Sfaira accelerates data and model reuse in single cell genomics

scPerturb: harmonized single-cell perturbation data

Analysis across a growing number of single-cell perturbation datasets is hampered by poor data interoperability. To facilitate development and benchmarking of computational methods, we collect a set of 44 publicly available single-cell perturbation-response datasets with molecular readouts, including transcriptomics, proteomics and epigenomics. We apply uniform quality control pipelines and harmonize feature annotations. The resulting information resource, scPerturb, enables development and testing of computational methods, and facilitates comparison and integration across datasets. We describe energy statistics (E-statistics) for quantification of perturbation effects and significance testing, and demonstrate E-distance as a general distance measure between sets of single-cell expression profiles. We illustrate the application of E-statistics for quantifying similarity and efficacy of perturbations. The perturbation-response datasets and E-statistics computation software are publicly available at scperturb.org. This work provides an information resource for researchers working with single-cell perturbation data and recommendations for experimental design, including optimal cell counts and read depth.

Single-cell transcriptomic atlas-guided development of CAR-T cells for the treatment of acute myeloid leukemia

Chimeric antigen receptor T cells (CAR-T cells) have emerged as a powerful treatment option for individuals with B cell malignancies but have yet to achieve success in treating acute myeloid leukemia (AML) due to a lack of safe targets. Here we leveraged an atlas of publicly available RNA-sequencing data of over 500,000 single cells from 15 individuals with AML and tissue from 9 healthy individuals for prediction of target antigens that are expressed on malignant cells but lacking on healthy cells, including T cells. Aided by this high-resolution, single-cell expression approach, we computationally identify colony-stimulating factor 1 receptor and cluster of differentiation 86 as targets for CAR-T cell therapy in AML. Functional validation of these established CAR-T cells shows robust in vitro and in vivo efficacy in cell line- and human-derived AML models with minimal off-target toxicity toward relevant healthy human tissues. This provides a strong rationale for further clinical development.

Scaling cross-tissue single-cell annotation models

Identifying cellular identities (both novel and well-studied) is one of the key use cases in single-cell transcriptomics. While supervised machine learning has been leveraged to automate cell annotation predictions for some time, there has been relatively little progress both in scaling neural networks to large data sets and in constructing models that generalize well across diverse tissues and biological contexts up to whole organisms. Here, we propose scTab, an automated, feature-attention-based cell type prediction model specific to tabular data, and train it using a novel data augmentation scheme across a large corpus of single-cell RNA-seq observations (22.2 million human cells in total). In addition, scTab leverages deep ensembles for uncertainty quantification. Moreover, we account for ontological relationships between labels in the model evaluation to accommodate for differences in annotation granularity across datasets. On this large-scale corpus, we show that cross-tissue annotation requires nonlinear models and that the performance of scTab scales in terms of training dataset size as well as model size - demonstrating the advantage of scTab over current state-of-the-art linear models in this context. Additionally, we show that the proposed data augmentation schema improves model generalization. In summary, we introduce a de novo cell type prediction model for single-cell RNA-seq data that can be trained across a large-scale collection of curated datasets from a diverse selection of human tissues and demonstrate the benefits of using deep learning methods in this paradigm. Our codebase, training data, and model checkpoints are publicly available at https://github.com/theislab/scTab to further enable rigorous benchmarks of foundation models for single-cell RNA-seq data.

Delineating mouse β-cell identity during lifetime and in diabetes with a single cell atlas

Although multiple pancreatic islet single-cell RNA-sequencing (scRNA-seq) datasets have been generated, a consensus on pancreatic cell states in development, homeostasis and diabetes as well as the value of preclinical animal models is missing. Here, we present an scRNA-seq cross-condition mouse islet atlas (MIA), a curated resource for interactive exploration and computational querying. We integrate over 300,000 cells from nine scRNA-seq datasets consisting of 56 samples, varying in age, sex and diabetes models, including an autoimmune type 1 diabetes model (NOD), a glucotoxicity/lipotoxicity type 2 diabetes model (db/db) and a chemical streptozotocin β-cell ablation model. The β-cell landscape of MIA reveals new cell states during disease progression and cross-publication differences between previously suggested marker genes. We show that β-cells in the streptozotocin model transcriptionally correlate with those in human type 2 diabetes and mouse db/db models, but are less similar to human type 1 diabetes and mouse NOD β-cells. We also report pathways that are shared between β-cells in immature, aged and diabetes models. MIA enables a comprehensive analysis of β-cell responses to different stressors, providing a roadmap for the understanding of β-cell plasticity, compensation and demise.

Respiratory epithelial cell types, states and fates in the era of single-cell RNA-sequencing

Standalone and consortia-led single-cell atlases of healthy and diseased human airways generated with single-cell RNA-sequencing (scRNA-seq) have ushered in a new era in respiratory research. Numerous discoveries, including the pulmonary ionocyte, potentially novel cell fates, and a diversity of cell states among common and rare epithelial cell types have highlighted the extent of cellular heterogeneity and plasticity in the respiratory tract. scRNA-seq has also played a pivotal role in our understanding of host-virus interactions in coronavirus disease 2019 (COVID-19). However, as our ability to generate large quantities of scRNA-seq data increases, along with a growing number of scRNA-seq protocols and data analysis methods, new challenges related to the contextualisation and downstream applications of insights are arising. Here, we review the fundamental concept of cellular identity from the perspective of single-cell transcriptomics in the respiratory context, drawing attention to the need to generate reference annotations and to standardise the terminology used in literature. Findings about airway epithelial cell types, states and fates obtained from scRNA-seq experiments are compared and contrasted with information accumulated through the use of conventional methods. This review attempts to discuss major opportunities and to outline some of the key limitations of the modern-day scRNA-seq that need to be addressed to enable efficient and meaningful integration of scRNA-seq data from different platforms and studies, with each other as well as with data from other high-throughput sequencing-based genomic, transcriptomic and epigenetic analyses.

Biologically informed deep learning to query gene programs in single-cell atlases

The increasing availability of large-scale single-cell atlases has enabled the detailed description of cell states. In parallel, advances in deep learning allow rapid analysis of newly generated query datasets by mapping them into reference atlases. However, existing data transformations learned to map query data are not easily explainable using biologically known concepts such as genes or pathways. Here we propose expiMap, a biologically informed deep-learning architecture that enables single-cell reference mapping. ExpiMap learns to map cells into biologically understandable components representing known 'gene programs'. The activity of each cell for a gene program is learned while simultaneously refining them and learning de novo programs. We show that expiMap compares favourably to existing methods while bringing an additional layer of interpretability to integrative single-cell analysis. Furthermore, we demonstrate its applicability to analyse single-cell perturbation responses in different tissues and species and resolve responses of patients who have coronavirus disease 2019 to different treatments across cell types.

Increasing resolution in stress neurobiology: from single cells to complex group behaviors

Stress can have severe psychological and physiological consequences. Thus, inappropriate regulation of the stress response is linked to the etiology of mood and anxiety disorders. The generation and implementation of preclinical animal models represent valuable tools to explore and characterize the mechanisms underlying the pathophysiology of stress-related psychiatric disorders and the development of novel pharmacological strategies. In this commentary, we discuss the strengths and limitations of state-of-the-art molecular and computational advances employed in stress neurobiology research, with a focus on the ever-increasing spatiotemporal resolution in cell biology and behavioral science. Finally, we share our perspective on future directions in the fields of preclinical and human stress research.

Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.

SimBu: bias-aware simulation of bulk RNA-seq data with variable cell-type composition

MOTIVATION

As complex tissues are typically composed of various cell types, deconvolution tools have been developed to computationally infer their cellular composition from bulk RNA sequencing (RNA-seq) data. To comprehensively assess deconvolution performance, gold-standard datasets are indispensable. Gold-standard, experimental techniques like flow cytometry or immunohistochemistry are resource-intensive and cannot be systematically applied to the numerous cell types and tissues profiled with high-throughput transcriptomics. The simulation of 'pseudo-bulk' data, generated by aggregating single-cell RNA-seq expression profiles in pre-defined proportions, offers a scalable and cost-effective alternative. This makes it feasible to create in silico gold standards that allow fine-grained control of cell-type fractions not conceivable in an experimental setup. However, at present, no simulation software for generating pseudo-bulk RNA-seq data exists.

RESULTS

We developed SimBu, an R package capable of simulating pseudo-bulk samples based on various simulation scenarios, designed to test specific features of deconvolution methods. A unique feature of SimBu is the modeling of cell-type-specific mRNA bias using experimentally derived or data-driven scaling factors. Here, we show that SimBu can generate realistic pseudo-bulk data, recapitulating the biological and statistical features of real RNA-seq data. Finally, we illustrate the impact of mRNA bias on the evaluation of deconvolution tools and provide recommendations for the selection of suitable methods for estimating mRNA content. SimBu is a user-friendly and flexible tool for simulating realistic pseudo-bulk RNA-seq datasets serving as in silico gold-standard for assessing cell-type deconvolution methods.

AVAILABILITY AND IMPLEMENTATION

SimBu is freely available at https://github.com/omnideconv/SimBu as an R package under the GPL-3 license.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A transcriptional cross species map of pancreatic islet cells

OBJECTIVE

Pancreatic islets of Langerhans secrete hormones to regulate systemic glucose levels. Emerging evidence suggests that islet cells are functionally heterogeneous to allow a fine-tuned and efficient endocrine response to physiological changes. A precise description of the molecular basis of this heterogeneity, in particular linking animal models to human islets, is an important step towards identifying the factors critical for endocrine cell function in physiological and pathophysiological conditions.

METHODS

In this study, we used single-cell RNA sequencing to profile more than 50'000 endocrine cells isolated from healthy human, pig and mouse pancreatic islets and characterize transcriptional heterogeneity and evolutionary conservation of those cells across the three species. We systematically delineated endocrine cell types and α- and β-cell heterogeneity through prior knowledge- and data-driven gene sets shared across species, which altogether capture common and differential cellular properties, transcriptional dynamics and putative driving factors of state transitions.

RESULTS

We showed that global endocrine expression profiles correlate, and that critical identity and functional markers are shared between species, while only approximately 20% of cell type enriched expression is conserved. We resolved distinct human α- and β-cell states that form continuous transcriptional landscapes. These states differentially activate maturation and hormone secretion programs, which are related to regulatory hormone receptor expression, signaling pathways and different types of cellular stress responses. Finally, we mapped mouse and pig cells to the human reference and observed that the spectrum of human α- and β-cell heterogeneity and aspects of such functional gene expression are better recapitulated in the pig than mouse data.

CONCLUSIONS

Here, we provide a high-resolution transcriptional map of healthy human islet cells and their murine and porcine counterparts, which is easily queryable via an online interface. This comprehensive resource informs future efforts that focus on pancreatic endocrine function, failure and regeneration, and enables to assess molecular conservation in islet biology across species for translational purposes.

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.

Integrating single-cell genomics pipelines to discover mechanisms of stem cell differentiation

Pluripotent stem cells underpin a growing sector that leverages their differentiation potential for research, industry, and clinical applications. This review evaluates the landscape of methods in single-cell transcriptomics that are enabling accelerated discovery in stem cell science. We focus on strategies for scaling stem cell differentiation through multiplexed single-cell analyses, for evaluating molecular regulation of cell differentiation using new analysis algorithms, and methods for integration and projection analysis to classify and benchmark stem cell derivatives against in vivo cell types. By discussing the available methods, comparing their strengths, and illustrating strategies for developing integrated analysis pipelines, we provide user considerations to inform their implementation and interpretation.