PeakVI: A deep generative model for single-cell chromatin accessibility analysis

Fast clustering and cell-type annotation of scATAC data using pre-trained embeddings

Data from the single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) are now widely available. One major computational challenge is dealing with high dimensionality and inherent sparsity, which is typically addressed by producing lower dimensional representations of single cells for downstream clustering tasks. Current approaches produce such individual cell embeddings directly through a one-step learning process. Here, we propose an alternative approach by building embedding models pre-trained on reference data. We argue that this provides a more flexible analysis workflow that also has computational performance advantages through transfer learning. We implemented our approach in scEmbed, an unsupervised machine-learning framework that learns low-dimensional embeddings of genomic regulatory regions to represent and analyze scATAC-seq data. scEmbed performs well in terms of clustering ability and has the key advantage of learning patterns of region co-occurrence that can be transferred to other, unseen datasets. Moreover, models pre-trained on reference data can be exploited to build fast and accurate cell-type annotation systems without the need for other data modalities. scEmbed is implemented in Python and it is available to download from GitHub. We also make our pre-trained models available on huggingface for public use. scEmbed is open source and available at https://github.com/databio/geniml. Pre-trained models from this work can be obtained on huggingface: https://huggingface.co/databio.

MOCHA's advanced statistical modeling of scATAC-seq data enables functional genomic inference in large human cohorts

Single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) is being increasingly used to study gene regulation. However, major analytical gaps limit its utility in studying gene regulatory programs in complex diseases. In response, MOCHA (Model-based single cell Open CHromatin Analysis) presents major advances over existing analysis tools, including: 1) improving identification of sample-specific open chromatin, 2) statistical modeling of technical drop-out with zero-inflated methods, 3) mitigation of false positives in single cell analysis, 4) identification of alternative transcription-starting-site regulation, and 5) modules for inferring temporal gene regulatory networks from longitudinal data. These advances, in addition to open chromatin analyses, provide a robust framework after quality control and cell labeling to study gene regulatory programs in human disease. We benchmark MOCHA with four state-of-the-art tools to demonstrate its advances. We also construct cross-sectional and longitudinal gene regulatory networks, identifying potential mechanisms of COVID-19 response. MOCHA provides researchers with a robust analytical tool for functional genomic inference from scATAC-seq data.

Dependency-aware deep generative models for multitasking analysis of spatial omics data

Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks that are essential for SRT data analysis, including dimensionality reduction, visualization, clustering, batch integration, denoising, differential expression, spatial interpolation, resolution enhancement and identification of spatially variable genes. Moreover, we have extended spaVAE to spaPeakVAE and spaMultiVAE to characterize spatial ATAC-seq (assay for transposase-accessible chromatin using sequencing) data and spatial multi-omics data, respectively.

Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data

Here we present biVI, which combines the variational autoencoder framework of scVI with biophysical models describing the transcription and splicing kinetics of RNA molecules. We demonstrate on simulated and experimental single-cell RNA sequencing data that biVI retains the variational autoencoder's ability to capture cell type structure in a low-dimensional space while further enabling genome-wide exploration of the biophysical mechanisms, such as system burst sizes and degradation rates, that underlie observations.

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.

Liam tackles complex multimodal single-cell data integration challenges

Multi-omics characterization of single cells holds outstanding potential for profiling the dynamics and relations of gene regulatory states of thousands of cells. How to integrate multimodal data is an open problem, especially when aiming to combine data from multiple sources or conditions containing both biological and technical variation. We introduce liam, a flexible model for the simultaneous horizontal and vertical integration of paired single-cell multimodal data and mosaic integration of paired with unimodal data. Liam learns a joint low-dimensional representation of the measured modalities, which proves beneficial when the information content or quality of the modalities differ. Its integration accounts for complex batch effects using a tunable combination of conditional and adversarial training, which can be optimized using replicate information while retaining selected biological variation. We demonstrate liam's superior performance on multiple paired multimodal data types, including Multiome and CITE-seq data, and in mosaic integration scenarios. Our detailed benchmarking experiments illustrate the complexities and challenges remaining for integration and the meaningful assessment of its success.

Deep generative models in single-cell omics

Deep Generative Models (DGMs) are becoming instrumental for inferring probability distributions inherent to complex processes, such as most questions in biomedical research. For many years, there was a lack of mathematical methods that would allow this inference in the scarce data scenario of biomedical research. The advent of single-cell omics has finally made square the so-called "skinny matrix", allowing to apply mathematical methods already extensively used in other areas. Moreover, it is now possible to integrate data at different molecular levels in thousands or even millions of samples, thanks to the number of single-cell atlases being collaboratively generated. Additionally, DGMs have proven useful in other frequent tasks in single-cell analysis pipelines, from dimensionality reduction, cell type annotation to RNA velocity inference. In spite of its promise, DGMs need to be used with caution in biomedical research, paying special attention to its use to answer the right questions and the definition of appropriate error metrics and validation check points that confirm not only its correct use but also its relevance. All in all, DGMs provide an exciting tool that opens a bright future for the integrative analysis of single-cell -omics to understand health and disease.

Scalable and unbiased sequence-informed embedding of single-cell ATAC-seq data with CellSpace

Standard scATAC sequencing (scATAC-seq) analysis pipelines represent cells as sparse numeric vectors relative to an atlas of peaks or genomic tiles and consequently ignore genomic sequence information at accessible loci. Here we present CellSpace, an efficient and scalable sequence-informed embedding algorithm for scATAC-seq that learns a mapping of DNA k-mers and cells to the same space, to address this limitation. We show that CellSpace captures meaningful latent structure in scATAC-seq datasets, including cell subpopulations and developmental hierarchies, and can score transcription factor activities in single cells based on proximity to binding motifs embedded in the same space. Importantly, CellSpace implicitly mitigates batch effects arising from multiple samples, donors or assays, even when individual datasets are processed relative to different peak atlases. Thus, CellSpace provides a powerful tool for integrating and interpreting large-scale scATAC-seq compendia.

Challenges and best practices in omics benchmarking

Technological advances enabling massively parallel measurement of biological features - such as microarrays, high-throughput sequencing and mass spectrometry - have ushered in the omics era, now in its third decade. The resulting complex landscape of analytical methods has naturally fostered the growth of an omics benchmarking industry. Benchmarking refers to the process of objectively comparing and evaluating the performance of different computational or analytical techniques when processing and analysing large-scale biological data sets, such as transcriptomics, proteomics and metabolomics. With thousands of omics benchmarking studies published over the past 25 years, the field has matured to the point where the foundations of benchmarking have been established and well described. However, generating meaningful benchmarking data and properly evaluating performance in this complex domain remains challenging. In this Review, we highlight some common oversights and pitfalls in omics benchmarking. We also establish a methodology to bring the issues that can be addressed into focus and to be transparent about those that cannot: this takes the form of a spreadsheet template of guidelines for comprehensive reporting, intended to accompany publications. In addition, a survey of recent developments in benchmarking is provided as well as specific guidance for commonly encountered difficulties.

Discrete latent embedding of single-cell chromatin accessibility sequencing data for uncovering cell heterogeneity

Single-cell epigenomic data has been growing continuously at an unprecedented pace, but their characteristics such as high dimensionality and sparsity pose substantial challenges to downstream analysis. Although deep learning models-especially variational autoencoders-have been widely used to capture low-dimensional feature embeddings, the prevalent Gaussian assumption somewhat disagrees with real data, and these models tend to struggle to incorporate reference information from abundant cell atlases. Here we propose CASTLE, a deep generative model based on the vector-quantized variational autoencoder framework to extract discrete latent embeddings that interpretably characterize single-cell chromatin accessibility sequencing data. We validate the performance and robustness of CASTLE for accurate cell-type identification and reasonable visualization compared with state-of-the-art methods. We demonstrate the advantages of CASTLE for effective incorporation of existing massive reference datasets in a weakly supervised or supervised manner. We further demonstrate CASTLE's capacity for intuitively distilling cell-type-specific feature spectra that unveil cell heterogeneity and biological implications quantitatively.

A fast, scalable and versatile tool for analysis of single-cell omics data

Single-cell omics technologies have revolutionized the study of gene regulation in complex tissues. A major computational challenge in analyzing these datasets is to project the large-scale and high-dimensional data into low-dimensional space while retaining the relative relationships between cells. This low dimension embedding is necessary to decompose cellular heterogeneity and reconstruct cell-type-specific gene regulatory programs. Traditional dimensionality reduction techniques, however, face challenges in computational efficiency and in comprehensively addressing cellular diversity across varied molecular modalities. Here we introduce a nonlinear dimensionality reduction algorithm, embodied in the Python package SnapATAC2, which not only achieves a more precise capture of single-cell omics data heterogeneities but also ensures efficient runtime and memory usage, scaling linearly with the number of cells. Our algorithm demonstrates exceptional performance, scalability and versatility across diverse single-cell omics datasets, including single-cell assay for transposase-accessible chromatin using sequencing, single-cell RNA sequencing, single-cell Hi-C and single-cell multi-omics datasets, underscoring its utility in advancing single-cell analysis.

Representing and extracting knowledge from single-cell data

Single-cell analysis is currently one of the most high-resolution techniques to study biology. The large complex datasets that have been generated have spurred numerous developments in computational biology, in particular the use of advanced statistics and machine learning. This review attempts to explain the deeper theoretical concepts that underpin current state-of-the-art analysis methods. Single-cell analysis is covered from cell, through instruments, to current and upcoming models. The aim of this review is to spread concepts which are not yet in common use, especially from topology and generative processes, and how new statistical models can be developed to capture more of biology. This opens epistemological questions regarding our ontology and models, and some pointers will be given to how natural language processing (NLP) may help overcome our cognitive limitations for understanding single-cell data.

scMLC: an accurate and robust multiplex community detection method for single-cell multi-omics data

Clustering cells based on single-cell multi-modal sequencing technologies provides an unprecedented opportunity to create high-resolution cell atlas, reveal cellular critical states and study health and diseases. However, effectively integrating different sequencing data for cell clustering remains a challenging task. Motivated by the successful application of Louvain in scRNA-seq data, we propose a single-cell multi-modal Louvain clustering framework, called scMLC, to tackle this problem. scMLC builds multiplex single- and cross-modal cell-to-cell networks to capture modal-specific and consistent information between modalities and then adopts a robust multiplex community detection method to obtain the reliable cell clusters. In comparison with 15 state-of-the-art clustering methods on seven real datasets simultaneously measuring gene expression and chromatin accessibility, scMLC achieves better accuracy and stability in most datasets. Synthetic results also indicate that the cell-network-based integration strategy of multi-omics data is superior to other strategies in terms of generalization. Moreover, scMLC is flexible and can be extended to single-cell sequencing data with more than two modalities.

Modeling fragment counts improves single-cell ATAC-seq analysis

Single-cell ATAC sequencing coverage in regulatory regions is typically binarized as an indicator of open chromatin. Here we show that binarization is an unnecessary step that neither improves goodness of fit, clustering, cell type identification nor batch integration. Fragment counts, but not read counts, should instead be modeled, which preserves quantitative regulatory information. These results have immediate implications for single-cell ATAC sequencing analysis.

SEACells infers transcriptional and epigenomic cellular states from single-cell genomics data

Metacells are cell groupings derived from single-cell sequencing data that represent highly granular, distinct cell states. Here we present single-cell aggregation of cell states (SEACells), an algorithm for identifying metacells that overcome the sparsity of single-cell data while retaining heterogeneity obscured by traditional cell clustering. SEACells outperforms existing algorithms in identifying comprehensive, compact and well-separated metacells in both RNA and assay for transposase-accessible chromatin (ATAC) modalities across datasets with discrete cell types and continuous trajectories. We demonstrate the use of SEACells to improve gene-peak associations, compute ATAC gene scores and infer the activities of critical regulators during differentiation. Metacell-level analysis scales to large datasets and is particularly well suited for patient cohorts, where per-patient aggregation provides more robust units for data integration. We use our metacells to reveal expression dynamics and gradual reconfiguration of the chromatin landscape during hematopoietic differentiation and to uniquely identify CD4 T cell differentiation and activation states associated with disease onset and severity in a Coronavirus Disease 2019 (COVID-19) patient cohort.

Population-level integration of single-cell datasets enables multi-scale analysis across samples

The increasing generation of population-level single-cell atlases has the potential to link sample metadata with cellular data. Constructing such references requires integration of heterogeneous cohorts with varying metadata. Here we present single-cell population level integration (scPoli), an open-world learner that incorporates generative models to learn sample and cell representations for data integration, label transfer and reference mapping. We applied scPoli on population-level atlases of lung and peripheral blood mononuclear cells, the latter consisting of 7.8 million cells across 2,375 samples. We demonstrate that scPoli can explain sample-level biological and technical variations using sample embeddings revealing genes associated with batch effects and biological effects. scPoli is further applicable to single-cell sequencing assay for transposase-accessible chromatin and cross-species datasets, offering insights into chromatin accessibility and comparative genomics. We envision scPoli becoming an important tool for population-level single-cell data integration facilitating atlas use but also interpretation by means of multi-scale analyses.

GoM DE: interpreting structure in sequence count data with differential expression analysis allowing for grades of membership

Parts-based representations, such as non-negative matrix factorization and topic modeling, have been used to identify structure from single-cell sequencing data sets, in particular structure that is not as well captured by clustering or other dimensionality reduction methods. However, interpreting the individual parts remains a challenge. To address this challenge, we extend methods for differential expression analysis by allowing cells to have partial membership to multiple groups. We call this grade of membership differential expression (GoM DE). We illustrate the benefits of GoM DE for annotating topics identified in several single-cell RNA-seq and ATAC-seq data sets.

SnapATAC2: a fast, scalable and versatile tool for analysis of single-cell omics data

Single-cell omics technologies have ushered in a new era for the study of dynamic gene regulation in complex tissues during development and disease pathogenesis. A major computational challenge in analyzing these datasets is to project the large-scale and high dimensional data into low-dimensional space while retaining the relative relationships between cells in order to decompose the cellular heterogeneity and reconstruct cell-type-specific gene regulatory programs. Conventional dimensionality reduction methods suffer from computational inefficiency, difficulty to capture the full spectrum of cellular heterogeneity, or inability to apply across diverse molecular modalities. Here, we report a fast and nonlinear dimensionality reduction algorithm that not only more accurately captures the heterogeneities of single-cell omics data, but also features runtime and memory usage that is computational efficient and linearly proportional to cell numbers. We implement this algorithm in a Python package named SnapATAC2, and demonstrate its superior performance, remarkable scalability and general adaptability using an array of single-cell omics data types, including single-cell ATAC-seq, single-cell RNA-seq, single-cell Hi-C, and single-cell multiomics datasets.

Isolating salient variations of interest in single-cell data with contrastiveVI

Single-cell datasets are routinely collected to investigate changes in cellular state between control cells and the corresponding cells in a treatment condition, such as exposure to a drug or infection by a pathogen. To better understand heterogeneity in treatment response, it is desirable to deconvolve variations enriched in treated cells from those shared with controls. However, standard computational models of single-cell data are not designed to explicitly separate these variations. Here, we introduce contrastive variational inference (contrastiveVI; https://github.com/suinleelab/contrastiveVI ), a framework for deconvolving variations in treatment-control single-cell RNA sequencing (scRNA-seq) datasets into shared and treatment-specific latent variables. Using three treatment-control scRNA-seq datasets, we apply contrastiveVI to perform a variety of analysis tasks, including visualization, clustering and differential expression testing. We find that contrastiveVI consistently achieves results that agree with known ground truths and often highlights subtle phenomena that may be difficult to ascertain with standard workflows. We conclude by generalizing contrastiveVI to accommodate joint transcriptome and surface protein measurements.

Single-Cell Multiomics

Single-cell RNA sequencing methods have led to improved understanding of the heterogeneity and transcriptomic states present in complex biological systems. Recently, the development of novel single-cell technologies for assaying additional modalities, specifically genomic, epigenomic, proteomic, and spatial data, allows for unprecedented insight into cellular biology. While certain technologies collect multiple measurements from the same cells simultaneously, even when modalities are separately assayed in different cells, we can apply novel computational methods to integrate these data. The application of computational integration methods to multimodal paired and unpaired data results in rich information about the identities of the cells present and the interactions between different levels of biology, such as between genetic variation and transcription. In this review, we both discuss the single-cell technologies for measuring these modalities and describe and characterize a variety of computational integration methods for combining the resulting data to leverage multimodal information toward greater biological insight.

MultiVI: deep generative model for the integration of multimodal data

Jointly profiling the transcriptome, chromatin accessibility and other molecular properties of single cells offers a powerful way to study cellular diversity. Here we present MultiVI, a probabilistic model to analyze such multiomic data and leverage it to enhance single-modality datasets. MultiVI creates a joint representation that allows an analysis of all modalities included in the multiomic input data, even for cells for which one or more modalities are missing. It is available at scvi-tools.org .

Best practices for single-cell analysis across modalities

Recent advances in single-cell technologies have enabled high-throughput molecular profiling of cells across modalities and locations. Single-cell transcriptomics data can now be complemented by chromatin accessibility, surface protein expression, adaptive immune receptor repertoire profiling and spatial information. The increasing availability of single-cell data across modalities has motivated the development of novel computational methods to help analysts derive biological insights. As the field grows, it becomes increasingly difficult to navigate the vast landscape of tools and analysis steps. Here, we summarize independent benchmarking studies of unimodal and multimodal single-cell analysis across modalities to suggest comprehensive best-practice workflows for the most common analysis steps. Where independent benchmarks are not available, we review and contrast popular methods. Our article serves as an entry point for novices in the field of single-cell (multi-)omic analysis and guides advanced users to the most recent best practices.

Multi-batch single-cell comparative atlas construction by deep learning disentanglement

Cell state atlases constructed through single-cell RNA-seq and ATAC-seq analysis are powerful tools for analyzing the effects of genetic and drug treatment-induced perturbations on complex cell systems. Comparative analysis of such atlases can yield new insights into cell state and trajectory alterations. Perturbation experiments often require that single-cell assays be carried out in multiple batches, which can introduce technical distortions that confound the comparison of biological quantities between different batches. Here we propose CODAL, a variational autoencoder-based statistical model which uses a mutual information regularization technique to explicitly disentangle factors related to technical and biological effects. We demonstrate CODAL's capacity for batch-confounded cell type discovery when applied to simulated datasets and embryonic development atlases with gene knockouts. CODAL improves the representation of RNA-seq and ATAC-seq modalities, yields interpretable modules of biological variation, and enables the generalization of other count-based generative models to multi-batched data.

Spatially resolved multiomics of human cardiac niches

The function of a cell is defined by its intrinsic characteristics and its niche: the tissue microenvironment in which it dwells. Here we combine single-cell and spatial transcriptomics data to discover cellular niches within eight regions of the human heart. We map cells to microanatomical locations and integrate knowledge-based and unsupervised structural annotations. We also profile the cells of the human cardiac conduction system1. The results revealed their distinctive repertoire of ion channels, G-protein-coupled receptors (GPCRs) and regulatory networks, and implicated FOXP2 in the pacemaker phenotype. We show that the sinoatrial node is compartmentalized, with a core of pacemaker cells, fibroblasts and glial cells supporting glutamatergic signalling. Using a custom CellPhoneDB.org module, we identify trans-synaptic pacemaker cell interactions with glia. We introduce a druggable target prediction tool, drug2cell, which leverages single-cell profiles and drug-target interactions to provide mechanistic insights into the chronotropic effects of drugs, including GLP-1 analogues. In the epicardium, we show enrichment of both IgG+ and IgA+ plasma cells forming immune niches that may contribute to infection defence. Overall, we provide new clarity to cardiac electro-anatomy and immunology, and our suite of computational approaches can be applied to other tissues and organs.

ExplaiNN: interpretable and transparent neural networks for genomics

Deep learning models such as convolutional neural networks (CNNs) excel in genomic tasks but lack interpretability. We introduce ExplaiNN, which combines the expressiveness of CNNs with the interpretability of linear models. ExplaiNN can predict TF binding, chromatin accessibility, and de novo motifs, achieving performance comparable to state-of-the-art methods. Its predictions are transparent, providing global (cell state level) as well as local (individual sequence level) biological insights into the data. ExplaiNN can serve as a plug-and-play platform for pretrained models and annotated position weight matrices. ExplaiNN aims to accelerate the adoption of deep learning in genomic sequence analysis by domain experts.

A benchmark of computational pipelines for single-cell histone modification data

BACKGROUND

Single-cell histone post translational modification (scHPTM) assays such as scCUT&Tag or scChIP-seq allow single-cell mapping of diverse epigenomic landscapes within complex tissues and are likely to unlock our understanding of various mechanisms involved in development or diseases. Running scHTPM experiments and analyzing the data produced remains challenging since few consensus guidelines currently exist regarding good practices for experimental design and data analysis pipelines.

RESULTS

We perform a computational benchmark to assess the impact of experimental parameters and data analysis pipelines on the ability of the cell representation to recapitulate known biological similarities. We run more than ten thousand experiments to systematically study the impact of coverage and number of cells, of the count matrix construction method, of feature selection and normalization, and of the dimension reduction algorithm used. This allows us to identify key experimental parameters and computational choices to obtain a good representation of single-cell HPTM data. We show in particular that the count matrix construction step has a strong influence on the quality of the representation and that using fixed-size bin counts outperforms annotation-based binning. Dimension reduction methods based on latent semantic indexing outperform others, and feature selection is detrimental, while keeping only high-quality cells has little influence on the final representation as long as enough cells are analyzed.

CONCLUSIONS

This benchmark provides a comprehensive study on how experimental parameters and computational choices affect the representation of single-cell HPTM data. We propose a series of recommendations regarding matrix construction, feature and cell selection, and dimensionality reduction algorithms.

Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data

We motivate and present biVI, which combines the variational autoencoder framework of scVI with biophysically motivated, bivariate models for nascent and mature RNA distributions. While previous approaches to integrate bimodal data via the variational autoencoder framework ignore the causal relationship between measurements, biVI models the biophysical processes that give rise to observations. We demonstrate through simulated benchmarking that biVI captures cell type structure in a low-dimensional space and accurately recapitulates parameter values and copy number distributions. On biological data, biVI provides a scalable route for identifying the biophysical mechanisms underlying gene expression. This analytical approach outlines a generalizable strategy for treating multimodal datasets generated by high-throughput, single-cell genomic assays.

A multi-view latent variable model reveals cellular heterogeneity in complex tissues for paired multimodal single-cell data

MOTIVATION

Single-cell multimodal assays allow us to simultaneously measure two different molecular features of the same cell, enabling new insights into cellular heterogeneity, cell development and diseases. However, most existing methods suffer from inaccurate dimensionality reduction for the joint-modality data, hindering their discovery of novel or rare cell subpopulations.

RESULTS

Here, we present VIMCCA, a computational framework based on variational-assisted multi-view canonical correlation analysis to integrate paired multimodal single-cell data. Our statistical model uses a common latent variable to interpret the common source of variances in two different data modalities. Our approach jointly learns an inference model and two modality-specific non-linear models by leveraging variational inference and deep learning. We perform VIMCCA and compare it with 10 existing state-of-the-art algorithms on four paired multi-modal datasets sequenced by different protocols. Results demonstrate that VIMCCA facilitates integrating various types of joint-modality data, thus leading to more reliable and accurate downstream analysis. VIMCCA improves our ability to identify novel or rare cell subtypes compared to existing widely used methods. Besides, it can also facilitate inferring cell lineage based on joint-modality profiles.

AVAILABILITY AND IMPLEMENTATION

The VIMCCA algorithm has been implemented in our toolkit package scbean (≥0.5.0), and its code has been archived at https://github.com/jhu99/scbean under MIT license.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Multimodal Single-Cell Translation and Alignment with Semi-Supervised Learning

Single-cell multi-omics technologies enable comprehensive interrogation of cellular regulation, yet most single-cell assays measure only one type of activity-such as transcription, chromatin accessibility, DNA methylation, or 3D chromatin architecture-for each cell. To enable a multimodal view for individual cells, we propose Polarbear, a semi-supervised machine learning framework that facilitates missing modality profile prediction and single-cell cross-modality alignment. Polarbear learns to translate between modalities by using data from co-assay measurements coupled with the large quantity of single-assay data available in public databases. This semi-supervised scheme mitigates issues related to low cell quantities and high sparsity in co-assay data. Polarbear first pre-trains a beta-variational autoencoder for each modality using both co-assay and single-assay profiles to learn robust representations of individual cells, and it then uses the co-assay labels to train a translator between these cell representations. This semi-supervised framework enables us to predict missing modality profiles and match single cells across modalities with improved accuracy compared with fully supervised methods, thus facilitating multimodal data integration.

Multi-omics single-cell data integration and regulatory inference with graph-linked embedding

Despite the emergence of experimental methods for simultaneous measurement of multiple omics modalities in single cells, most single-cell datasets include only one modality. A major obstacle in integrating omics data from multiple modalities is that different omics layers typically have distinct feature spaces. Here, we propose a computational framework called GLUE (graph-linked unified embedding), which bridges the gap by modeling regulatory interactions across omics layers explicitly. Systematic benchmarking demonstrated that GLUE is more accurate, robust and scalable than state-of-the-art tools for heterogeneous single-cell multi-omics data. We applied GLUE to various challenging tasks, including triple-omics integration, integrative regulatory inference and multi-omics human cell atlas construction over millions of cells, where GLUE was able to correct previous annotations. GLUE features a modular design that can be flexibly extended and enhanced for new analysis tasks. The full package is available online at https://github.com/gao-lab/GLUE.

Different single-cell data modalities are integrated at atlas-scale by modeling regulatory interactions.