Computational principles and challenges in single-cell data integration

Mosaic integration and knowledge transfer of single-cell multimodal data with MIDAS

Integrating single-cell datasets produced by multiple omics technologies is essential for defining cellular heterogeneity. Mosaic integration, in which different datasets share only some of the measured modalities, poses major challenges, particularly regarding modality alignment and batch effect removal. Here, we present a deep probabilistic framework for the mosaic integration and knowledge transfer (MIDAS) of single-cell multimodal data. MIDAS simultaneously achieves dimensionality reduction, imputation and batch correction of mosaic data by using self-supervised modality alignment and information-theoretic latent disentanglement. We demonstrate its superiority to 19 other methods and reliability by evaluating its performance in trimodal and mosaic integration tasks. We also constructed a single-cell trimodal atlas of human peripheral blood mononuclear cells and tailored transfer learning and reciprocal reference mapping schemes to enable flexible and accurate knowledge transfer from the atlas to new data. Applications in mosaic integration, pseudotime analysis and cross-tissue knowledge transfer on bone marrow mosaic datasets demonstrate the versatility and superiority of MIDAS. MIDAS is available at https://github.com/labomics/midas .

A cell type-aware framework for nominating non-coding variants in Mendelian regulatory disorders

Unsolved Mendelian cases often lack obvious pathogenic coding variants, suggesting potential non-coding etiologies. Here, we present a single cell multi-omic framework integrating embryonic mouse chromatin accessibility, histone modification, and gene expression assays to discover cranial motor neuron (cMN) cis-regulatory elements and subsequently nominate candidate non-coding variants in the congenital cranial dysinnervation disorders (CCDDs), a set of Mendelian disorders altering cMN development. We generate single cell epigenomic profiles for ~86,000 cMNs and related cell types, identifying ~250,000 accessible regulatory elements with cognate gene predictions for ~145,000 putative enhancers. We evaluate enhancer activity for 59 elements using an in vivo transgenic assay and validate 44 (75%), demonstrating that single cell accessibility can be a strong predictor of enhancer activity. Applying our cMN atlas to 899 whole genome sequences from 270 genetically unsolved CCDD pedigrees, we achieve significant reduction in our variant search space and nominate candidate variants predicted to regulate known CCDD disease genes MAFB, PHOX2A, CHN1, and EBF3 - as well as candidates in recurrently mutated enhancers through peak- and gene-centric allelic aggregation. This work delivers non-coding variant discoveries of relevance to CCDDs and a generalizable framework for nominating non-coding variants of potentially high functional impact in other Mendelian disorders.

Benchmarking algorithms for single-cell multi-omics prediction and integration

The development of single-cell multi-omics technology has greatly enhanced our understanding of biology, and in parallel, numerous algorithms have been proposed to predict the protein abundance and/or chromatin accessibility of cells from single-cell transcriptomic information and to integrate various types of single-cell multi-omics data. However, few studies have systematically compared and evaluated the performance of these algorithms. Here, we present a benchmark study of 14 protein abundance/chromatin accessibility prediction algorithms and 18 single-cell multi-omics integration algorithms using 47 single-cell multi-omics datasets. Our benchmark study showed overall totalVI and scArches outperformed the other algorithms for predicting protein abundance, and LS_Lab was the top-performing algorithm for the prediction of chromatin accessibility in most cases. Seurat, MOJITOO and scAI emerge as leading algorithms for vertical integration, whereas totalVI and UINMF excel beyond their counterparts in both horizontal and mosaic integration scenarios. Additionally, we provide a pipeline to assist researchers in selecting the optimal multi-omics prediction and integration algorithm.

scMMO-atlas: a single cell multimodal omics atlas and portal for exploring fine cell heterogeneity and cell dynamics

Single-cell multimodal sequencing parallelly captures multiple modalities of the same cell, providing unparalleled insights into cell heterogeneity and cell dynamics. For example, joint profiling of chromatin accessibility and transcriptome from the same single cell (scATAC + RNA) identified new cell subsets within the well-defined clusters. However, lack of single-cell multimodal omics (scMMO) database has led to data fragmentation, seriously hindering access, utilization and mining of scMMO data. Here, we constructed a scMMO atlas by collecting and integrating various scMMO data, then constructed scMMO database and portal called scMMO-atlas (https://www.biosino.org/scMMO-atlas/). scMMO-atlas includes scATAC + RNA (ISSAAS-seq, SNARE-seq, paired-seq, sci-CAR, scCARE-seq, 10X Multiome and so on), scRNA + protein, scATAC + protein and scTri-modal omics data, with 3 168 824 cells from 27 cell tissues/organs. scMMO-atlas offered an interactive portal for visualization and featured analysis for each modality and the integrated data. Integrated analysis of scATAC + RNA data of mouse cerebral cortex in scMMO-atlas identified more cell subsets compared with unimodal omics data. Among these new cell subsets, there is an early astrocyte subset highly expressed Grm3, called Astro-Grm3. Furthermore, we identified Ex-L6-Tle4-Nrf1, a progenitor of Ex-L6-Tle4, indicating the statistical power provided by the big data in scMMO-atlas. In summary, scMMO-atlas offers cell atlas, database and portal to facilitate data utilization and biological insight.

Cancer cell states: Lessons from ten years of single-cell RNA-sequencing of human tumors

Human tumors are intricate ecosystems composed of diverse genetic clones and malignant cell states that evolve in a complex tumor micro-environment. Single-cell RNA-sequencing (scRNA-seq) provides a compelling strategy to dissect this intricate biology and has enabled a revolution in our ability to understand tumor biology over the last ten years. Here we reflect on this first decade of scRNA-seq in human tumors and highlight some of the powerful insights gleaned from these studies. We first focus on computational approaches for robustly defining cancer cell states and their diversity and highlight some of the most common patterns of gene expression intra-tumor heterogeneity (eITH) observed across cancer types. We then discuss ambiguities in the field in defining and naming such eITH programs. Finally, we highlight critical developments that will facilitate future research and the broader implementation of these technologies in clinical settings.

A primer on single-cell RNA-seq analysis using dendritic cells as a case study

Recent advances in single-cell (sc) transcriptomics have revolutionized our understanding of dendritic cells (DCs), pivotal players of the immune system. ScRNA-sequencing (scRNA-seq) has unraveled a previously unrecognized complexity and heterogeneity of DC subsets, shedding light on their ontogeny and specialized roles. However, navigating the rapid technological progress and computational methods can be daunting for researchers unfamiliar with the field. This review aims to provide immunologists with a comprehensive introduction to sc transcriptomic analysis, offering insights into recent developments in DC biology. Addressing common analytical queries, we guide readers through popular tools and methodologies, supplemented with references to benchmarks and tutorials for in-depth understanding. By examining findings from pioneering studies, we illustrate how computational techniques have expanded our knowledge of DC biology. Through this synthesis, we aim to equip researchers with the necessary tools and knowledge to navigate and leverage scRNA-seq for unraveling the intricacies of DC biology and advancing immunological research.

A Quantitative Computational Framework for Allopolyploid Single-Cell Data Integration and Core Gene Ranking in Development

Polyploidization drives regulatory and phenotypic innovation. How the merger of different genomes contributes to polyploid development is a fundamental issue in evolutionary developmental biology and breeding research. Clarifying this issue is challenging because of genome complexity and the difficulty in tracking stochastic subgenome divergence during development. Recent single-cell sequencing techniques enabled probing subgenome-divergent regulation in the context of cellular differentiation. However, analyzing single-cell data suffers from high error rates due to high dimensionality, noise, and sparsity, and the errors stack up in polyploid analysis due to the increased dimensionality of comparisons between subgenomes of each cell, hindering deeper mechanistic understandings. In this study, we develop a quantitative computational framework, called "pseudo-genome divergence quantification" (pgDQ), for quantifying and tracking subgenome divergence directly at the cellular level. Further comparing with cellular differentiation trajectories derived from single-cell RNA sequencing data allows for an examination of the relationship between subgenome divergence and the progression of development. pgDQ produces robust results and is insensitive to data dropout and noise, avoiding high error rates due to multiple comparisons of genes, cells, and subgenomes. A statistical diagnostic approach is proposed to identify genes that are central to subgenome divergence during development, which facilitates the integration of different data modalities, enabling the identification of factors and pathways that mediate subgenome-divergent activity during development. Case studies have demonstrated that applying pgDQ to single-cell and bulk tissue transcriptomic data promotes a systematic and deeper understanding of how dynamic subgenome divergence contributes to developmental trajectories in polyploid evolution.

SCIntRuler: guiding the integration of multiple single-cell RNA-seq datasets with a novel statistical metric

MOTIVATION

The growing number of single-cell RNA-seq (scRNA-seq) studies highlights the potential benefits of integrating multiple datasets, such as augmenting sample sizes and enhancing analytical robustness. Inherent diversity and batch discrepancies within samples or across studies continue to pose significant challenges for computational analyses. Questions persist in practice, lacking definitive answers: Should we use a specific integration method or opt for simply merging the datasets during joint analysis? Among all the existing data integration methods, which one is more suitable in specific scenarios?

RESULT

To fill the gap, we introduce SCIntRuler, a novel statistical metric for guiding the integration of multiple scRNA-seq datasets. SCIntRuler helps researchers make informed decisions regarding the necessity of data integration and the selection of an appropriate integration method. Our simulations and real data applications demonstrate that SCIntRuler streamlines decision-making processes and facilitates the analysis of diverse scRNA-seq datasets under varying contexts, thereby alleviating the complexities associated with the integration of heterogeneous scRNA-seq datasets.

AVAILABILITY AND IMPLEMENTATION

The implementation of our method is available on CRAN as an open-source R package with a user-friendly manual available: https://cloud.r-project.org/web/packages/SCIntRuler/index.html.

scCAD: Cluster decomposition-based anomaly detection for rare cell identification in single-cell expression data

Single-cell RNA sequencing (scRNA-seq) technologies have become essential tools for characterizing cellular landscapes within complex tissues. Large-scale single-cell transcriptomics holds great potential for identifying rare cell types critical to the pathogenesis of diseases and biological processes. Existing methods for identifying rare cell types often rely on one-time clustering using partial or global gene expression. However, these rare cell types may be overlooked during the clustering phase, posing challenges for their accurate identification. In this paper, we propose a Cluster decomposition-based Anomaly Detection method (scCAD), which iteratively decomposes clusters based on the most differential signals in each cluster to effectively separate rare cell types and achieve accurate identification. We benchmark scCAD on 25 real-world scRNA-seq datasets, demonstrating its superior performance compared to 10 state-of-the-art methods. In-depth case studies across diverse datasets, including mouse airway, brain, intestine, human pancreas, immunology data, and clear cell renal cell carcinoma, showcase scCAD's efficiency in identifying rare cell types in complex biological scenarios. Furthermore, scCAD can correct the annotation of rare cell types and identify immune cell subtypes associated with disease, thereby offering valuable insights into disease progression.

Progress in multifactorial single-cell chromatin profiling methods

Chromatin states play a key role in shaping overall cellular states and fates. Building a complete picture of the functional state of chromatin in cells requires the co-detection of several distinct biochemical aspects. These span DNA methylation, chromatin accessibility, chromosomal conformation, histone posttranslational modifications, and more. While this certainly presents a challenging task, over the past few years many new and creative methods have been developed that now enable co-assay of these different aspects of chromatin at single cell resolution. This field is entering an exciting phase, where a confluence of technological improvements, decreased sequencing costs, and computational innovation are presenting new opportunities to dissect the diversity of chromatin states present in tissues, and how these states may influence gene regulation. In this review, I discuss the spectrum of current experimental approaches for multifactorial chromatin profiling, highlight some of the experimental and analytical challenges, as well as some areas for further innovation.

Global transcription regulation revealed from dynamical correlations in time-resolved single-cell RNA sequencing

Single-cell transcriptomics reveals significant variations in transcriptional activity across cells. Yet, it remains challenging to identify mechanisms of transcription dynamics from static snapshots. It is thus still unknown what drives global transcription dynamics in single cells. We present a stochastic model of gene expression with cell size- and cell cycle-dependent rates in growing and dividing cells that harnesses temporal dimensions of single-cell RNA sequencing through metabolic labeling protocols and cel lcycle reporters. We develop a parallel and highly scalable approximate Bayesian computation method that corrects for technical variation and accurately quantifies absolute burst frequency, burst size, and degradation rate along the cell cycle at a transcriptome-wide scale. Using Bayesian model selection, we reveal scaling between transcription rates and cell size and unveil waves of gene regulation across the cell cycle-dependent transcriptome. Our study shows that stochastic modeling of dynamical correlations identifies global mechanisms of transcription regulation. A record of this paper's transparent peer review process is included in the supplemental information.

A gene regulatory network-aware graph learning method for cell identity annotation in single-cell RNA-seq data

Cell identity annotation for single-cell transcriptome data is a crucial process for constructing cell atlases, unraveling pathogenesis, and inspiring therapeutic approaches. Currently, the efficacy of existing methodologies is contingent upon specific data sets. Nevertheless, such data are often sourced from various batches, sequencing technologies, tissues, and even species. Notably, the gene regulatory relationship remains unaffected by the aforementioned factors, highlighting the extensive gene interactions within organisms. Therefore, we propose scHGR, an automated annotation tool designed to leverage gene regulatory relationships in constructing gene-mediated cell communication graphs for single-cell transcriptome data. This strategy helps reduce noise from diverse data sources while establishing distant cellular connections, yielding valuable biological insights. Experiments involving 22 scenarios demonstrate that scHGR precisely and consistently annotates cell identities, benchmarked against state-of-the-art methods. Crucially, scHGR uncovers novel subtypes within peripheral blood mononuclear cells, specifically from CD4+ T cells and cytotoxic T cells. Furthermore, by characterizing a cell atlas comprising 56 cell types for COVID-19 patients, scHGR identifies vital factors like IL1 and calcium ions, offering insights for targeted therapeutic interventions.

A Cell Cycle-Aware Network for Data Integration and Label Transferring of Single-Cell RNA-Seq and ATAC-Seq

In recent years, the integration of single-cell multi-omics data has provided a more comprehensive understanding of cell functions and internal regulatory mechanisms from a non-single omics perspective, but it still suffers many challenges, such as omics-variance, sparsity, cell heterogeneity, and confounding factors. As it is known, the cell cycle is regarded as a confounder when analyzing other factors in single-cell RNA-seq data, but it is not clear how it will work on the integrated single-cell multi-omics data. Here, a cell cycle-aware network (CCAN) is developed to remove cell cycle effects from the integrated single-cell multi-omics data while keeping the cell type-specific variations. This is the first computational model to study the cell-cycle effects in the integration of single-cell multi-omics data. Validations on several benchmark datasets show the outstanding performance of CCAN in a variety of downstream analyses and applications, including removing cell cycle effects and batch effects of scRNA-seq datasets from different protocols, integrating paired and unpaired scRNA-seq and scATAC-seq data, accurately transferring cell type labels from scRNA-seq to scATAC-seq data, and characterizing the differentiation process from hematopoietic stem cells to different lineages in the integration of differentiation data.

scaDA: A novel statistical method for differential analysis of single-cell chromatin accessibility sequencing data

Single-cell ATAC-seq sequencing data (scATAC-seq) has been widely used to investigate chromatin accessibility on the single-cell level. One important application of scATAC-seq data analysis is differential chromatin accessibility (DA) analysis. However, the data characteristics of scATAC-seq such as excessive zeros and large variability of chromatin accessibility across cells impose a unique challenge for DA analysis. Existing statistical methods focus on detecting the mean difference of the chromatin accessible regions while overlooking the distribution difference. Motivated by real data exploration that distribution difference exists among cell types, we introduce a novel composite statistical test named "scaDA", which is based on zero-inflated negative binomial model (ZINB), for performing differential distribution analysis of chromatin accessibility by jointly testing the abundance, prevalence and dispersion simultaneously. Benefiting from both dispersion shrinkage and iterative refinement of mean and prevalence parameter estimates, scaDA demonstrates its superiority to both ZINB-based likelihood ratio tests and published methods by achieving the highest power and best FDR control in a comprehensive simulation study. In addition to demonstrating the highest power in three real sc-multiome data analyses, scaDA successfully identifies differentially accessible regions in microglia from sc-multiome data for an Alzheimer's disease (AD) study that are most enriched in GO terms related to neurogenesis and the clinical phenotype of AD, and AD-associated GWAS SNPs.

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.

Contextual AI models for single-cell protein biology

Understanding protein function and developing molecular therapies require deciphering the cell types in which proteins act as well as the interactions between proteins. However, modeling protein interactions across biological contexts remains challenging for existing algorithms. Here, we introduce Pinnacle, a geometric deep learning approach that generates context-aware protein representations. Leveraging a multi-organ single-cell atlas, Pinnacle learns on contextualized protein interaction networks to produce 394,760 protein representations from 156 cell type contexts across 24 tissues. Pinnacle's embedding space reflects cellular and tissue organization, enabling zero-shot retrieval of the tissue hierarchy. Pretrained protein representations can be adapted for downstream tasks: enhancing 3D structure-based representations for resolving immuno-oncological protein interactions, and investigating drugs' effects across cell types. Pinnacle outperforms state-of-the-art models in nominating therapeutic targets for rheumatoid arthritis and inflammatory bowel diseases, and pinpoints cell type contexts with higher predictive capability than context-free models. Pinnacle's ability to adjust its outputs based on the context in which it operates paves way for large-scale context-specific predictions in biology.

Data enhancement in the age of spatial biology

Unveiling the intricate interplay of cells in their native environment lies at the heart of understanding fundamental biological processes and unraveling disease mechanisms, particularly in complex diseases like cancer. Spatial transcriptomics (ST) offers a revolutionary lens into the spatial organization of gene expression within tissues, empowering researchers to study both cell heterogeneity and microenvironments in health and disease. However, current ST technologies often face limitations in either resolution or the number of genes profiled simultaneously. Integrating ST data with complementary sources, such as single-cell transcriptomics and detailed tissue staining images, presents a powerful solution to overcome these limitations. This review delves into the computational approaches driving the integration of spatial transcriptomics with other data types. By illuminating the key challenges and outlining the current algorithmic solutions, we aim to highlight the immense potential of these methods to revolutionize our understanding of cancer biology.

mosaicMPI: a framework for modular data integration across cohorts and -omics modalities

Advances in molecular profiling have facilitated generation of large multi-modal datasets that can potentially reveal critical axes of biological variation underlying complex diseases. Distilling biological meaning, however, requires computational strategies that can perform mosaic integration across diverse cohorts and datatypes. Here, we present mosaicMPI, a framework for discovery of low to high-resolution molecular programs representing both cell types and states, and integration within and across datasets into a network representing biological themes. Using existing datasets in glioblastoma, we demonstrate that this approach robustly integrates single cell and bulk programs across multiple platforms. Clinical and molecular annotations from cohorts are statistically propagated onto this network of programs, yielding a richly characterized landscape of biological themes. This enables deep understanding of individual tumor samples, systematic exploration of relationships between modalities, and generation of a reference map onto which new datasets can rapidly be mapped. mosaicMPI is available at https://github.com/MorrissyLab/mosaicMPI.

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.

A systematic overview of single-cell transcriptomics databases, their use cases, and limitations

Rapid advancements in high-throughput single-cell RNA-seq (scRNA-seq) technologies and experimental protocols have led to the generation of vast amounts of transcriptomic data that populates several online databases and repositories. Here, we systematically examined large-scale scRNA-seq databases, categorizing them based on their scope and purpose such as general, tissue-specific databases, disease-specific databases, cancer-focused databases, and cell type-focused databases. Next, we discuss the technical and methodological challenges associated with curating large-scale scRNA-seq databases, along with current computational solutions. We argue that understanding scRNA-seq databases, including their limitations and assumptions, is crucial for effectively utilizing this data to make robust discoveries and identify novel biological insights. Such platforms can help bridge the gap between computational and wet lab scientists through user-friendly web-based interfaces needed for democratizing access to single-cell data. These platforms would facilitate interdisciplinary research, enabling researchers from various disciplines to collaborate effectively. This review underscores the importance of leveraging computational approaches to unravel the complexities of single-cell data and offers a promising direction for future research in the field.

Application of spatial-omics to the classification of kidney biopsy samples in transplantation

Improvement of long-term outcomes through targeted treatment is a primary concern in kidney transplant medicine. Currently, the validation of a rejection diagnosis and subsequent treatment depends on the histological assessment of allograft biopsy samples, according to the Banff classification system. However, the lack of (early) disease-specific tissue markers hinders accurate diagnosis and thus timely intervention. This challenge mainly results from an incomplete understanding of the pathophysiological processes underlying late allograft failure. Integration of large-scale multimodal approaches for investigating allograft biopsy samples might offer new insights into this pathophysiology, which are necessary for the identification of novel therapeutic targets and the development of tailored immunotherapeutic interventions. Several omics technologies - including transcriptomic, proteomic, lipidomic and metabolomic tools (and multimodal data analysis strategies) - can be applied to allograft biopsy investigation. However, despite their successful application in research settings and their potential clinical value, several barriers limit the broad implementation of many of these tools into clinical practice. Among spatial-omics technologies, mass spectrometry imaging, which is under-represented in the transplant field, has the potential to enable multi-omics investigations that might expand the insights gained with current clinical analysis technologies.

Quartet RNA reference materials improve the quality of transcriptomic data through ratio-based profiling

Certified RNA reference materials are indispensable for assessing the reliability of RNA sequencing to detect intrinsically small biological differences in clinical settings, such as molecular subtyping of diseases. As part of the Quartet Project for quality control and data integration of multi-omics profiling, we established four RNA reference materials derived from immortalized B-lymphoblastoid cell lines from four members of a monozygotic twin family. Additionally, we constructed ratio-based transcriptome-wide reference datasets between two samples, providing cross-platform and cross-laboratory 'ground truth'. Investigation of the intrinsically subtle biological differences among the Quartet samples enables sensitive assessment of cross-batch integration of transcriptomic measurements at the ratio level. The Quartet RNA reference materials, combined with the ratio-based reference datasets, can serve as unique resources for assessing and improving the quality of transcriptomic data in clinical and biological settings.

Multi-omics data integration using ratio-based quantitative profiling with Quartet reference materials

Characterization and integration of the genome, epigenome, transcriptome, proteome and metabolome of different datasets is difficult owing to a lack of ground truth. Here we develop and characterize suites of publicly available multi-omics reference materials of matched DNA, RNA, protein and metabolites derived from immortalized cell lines from a family quartet of parents and monozygotic twin daughters. These references provide built-in truth defined by relationships among the family members and the information flow from DNA to RNA to protein. We demonstrate how using a ratio-based profiling approach that scales the absolute feature values of a study sample relative to those of a concurrently measured common reference sample produces reproducible and comparable data suitable for integration across batches, labs, platforms and omics types. Our study identifies reference-free 'absolute' feature quantification as the root cause of irreproducibility in multi-omics measurement and data integration and establishes the advantages of ratio-based multi-omics profiling with common reference materials.

Integration of spatial and single-cell data across modalities with weakly linked features

Although single-cell and spatial sequencing methods enable simultaneous measurement of more than one biological modality, no technology can capture all modalities within the same cell. For current data integration methods, the feasibility of cross-modal integration relies on the existence of highly correlated, a priori 'linked' features. We describe matching X-modality via fuzzy smoothed embedding (MaxFuse), a cross-modal data integration method that, through iterative coembedding, data smoothing and cell matching, uses all information in each modality to obtain high-quality integration even when features are weakly linked. MaxFuse is modality-agnostic and demonstrates high robustness and accuracy in the weak linkage scenario, achieving 20~70% relative improvement over existing methods under key evaluation metrics on benchmarking datasets. A prototypical example of weak linkage is the integration of spatial proteomic data with single-cell sequencing data. On two example analyses of this type, MaxFuse enabled the spatial consolidation of proteomic, transcriptomic and epigenomic information at single-cell resolution on the same tissue section.

Accurate and efficient integrative reference-informed spatial domain detection for spatial transcriptomics

Spatially resolved transcriptomics (SRT) studies are becoming increasingly common and large, offering unprecedented opportunities in mapping complex tissue structures and functions. Here we present integrative and reference-informed tissue segmentation (IRIS), a computational method designed to characterize tissue spatial organization in SRT studies through accurately and efficiently detecting spatial domains. IRIS uniquely leverages single-cell RNA sequencing data for reference-informed detection of biologically interpretable spatial domains, integrating multiple SRT slices while explicitly considering correlations both within and across slices. We demonstrate the advantages of IRIS through in-depth analysis of six SRT datasets encompassing diverse technologies, tissues, species and resolutions. In these applications, IRIS achieves substantial accuracy gains (39-1,083%) and speed improvements (4.6-666.0) in moderate-sized datasets, while representing the only method applicable for large datasets including Stereo-seq and 10x Xenium. As a result, IRIS reveals intricate brain structures, uncovers tumor microenvironment heterogeneity and detects structural changes in diabetes-affected testis, all with exceptional speed and accuracy.

Deciphering brain cellular and behavioral mechanisms: Insights from single-cell and spatial RNA sequencing

The brain is a complex computing system composed of a multitude of interacting neurons. The computational outputs of this system determine the behavior and perception of every individual. Each brain cell expresses thousands of genes that dictate the cell's function and physiological properties. Therefore, deciphering the molecular expression of each cell is of great significance for understanding its characteristics and role in brain function. Additionally, the positional information of each cell can provide crucial insights into their involvement in local brain circuits. In this review, we briefly overview the principles of single-cell RNA sequencing and spatial transcriptomics, the potential issues and challenges in their data processing, and their applications in brain research. We further outline several promising directions in neuroscience that could be integrated with single-cell RNA sequencing, including neurodevelopment, the identification of novel brain microstructures, cognition and behavior, neuronal cell positioning, molecules and cells related to advanced brain functions, sleep-wake cycles/circadian rhythms, and computational modeling of brain function. We believe that the deep integration of these directions with single-cell and spatial RNA sequencing can contribute significantly to understanding the roles of individual cells or cell types in these specific functions, thereby making important contributions to addressing critical questions in those fields. This article is categorized under: RNA Evolution and Genomics > Computational Analyses of RNA RNA in Disease and Development > RNA in Development RNA in Disease and Development > RNA in Disease.

Machine learning integrative approaches to advance computational immunology

The study of immunology, traditionally reliant on proteomics to evaluate individual immune cells, has been revolutionized by single-cell RNA sequencing. Computational immunologists play a crucial role in analysing these datasets, moving beyond traditional protein marker identification to encompass a more detailed view of cellular phenotypes and their functional roles. Recent technological advancements allow the simultaneous measurements of multiple cellular components-transcriptome, proteome, chromatin, epigenetic modifications and metabolites-within single cells, including in spatial contexts within tissues. This has led to the generation of complex multiscale datasets that can include multimodal measurements from the same cells or a mix of paired and unpaired modalities. Modern machine learning (ML) techniques allow for the integration of multiple "omics" data without the need for extensive independent modelling of each modality. This review focuses on recent advancements in ML integrative approaches applied to immunological studies. We highlight the importance of these methods in creating a unified representation of multiscale data collections, particularly for single-cell and spatial profiling technologies. Finally, we discuss the challenges of these holistic approaches and how they will be instrumental in the development of a common coordinate framework for multiscale studies, thereby accelerating research and enabling discoveries in the computational immunology field.

scCross: efficient search for rare subpopulations across multiple single-cell samples

MOTIVATION

Identifying rare cell types is an important task to capture the heterogeneity of single-cell data, such as scRNA-seq. The widespread availability of such data enables to aggregate multiple samples, corresponding for example to different donors, into the same study. Yet, such aggregated data is often subject to batch effects between samples. Clustering it therefore generally requires the use of data integration methods, which can lead to overcorrection, making the identification of rare cells difficult. We present scCross, a biclustering method identifying rare subpopulations of cells present across multiple single-cell samples. It jointly identifies a group of cells with specific marker genes by relying on a global sum criterion, computed over entire subpopulation of cells, rather than pairwise comparisons between individual cells. This proves robust with respect to the high variability of scRNA-seq data, in particular batch effects.

RESULTS

We show through several case studies that scCross is able to identify rare subpopulations across multiple samples without performing prior data integration. Namely, it identifies a cilium subpopulation with potential new ciliary genes from lung cancer cells, which is not detected by typical alternatives. It also highlights rare subpopulations in human pancreas samples sequenced with different protocols, despite visible shifts in expression levels between batches. We further show that scCross outperforms typical alternatives at identifying a target rare cell type in a controlled experiment with artificially created batch effects. This shows the ability of scCross to efficiently identify rare cell subpopulations characterized by specific genes despite the presence of batch effects.

AVAILABILITY AND IMPLEMENTATION

The R and Scala implementation of scCross is freely available on GitHub, at https://github.com/agerniers/scCross/. A snapshot of the code and the data underlying this article are available on Zenodo, at https://zenodo.org/doi/10.5281/zenodo.10471063.

Omics Approaches to Investigate the Pathogenesis of Suicide

Suicide is the second leading cause of death in U.S. adolescents and young adults and is generally associated with a psychiatric disorder. Suicidal behavior has a complex etiology and pathogenesis. Moderate heritability suggests genetic causes. Associations between childhood and recent life adversity indicate contributions from epigenetic factors. Genomic contributions to suicide pathogenesis remain largely unknown. This article is based on a workshop held to design strategies to identify molecular drivers of suicide neurobiology that would be putative new treatment targets. The panel determined that while bulk tissue studies provide comprehensive information, single-nucleus approaches that identify cell type-specific changes are needed. While single-nuclei techniques lack information on cytoplasm, processes, spines, and synapses, spatial multiomic technologies on intact tissue detect cell alterations specific to brain tissue layers and subregions. Because suicide has genetic and environmental drivers, multiomic approaches that combine cell type-specific epigenome, transcriptome, and proteome provide a more complete picture of pathogenesis. To determine the direction of effect of suicide risk gene variants on RNA and protein expression and how these interact with epigenetic marks, single-nuclei and spatial multiomics quantitative trait loci maps should be integrated with whole-genome sequencing and genome-wide association databases. The workshop concluded with a recommendation for the formation of an international suicide biology consortium that will bring together brain banks and investigators with expertise in cutting-edge omics technologies to delineate the biology of suicide and identify novel potential treatment targets to be tested in cellular and animal models for drug and biomarker discovery to guide suicide prevention.

Multi-view data visualisation via manifold learning

Non-linear dimensionality reduction can be performed by manifold learning approaches, such as stochastic neighbour embedding (SNE), locally linear embedding (LLE) and isometric feature mapping (ISOMAP). These methods aim to produce two or three latent embeddings, primarily to visualise the data in intelligible representations. This manuscript proposes extensions of Student's t-distributed SNE (t-SNE), LLE and ISOMAP, for dimensionality reduction and visualisation of multi-view data. Multi-view data refers to multiple types of data generated from the same samples. The proposed multi-view approaches provide more comprehensible projections of the samples compared to the ones obtained by visualising each data-view separately. Commonly, visualisation is used for identifying underlying patterns within the samples. By incorporating the obtained low-dimensional embeddings from the multi-view manifold approaches into the K-means clustering algorithm, it is shown that clusters of the samples are accurately identified. Through extensive comparisons of novel and existing multi-view manifold learning algorithms on real and synthetic data, the proposed multi-view extension of t-SNE, named multi-SNE, is found to have the best performance, quantified both qualitatively and quantitatively by assessing the clusterings obtained. The applicability of multi-SNE is illustrated by its implementation in the newly developed and challenging multi-omics single-cell data. The aim is to visualise and identify cell heterogeneity and cell types in biological tissues relevant to health and disease. In this application, multi-SNE provides an improved performance over single-view manifold learning approaches and a promising solution for unified clustering of multi-omics single-cell data.

The future of rapid and automated single-cell data analysis using reference mapping

As the number of single-cell datasets continues to grow rapidly, workflows that map new data to well-curated reference atlases offer enormous promise for the biological community. In this perspective, we discuss key computational challenges and opportunities for single-cell reference-mapping algorithms. We discuss how mapping algorithms will enable the integration of diverse datasets across disease states, molecular modalities, genetic perturbations, and diverse species and will eventually replace manual and laborious unsupervised clustering pipelines.

Scalable integration of multiomic single-cell data using generative adversarial networks

MOTIVATION

Single-cell profiling has become a common practice to investigate the complexity of tissues, organs, and organisms. Recent technological advances are expanding our capabilities to profile various molecular layers beyond the transcriptome such as, but not limited to, the genome, the epigenome, and the proteome. Depending on the experimental procedure, these data can be obtained from separate assays or the very same cells. Yet, integration of more than two assays is currently not supported by the majority of the computational frameworks avaiable.

RESULTS

We here propose a Multi-Omic data integration framework based on Wasserstein Generative Adversarial Networks suitable for the analysis of paired or unpaired data with a high number of modalities (>2). At the core of our strategy is a single network trained on all modalities together, limiting the computational burden when many molecular layers are evaluated.

AVAILABILITY AND IMPLEMENTATION

Source code of our framework is available at https://github.com/vgiansanti/MOWGAN.

scmFormer Integrates Large-Scale Single-Cell Proteomics and Transcriptomics Data by Multi-Task Transformer

Transformer-based models have revolutionized single cell RNA-seq (scRNA-seq) data analysis. However, their applicability is challenged by the complexity and scale of single-cell multi-omics data. Here a novel single-cell multi-modal/multi-task transformer (scmFormer) is proposed to fill up the existing blank of integrating single-cell proteomics with other omics data. Through systematic benchmarking, it is demonstrated that scmFormer excels in integrating large-scale single-cell multimodal data and heterogeneous multi-batch paired multi-omics data, while preserving shared information across batchs and distinct biological information. scmFormer achieves 54.5% higher average F1 score compared to the second method in transferring cell-type labels from single-cell transcriptomics to proteomics data. Using COVID-19 datasets, it is presented that scmFormer successfully integrates over 1.48 million cells on a personal computer. Moreover, it is also proved that scmFormer performs better than existing methods on generating the unmeasured modality and is well-suited for spatial multi-omic data. Thus, scmFormer is a powerful and comprehensive tool for analyzing single-cell multi-omics data.

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.

Single-cell multiomics guided mechanistic understanding of Fontan-associated liver disease

The Fontan operation is the current standard of care for single-ventricle congenital heart disease. Individuals with a Fontan circulation (FC) exhibit central venous hypertension and face life-threatening complications of hepatic fibrosis, known as Fontan-associated liver disease (FALD). The fundamental biology and mechanisms of FALD are little understood. Here, we generated a transcriptomic and epigenomic atlas of human FALD at single-cell resolution using multiomic snRNA-ATAC-seq. We found profound cell type-specific transcriptomic and epigenomic changes in FC livers. Central hepatocytes (cHep) exhibited the most substantial changes, featuring profound metabolic reprogramming. These cHep changes preceded substantial activation of hepatic stellate cells and liver fibrosis, suggesting cHep as a potential first "responder" in the pathogenesis of FALD. We also identified a network of ligand-receptor pairs that transmit signals from cHep to hepatic stellate cells, which may promote their activation and liver fibrosis. We further experimentally demonstrated that activins A and B promote fibrotic activation in vitro and identified mechanisms of activin A's transcriptional activation in FALD. Together, our single-cell transcriptomic and epigenomic atlas revealed mechanistic insights into the pathogenesis of FALD and may aid identification of potential therapeutic targets.

scButterfly: a versatile single-cell cross-modality translation method via dual-aligned variational autoencoders

Recent advancements for simultaneously profiling multi-omics modalities within individual cells have enabled the interrogation of cellular heterogeneity and molecular hierarchy. However, technical limitations lead to highly noisy multi-modal data and substantial costs. Although computational methods have been proposed to translate single-cell data across modalities, broad applications of the methods still remain impeded by formidable challenges. Here, we propose scButterfly, a versatile single-cell cross-modality translation method based on dual-aligned variational autoencoders and data augmentation schemes. With comprehensive experiments on multiple datasets, we provide compelling evidence of scButterfly's superiority over baseline methods in preserving cellular heterogeneity while translating datasets of various contexts and in revealing cell type-specific biological insights. Besides, we demonstrate the extensive applications of scButterfly for integrative multi-omics analysis of single-modality data, data enhancement of poor-quality single-cell multi-omics, and automatic cell type annotation of scATAC-seq data. Moreover, scButterfly can be generalized to unpaired data training, perturbation-response analysis, and consecutive translation.

Integration of single-cell proteomic datasets through distinctive proteins in cell clusters

The use of mass spectrometry and antibody-based sequencing technologies at the single-cell level has led to an increase in single-cell proteomic datasets. Integrating these datasets is crucial to eliminate the batch effect that often arises due to their limited sequencing molecules. Although methods for horizontally integrating high-dimensional single-cell transcriptomic datasets can also be applied to single-cell proteomic datasets, a specialized approach explicitly tailored for low-dimensional proteomic datasets may enhance the integration process. Here, we introduce SCPRO-HI, an algorithm for the horizontal integration of antibody-based single-cell proteomic datasets. It utilizes a hierarchical cell anchoring technique to match cells based on the similarity of distinctive proteins for constituting cell clusters. A novel variational auto-encoder model is employed for correcting batch effects on the protein abundances, eliminating the need for mapping them into a new domain. Moreover, we propose a technique for extending the algorithm to high-dimensional datasets. The performance of the SCPRO-HI algorithm is evaluated using simulated and real-world single-cell proteomic datasets. The findings demonstrate our algorithm outperforms state-of-the-art methods, achieving a 75% higher silhouette score while preserving HVPs 13% better. Furthermore, the algorithm shows competitive performance in transcriptomic datasets, suggesting potential for integrating high-dimensional mass-spectrometry-based proteomic datasets.

A Multimodal Omics Framework to Empower Target Discovery for Cardiovascular Regeneration

Ischaemic heart disease is a global healthcare challenge with high morbidity and mortality. Early revascularisation in acute myocardial infarction has improved survival; however, limited regenerative capacity and microvascular dysfunction often lead to impaired function and the development of heart failure. New mechanistic insights are required to identify robust targets for the development of novel strategies to promote regeneration. Single-cell RNA sequencing (scRNA-seq) has enabled profiling and analysis of the transcriptomes of individual cells at high resolution. Applications of scRNA-seq have generated single-cell atlases for multiple species, revealed distinct cellular compositions for different regions of the heart, and defined multiple mechanisms involved in myocardial injury-induced regeneration. In this review, we summarise findings from studies of healthy and injured hearts in multiple species and spanning different developmental stages. Based on this transformative technology, we propose a multi-species, multi-omics, meta-analysis framework to drive the discovery of new targets to promote cardiovascular regeneration.

Recent advances in differential expression analysis for single-cell RNA-seq and spatially resolved transcriptomic studies

Differential expression (DE) analysis is a necessary step in the analysis of single-cell RNA sequencing (scRNA-seq) and spatially resolved transcriptomics (SRT) data. Unlike traditional bulk RNA-seq, DE analysis for scRNA-seq or SRT data has unique characteristics that may contribute to the difficulty of detecting DE genes. However, the plethora of DE tools that work with various assumptions makes it difficult to choose an appropriate one. Furthermore, a comprehensive review on detecting DE genes for scRNA-seq data or SRT data from multi-condition, multi-sample experimental designs is lacking. To bridge such a gap, here, we first focus on the challenges of DE detection, then highlight potential opportunities that facilitate further progress in scRNA-seq or SRT analysis, and finally provide insights and guidance in selecting appropriate DE tools or developing new computational DE methods.

Spatial transcriptomics data and analytical methods: An updated perspective

Spatial transcriptomics (ST) is a newly emerging field that integrates high-resolution imaging and transcriptomic data to enable the high-throughput analysis of the spatial localization of transcripts in diverse biological systems. The rapid progress in this field necessitates the development of innovative computational methods to effectively tackle the distinct challenges posed by the analysis of ST data. These platforms, integrating AI techniques, offer a promising avenue for understanding disease mechanisms and expediting drug discovery. Despite significant advances in the development of ST data analysis techniques, there is an ongoing need to enhance these models for increased biological relevance. In this review, we briefly discuss the ST-related databases and current deep-learning-based models for spatial transcriptome data analyses and highlight their roles and future perspectives in biomedical applications.

Characterizing the impacts of dataset imbalance on single-cell data integration

Computational methods for integrating single-cell transcriptomic data from multiple samples and conditions do not generally account for imbalances in the cell types measured in different datasets. In this study, we examined how differences in the cell types present, the number of cells per cell type and the cell type proportions across samples affect downstream analyses after integration. The Iniquitate pipeline assesses the robustness of integration results after perturbing the degree of imbalance between datasets. Benchmarking of five state-of-the-art single-cell RNA sequencing integration techniques in 2,600 integration experiments indicates that sample imbalance has substantial impacts on downstream analyses and the biological interpretation of integration results. Imbalance perturbation led to statistically significant variation in unsupervised clustering, cell type classification, differential expression and marker gene annotation, query-to-reference mapping and trajectory inference. We quantified the impacts of imbalance through newly introduced properties-aggregate cell type support and minimum cell type center distance. To better characterize and mitigate impacts of imbalance, we introduce balanced clustering metrics and imbalanced integration guidelines for integration method users.

Semi-automated approaches for interrogating spatial heterogeneity of tissue samples

Tissues are spatially orchestrated ecosystems composed of heterogeneous cell populations and non-cellular elements. Tissue components' interactions shape the biological processes that govern homeostasis and disease, thus comprehensive insights into tissues' composition are crucial for understanding their biology. Recently, advancements in the spatial biology field enabled the in-depth analyses of tissue architecture at single-cell resolution, while preserving the structural context. The increasing number of biomarkers analyzed, together with whole tissue imaging, generate datasets approaching several hundreds of gigabytes in size, which are rich sources of valuable knowledge but require investments in infrastructure and resources for extracting quantitative information. The analysis of multiplex whole-tissue images requires extensive training and experience in data analysis. Here, we showcase how a set of open-source tools can allow semi-automated image data extraction to study the spatial composition of tissues with a focus on tumor microenvironment (TME). With the use of Lunaphore COMET platform, we interrogated lung cancer specimens where we examined the expression of 20 biomarkers. Subsequently, the tissue composition was interrogated using an in-house optimized nuclei detection algorithm followed by a newly developed image artifact exclusion approach. Thereafter, the data was processed using several publicly available tools, highlighting the compatibility of COMET-derived data with currently available image analysis frameworks. In summary, we showcased an innovative semi-automated workflow that highlights the ease of adoption of multiplex imaging to explore TME composition at single-cell resolution using a simple slide in, data out approach. Our workflow is easily transferrable to various cohorts of specimens to provide a toolset for spatial cellular dissection of the tissue composition.

A call for a unified and multimodal definition of cellular identity in the enteric nervous system

The enteric nervous system (ENS) is a tantalizing frontier in neuroscience. With the recent emergence of single cell transcriptomic technologies, this rare and poorly understood tissue has begun to be better characterized in recent years. A precise functional mapping of enteric neuron diversity is critical for understanding ENS biology and enteric neuropathies. Nonetheless, this pursuit has faced considerable technical challenges. By leveraging different methods to compare available primary mouse and human ENS datasets, we underscore the urgent need for careful identity annotation, achieved through the harmonization and advancements of wet lab and computational techniques. We took different approaches including differential gene expression, module scoring, co-expression and correlation analysis, unbiased biological function hierarchical clustering, data integration and label transfer to compare and contrast functional annotations of several independently reported ENS datasets. These analyses highlight substantial discrepancies stemming from an overreliance on transcriptomics data without adequate validation in tissues. To achieve a comprehensive understanding of enteric neuron identity and their functional context, it is imperative to expand tissue sources and incorporate innovative technologies such as multiplexed imaging, electrophysiology, spatial transcriptomics, as well as comprehensive profiling of epigenome, proteome, and metabolome. Harnessing human pluripotent stem cell (hPSC) models provides unique opportunities for delineating lineage trees of the human ENS, and offers unparalleled advantages, including their scalability and compatibility with genetic manipulation and unbiased screens. We encourage a paradigm shift in our comprehension of cellular complexity and function in the ENS by calling for large-scale collaborative efforts and research investments.

A Cell Cycle-aware Network for Data Integration and Label Transferring of Single-cell RNA-seq and ATAC-seq

In recent years, the integration of single-cell multi-omics data has provided a more comprehensive understanding of cell functions and internal regulatory mechanisms from a non-single omics perspective, but it still suffers many challenges, such as omics-variance, sparsity, cell heterogeneity and confounding factors. As we know, cell cycle is regarded as a confounder when analyzing other factors in single-cell RNA-seq data, but it's not clear how it will work on the integrated single-cell multi-omics data. Here, we developed a Cell Cycle-Aware Network (CCAN) to remove cell cycle effects from the integrated single-cell multi-omics data while keeping the cell type-specific variations. This is the first computational model to study the cell-cycle effects in the integration of single-cell multi-omics data. Validations on several benchmark datasets show the out-standing performance of CCAN in a variety of downstream analyses and applications, including removing cell cycle effects and batch effects of scRNA-seq datasets from different protocols, integrating paired and unpaired scRNA-seq and scATAC-seq data, accurately transferring cell type labels from scRNA-seq to scATAC-seq data, and characterizing the differentiation process from hematopoietic stem cells to different lineages in the integration of differentiation data.

scDesign3 generates realistic in silico data for multimodal single-cell and spatial omics

We present a statistical simulator, scDesign3, to generate realistic single-cell and spatial omics data, including various cell states, experimental designs and feature modalities, by learning interpretable parameters from real data. Using a unified probabilistic model for single-cell and spatial omics data, scDesign3 infers biologically meaningful parameters; assesses the goodness-of-fit of inferred cell clusters, trajectories and spatial locations; and generates in silico negative and positive controls for benchmarking computational tools.

Stabilized mosaic single-cell data integration using unshared features

Currently available single-cell omics technologies capture many unique features with different biological information content. Data integration aims to place cells, captured with different technologies, onto a common embedding to facilitate downstream analytical tasks. Current horizontal data integration techniques use a set of common features, thereby ignoring non-overlapping features and losing information. Here we introduce StabMap, a mosaic data integration technique that stabilizes mapping of single-cell data by exploiting the non-overlapping features. StabMap first infers a mosaic data topology based on shared features, then projects all cells onto supervised or unsupervised reference coordinates by traversing shortest paths along the topology. We show that StabMap performs well in various simulation contexts, facilitates 'multi-hop' mosaic data integration where some datasets do not share any features and enables the use of spatial gene expression features for mapping dissociated single-cell data onto a spatial transcriptomic reference.

Semi-supervised integration of single-cell transcriptomics data

Batch effects in single-cell RNA-seq data pose a significant challenge for comparative analyses across samples, individuals, and conditions. Although batch effect correction methods are routinely applied, data integration often leads to overcorrection and can result in the loss of biological variability. In this work we present STACAS, a batch correction method for scRNA-seq that leverages prior knowledge on cell types to preserve biological variability upon integration. Through an open-source benchmark, we show that semi-supervised STACAS outperforms state-of-the-art unsupervised methods, as well as supervised methods such as scANVI and scGen. STACAS scales well to large datasets and is robust to incomplete and imprecise input cell type labels, which are commonly encountered in real-life integration tasks. We argue that the incorporation of prior cell type information should be a common practice in single-cell data integration, and we provide a flexible framework for semi-supervised batch effect correction.