both significance and relevance measures of a feature. The importance of the proposed algorithm over other existing methods is established extensively on real life multimodal omics data set.

Serrated colorectal cancer (SCC) is a rare and aggressive subtype of colorectal cancer. Identifying SCC is crucial due to its high mortality rate and limited therapeutic options. Traditional methods to identify BRAF hotspot mutations and MLH1 methylation are insufficient in clinical practice. This study aims to explore the WNT pathway alterations in the CRC and to develop a WNT-derived subtyping model to identify SCC patients by using multi-OMICs data. We included multi-omics data of 1751 colorectal cancer patients from the TCGA and GEO databases, and single-cell transcriptome data of 33 normal and cancer tissues from the SMC study cohort. The comprehensive study process incorporated unsupervised clustering, enrichment analysis, and statistical analysis. In this study, we investigated WNT pathway alterations in SCC by integrating both bulk and single-cell data into the multi-OMICs framework. The SCC subtype demonstrated significant WNT pathway heterogeneity and a more stable genomic structure. These findings support the development of a WNT-derived subtyping model that accurately identifies SCC patients across different CRC cohorts. In addition, the SCC subtype also presented a distinct immune microenvironment characterized by CD8+ T cell exhaustion. Finally, we utilized drug perturbation data to explore the potential drug targets for this severe cancer subtype. We developed a WNT-derived subtyping method to identify SCC from canonical CRC, which enhances the molecular understanding of this severe cancer subtype and provides potential therapeutic strategies. Our findings suggest that SCC patients may benefit from the HSP90 inhibitor NVP-AUY922, highlighting its potential as a targeted therapy.

Multimodal single-cell omics technologies enable multiple molecular programs to be simultaneously profiled at a global scale in individual cells, creating opportunities to study biological systems at a resolution that was previously inaccessible. However, the analysis of multimodal single-cell omics data is challenging due to the lack of methods that can integrate across multiple data modalities generated from such technologies. Here, we present Matilda, a multi-task learning method for integrative analysis of multimodal single-cell omics data. By leveraging the interrelationship among tasks, Matilda learns to perform data simulation, dimension reduction, cell type classification, and feature selection in a single unified framework. We compare Matilda with other state-of-the-art methods on datasets generated from some of the most popular multimodal single-cell omics technologies. Our results demonstrate the utility of Matilda for addressing multiple key tasks on integrative multimodal single-cell omics data analysis. Matilda is implemented in Pytorch and is freely available from https://github.com/PYangLab/Matilda.

It is an essential task to accurately diagnose cancer subtypes in computational pathology for personalized cancer treatment. Recent studies have indicated that the combination of multimodal data, such as whole slide images (WSIs) and multi-omics data, could achieve more accurate diagnosis. However, robust cancer diagnosis remains challenging due to the heterogeneity among multimodal data, as well as the performance degradation caused by insufficient multimodal patient data. In this work, we propose a novel multimodal co-attention fusion network (MCFN) with online data augmentation (ODA) for cancer subtype classification. Specifically, a multimodal mutual-guided co-attention (MMC) module is proposed to effectively perform dense multimodal interactions. It enables multimodal data to mutually guide and calibrate each other during the integration process to alleviate inter- and intra-modal heterogeneities. Subsequently, a self-normalizing network (SNN)-Mixer is developed to allow information communication among different omics data and alleviate the high-dimensional small-sample size problem in multi-omics data. Most importantly, to compensate for insufficient multimodal samples for model training, we propose an ODA module in MCFN. The ODA module leverages the multimodal knowledge to guide the data augmentations of WSIs and maximize the data diversity during model training. Extensive experiments are conducted on the public TCGA dataset. The experimental results demonstrate that the proposed MCFN outperforms all the compared algorithms, suggesting its effectiveness.

Determining cell types by single-cell transcriptomics data is fundamental for downstream analysis. However, cell clustering and data imputation still face the computation challenges, due to the high dropout rate, sparsity and dimensionality of single-cell data. Although some deep learning based solutions have been proposed to handle these challenges, they still can not leverage gene attribute information and cell topology in a sensible way to explore the consistent clustering. In this paper, we present scDeepFC, a deep information fusion-based single-cell data clustering method for cell clustering and data imputation. Specifically, scDeepFC uses a deep auto-encoder (DAE) network and a deep graph convolution network to embed high-dimensional gene attribute information and high-order cell-cell topological information into different low-dimensional representations, and then fuses them to generate a more comprehensive and accurate consensus representation via a deep information fusion network. In addition, scDeepFC integrates the zero-inflated negative binomial (ZINB) into DAE to model the dropout events. By jointly optimizing the ZINB loss and cell graph reconstruction loss, scDeepFC generates a salient embedding representation for clustering cells and imputing missing data. Extensive experiments on real single-cell datasets prove that scDeepFC outperforms other popular single-cell analysis methods. Both the gene attribute and cell topology information can improve the cell clustering.

Auditory hair cells transduce sound to the brain, and in mammals, these cells reside together with supporting cells in the sensory epithelium of the cochlea, called the organ of Corti. To establish the organ's delicate function during development and differentiation, spatiotemporal gene expression is strictly controlled by chromatin accessibility and cell type–specific transcription factors, jointly representing the regulatory landscape. Bulk sequencing technology and cellular heterogeneity obscured investigations on the interplay between transcription factors and chromatin accessibility in inner ear development. To study the formation of the regulatory landscape in hair cells, we collected single-cell chromatin accessibility profiles accompanied by single-cell RNA data from genetically labeled murine hair cells and supporting cells after birth. Using an integrative approach, we predicted cell type–specific activating and repressing functions of developmental transcription factors. Furthermore, by integrating gene expression and chromatin accessibility data sets, we reconstructed gene regulatory networks. Then, using a comparative approach, 20 hair cell–specific activators and repressors, including putative downstream target genes, were identified. Clustering of target genes resolved groups of related transcription factors and was used to infer their developmental functions. Finally, the heterogeneity in the single-cell data allowed us to spatially reconstruct transcriptional as well as chromatin accessibility trajectories, indicating that gradual changes in the chromatin accessibility landscape are lagging behind the transcriptional identity of hair cells along the organ's longitudinal axis. Overall, this study provides a strategy to spatially reconstruct the formation of a lineage-specific regulatory landscape using a single-cell multi-omics approach.

Recent developments of video and sensing technology have led to large volumes of digital media data. Current media production relies on videos from the principal camera together with a wide variety of heterogeneous source of supporting data [photos, light detection and ranging point clouds, witness video camera, high dynamic range imaging, and depth imagery]. Registration of visual data acquired from various 2D and 3D sensing modalities is challenging because current matching and registration methods are not appropriate due to differences in structure, format, and noise characteristics for multimodal data. A combined 2D/3D visualization of this registered data allows an integrated overview of the entire data set. For such a visualization, a Web-based context presents several advantages. In this paper, we propose a unified framework for registration and visualization of this type of visual media data. A new feature description and matching method is proposed, adaptively considering local geometry, semiglobal geometry, and color information in the scene for more robust registration. The resulting registered 2D/3D multimodal visual data are too large to be downloaded and viewed directly via the Web browser, while maintaining an acceptable user experience. Thus, we employ hierarchical techniques for compression and restructuring to enable efficient transmission and visualization over the Web, leading to interactive visualization as registered point clouds, 2D images, and videos in the browser, improving on the current state-of-the-art techniques for Web-based visualization of big media data. This is the first unified 3D Web-based visualization of multimodal visual media production data sets. The proposed pipeline is tested on big multimodal data set typical of film and broadcast production, which are made publicly available. The<br/>proposed feature description method shows two times higher precision of feature matching and more stable registration performance than existing 3D feature descriptors.

The March of Monocytes in Atherosclerosis: One Cell at a Time.

The development of single-cell transcriptomic technologies yields large datasets comprising multimodal informations, such as transcriptomes and immunophenotypes. Despite the current explosion of methods for pre-processing and integrating multimodal single-cell data, there is currently no user-friendly software to display easily and simultaneously both immunophenotype and transcriptome-based UMAP/t-SNE plots from the pre-processed data. Here, we introduce Single-Cell Virtual Cytometer, an open-source software for flow cytometry-like visualization and exploration of pre-processed multi-omics single cell datasets. Using an original CITE-seq dataset of PBMC from an healthy donor, we illustrate its use for the integrated analysis of transcriptomes and epitopes of functional maturation in human peripheral T lymphocytes. So this free and open-source algorithm constitutes a unique resource for biologists seeking for a user-friendly analytic tool for multimodal single cell datasets.

Single-cell sequencing technologies that simultaneously generate multimodal cellular profiles present opportunities for improved understanding of cell heterogeneity in tissues. How the multimodal information can be integrated to obtain a common cell type identification, however, poses a computational challenge. Multilayer graphs provide a natural representation of multi-omic single-cell sequencing datasets, and finding cell clusters may be understood as a multilayer graph partition problem. We introduce two spectral algorithms on multilayer graphs, spectral clustering on multilayer graphs and the weighted locally linear (WLL) method, to cluster cells in multi-omic single-cell sequencing datasets. We connect these algorithms through a unifying mathematical framework that represents each layer using a Hamiltonian operator and a mixture of its eigenstates to integrate the multiple graph layers, demonstrating in the process that the WLL method is a rigorous multilayer spectral graph theoretic reformulation of the popular Seurat weighted nearest neighbor (WNN) algorithm. Implementing our algorithms and applying them to a CITE-seq dataset of cord blood mononuclear cells yields results similar to the Seurat WNN analysis. Our work thus extends spectral methods to multimodal single-cell data analysis. The code used in this study can be found at https://github.com/jssong-lab/sc-spectrum. All public data used in the article are accurately cited and described in Materials and Methods and in Supplementary Information. Supplementary data are available at Bioinformatics online.

Single-cell multi-omics sequencing techniques have rapidly developed in the past few years. Clustering analysis with single-cell multi-omics data may give us novel perspectives to dissect cellular heterogeneity. However, multi-omics data have the properties of inherited large dimension, high sparsity and existence of doublets. Moreover, representations of different omics from even the same cell follow diverse distributions. Without proper distribution alignment techniques, clustering methods will encounter less separable clusters easily affected by less informative omics data. We developed MoClust, a novel joint clustering framework that can be applied to several types of single-cell multi-omics data. A selective automatic doublet detection module that can identify and filter out doublets is introduced in the pretraining stage to improve data quality. Omics-specific autoencoders are introduced to characterize the multi-omics data. A contrastive learning way of distribution alignment is adopted to adaptively fuse omics representations into an omics-invariant representation. This novel way of alignment boosts the compactness and separableness of clusters, while accurately weighting the contribution of each omics to the clustering object. Extensive experiments, over both simulated and real multi-omics datasets, demonstrated the powerful alignment, doublet detection and clustering ability features of MoClust. An implementation of MoClust is available from https://doi.org/10.5281/zenodo.7306504. Supplementary data are available at Bioinformatics online.

Motivation: Advances in single-cell measurement techniques provide rich multimodal data, which helps us to explore the life state of cells more deeply. However, multimodal integration, or, learning joint embeddings from multimodal data remains a current challenge. The difficulty in integrating unpaired single-cell multimodal data is that different modalities have different feature spaces, which easily leads to information loss in joint embedding. And few existing methods have fully exploited and fused the information in single-cell multimodal data. Result: In this study, we propose CoVEL, a deep learning method for unsupervised integration of single-cell multimodal data. CoVEL learns single-cell representations from a comprehensive view, including regulatory relationships between modalities, fine-grained representations of cells, and relationships between different cells. The comprehensive view embedding enables CoVEL to remove the gap between modalities while protecting biological heterogeneity. Experimental results on multiple public datasets show that CoVEL is accurate and robust to single-cell multimodal integration. Data availability: https://github.com/shapsider/scintegration.