Automatic cell type identification methods for single-cell RNA sequencing

Single-cell RNA-sequencing analysis reveals α-syn induced astrocyte-neuron crosstalk-mediated neurotoxicity

Accumulation of alpha-synuclein (α-syn) is a key pathological hallmark of synucleinopathies and has been shown to negatively impact neuronal function and activity. α-syn is an important factor contributing to astrocyte overactivation, though the effect of astrocyte overactivation on neurons remains unclear. Single-cell RNA sequencing data of mouse brain frontal cortex and midbrain from Hua-Syn (A53T) and wild type mice were utilized from the GEO database. Enrichment analysis, protein-protein interaction networks, and cell-cell interaction networks all indicated enhanced communication between astrocytes and neurons, along with the involvement of TNF and inflammation-related signaling pathways. In vitro experiments were performed to further explore the mechanism of neurotoxicity in astrocyte-neuron crosstalk. Astrocytes were treated by α-syn, neuronal TNFR1 receptors were antagonized by R-7050, and the cells were co-cultured after 24 h treatment. ELISA results revealed that cytokines such as TNF-α and IL-6 were significantly upregulated in astrocytes following the endocytosis of α-syn. Immunofluorescence (IF) showed neuronal dendritic reduction, axon elongation and increased co-localisation of TNFR1 receptor expression. Western blot showed up-regulation of PKR, P-eIF2α and ATF4 protein expression. Conversely, after antagonizing neuronal TNFR1 receptors with the R-7050 chemical inhibitor, neuronal synaptic structure was significantly restored and the expression of PKR, P-eIF2α and ATF4 was down-regulated. In summary, TNF-α acts as a signaling molecule mediating the up-regulated astrocyte-neuron crosstalk, providing new insights into the pathogenesis of α-syn-related neurological disorders.

Coding and Non-Coding Transcriptomic Landscape of Aortic Complications in Marfan Syndrome

Marfan syndrome (MFS) is a rare congenital disorder of the connective tissue, leading to thoracic aortic aneurysms (TAA) and dissection, among other complications. Currently, the most efficient strategy to prevent life-threatening dissection is preventive surgery. Periodic imaging applying complex techniques is required to monitor TAA progression and to guide the timing of surgical intervention. Thus, there is an acute demand for non-invasive biomarkers for diagnosis and prognosis, as well as for innovative therapeutic targets of MFS. Unraveling the intricate pathomolecular mechanisms underlying the syndrome is vital to address these needs. High-throughput platforms are particularly well-suited for this purpose, as they enable the integration of different datasets, such as transcriptomic and epigenetic profiles. In this narrative review, we summarize relevant studies investigating changes in both the coding and non-coding transcriptome and epigenome in MFS-induced TAA. The collective findings highlight the implicated pathways, such as TGF-β signaling, extracellular matrix structure, inflammation, and mitochondrial dysfunction. Potential candidates as biomarkers, such as miR-200c, as well as therapeutic targets emerged, like Tfam, associated with mitochondrial respiration, or miR-632, stimulating endothelial-to-mesenchymal transition. While these discoveries are promising, rigorous and extensive validation in large patient cohorts is indispensable to confirm their clinical relevance and therapeutic potential.

Target-Oriented Reference Construction for supervised cell-type identification in scRNA-seq

Cell-type identification is the most crucial step in single cell RNA-seq (scRNA-seq) data analysis, for which the supervised cell-type identification method is a desired solution due to the accuracy and efficiency. The performance of such methods is highly dependent on the quality of the reference data. Even though there are many supervised cell-type identification tools, there is no method for selecting and constructing reference data. Here we develop Target-Oriented Reference Construction (TORC), a widely applicable strategy for constructing reference given target dataset in scRNA-seq supervised cell-type identification. TORC alleviates the differences in data distribution and cell-type composition between reference and target. Extensive benchmarks on simulated and real data analyses demonstrate consistent improvements in cell-type identification from TORC. TORC is freely available at https://github.com/weix21/TORC.

CAraCAl: CAMML with the integration of chromatin accessibility

BACKGROUND

A vital step in analyzing single-cell data is ascertaining which cell types are present in a dataset, and at what abundance. In many diseases, the proportions of varying cell types can have important implications for health and prognosis. Most approaches for cell type annotation have centered around cell typing for single-cell RNA-sequencing (scRNA-seq) and have had promising success. However, reliable methods are lacking for many other single-cell modalities such as single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq), which quantifies the extent to which genes of interest in each cell are epigenetically "open" for expression.

RESULTS

To leverage the informative potential of scATAC-seq data, we developed CAMML with the integration of chromatin accessibility (CAraCAl), a bioinformatic method that performs cell typing on scATAC-seq data. CAraCAl performs cell typing by scoring each cell for its enrichment of cell type-specific gene sets. These gene sets are composed of the most upregulated or downregulated genes present in each cell type according to projected gene activity.

CONCLUSIONS

We found that CAraCAl does not improve performance beyond CAMML when scRNA-seq is present, but if only scATAC-seq is available, CAraCAl performs cell typing relatively successfully. As such, we also discuss best practices for cell typing and the strengths and weaknesses of various cell annotation options.

Leveraging Multi-Tissue, Single-Cell Atlases as Tools to Elucidate Shared Mechanisms of Immune-Mediated Inflammatory Diseases

The observation that certain therapeutic strategies for targeting inflammation benefit patients with distinct immune-mediated inflammatory diseases (IMIDs) is exemplified by the success of TNF blockade in conditions including rheumatoid arthritis, ulcerative colitis, and skin psoriasis, albeit only for subsets of individuals with each condition. This suggests intersecting "nodes" in inflammatory networks at a molecular and cellular level may drive and/or maintain IMIDs, being "shared" between traditionally distinct diagnoses without mapping neatly to a single clinical phenotype. In line with this proposition, integrative tumour tissue analyses in oncology have highlighted novel cell states acting across diverse cancers, with important implications for precision medicine. Drawing upon advances in the oncology field, this narrative review will first summarise learnings from the Human Cell Atlas in health as a platform for interrogating IMID tissues. It will then review cross-disease studies to date that inform this endeavour before considering future directions in the field.

Multiscale topology classifies cells in subcellular spatial transcriptomics

Spatial transcriptomics measures in situ gene expression at millions of locations within a tissue1, hitherto with some trade-off between transcriptome depth, spatial resolution and sample size2. Although integration of image-based segmentation has enabled impactful work in this context, it is limited by imaging quality and tissue heterogeneity. By contrast, recent array-based technologies offer the ability to measure the entire transcriptome at subcellular resolution across large samples3-6. Presently, there exist no approaches for cell type identification that directly leverage this information to annotate individual cells. Here we propose a multiscale approach to automatically classify cell types at this subcellular level, using both transcriptomic information and spatial context. We showcase this on both targeted and whole-transcriptome spatial platforms, improving cell classification and morphology for human kidney tissue and pinpointing individual sparsely distributed renal mouse immune cells without reliance on image data. By integrating these predictions into a topological pipeline based on multiparameter persistent homology7-9, we identify cell spatial relationships characteristic of a mouse model of lupus nephritis, which we validate experimentally by immunofluorescence. The proposed framework readily generalizes to new platforms, providing a comprehensive pipeline bridging different levels of biological organization from genes through to tissues.

Single-cell and single-nucleus RNA-sequencing from paired normal-adenocarcinoma lung samples provide both common and discordant biological insights

Whether single-cell RNA-sequencing (scRNA-seq) captures the same biological information as single-nucleus RNA-sequencing (snRNA-seq) remains uncertain and likely to be context-dependent. Herein, a head-to-head comparison was performed in matched normal-adenocarcinoma human lung samples to assess biological insights derived from scRNA-seq versus snRNA-seq and better understand the cellular transition that occurs from normal to tumoral tissue. Here, the transcriptome of 160,621 cells/nuclei was obtained. In non-tumor lung, cell type proportions varied widely between scRNA-seq and snRNA-seq with a predominance of immune cells in the former (81.5%) and epithelial cells (69.9%) in the later. Similar results were observed in adenocarcinomas, in addition to an overall increase in cell type heterogeneity and a greater prevalence of copy number variants in cells of epithelial origin, which suggests malignant assignment. The cell type transition that occurs from normal lung tissue to adenocarcinoma was not always concordant whether cells or nuclei were examined. As expected, large differential expression of the whole-cell and nuclear transcriptome was observed, but cell-type specific changes of paired normal and tumor lung samples revealed a set of common genes in the cells and nuclei involved in cancer-related pathways. In addition, we showed that the ligand-receptor interactome landscape of lung adenocarcinoma was largely different whether cells or nuclei were evaluated. Immune cell depletion in fresh specimens partly mitigated the difference in cell type composition observed between cells and nuclei. However, the extra manipulations affected cell viability and amplified the transcriptional signatures associated with stress responses. In conclusion, research applications focussing on mapping the immune landscape of lung adenocarcinoma benefit from scRNA-seq in fresh samples, whereas snRNA-seq of frozen samples provide a low-cost alternative to profile more epithelial and cancer cells, and yield cell type proportions that more closely match tissue content.

Partial label learning for automated classification of single-cell transcriptomic profiles

Single-cell RNA sequencing (scRNASeq) data plays a major role in advancing our understanding of developmental biology. An important current question is how to classify transcriptomic profiles obtained from scRNASeq experiments into the various cell types and identify the lineage relationship for individual cells. Because of the fast accumulation of datasets and the high dimensionality of the data, it has become challenging to explore and annotate single-cell transcriptomic profiles by hand. To overcome this challenge, automated classification methods are needed. Classical approaches rely on supervised training datasets. However, due to the difficulty of obtaining data annotated at single-cell resolution, we propose instead to take advantage of partial annotations. The partial label learning framework assumes that we can obtain a set of candidate labels containing the correct one for each data point, a simpler setting than requiring a fully supervised training dataset. We study and extend when needed state-of-the-art multi-class classification methods, such as SVM, kNN, prototype-based, logistic regression and ensemble methods, to the partial label learning framework. Moreover, we study the effect of incorporating the structure of the label set into the methods. We focus particularly on the hierarchical structure of the labels, as commonly observed in developmental processes. We show, on simulated and real datasets, that these extensions enable to learn from partially labeled data, and perform predictions with high accuracy, particularly with a nonlinear prototype-based method. We demonstrate that the performances of our methods trained with partially annotated data reach the same performance as fully supervised data. Finally, we study the level of uncertainty present in the partially annotated data, and derive some prescriptive results on the effect of this uncertainty on the accuracy of the partial label learning methods. Overall our findings show how hierarchical and non-hierarchical partial label learning strategies can help solve the problem of automated classification of single-cell transcriptomic profiles, interestingly these methods rely on a much less stringent type of annotated datasets compared to fully supervised learning methods.

Best practices for the execution, analysis, and data storage of plant single-cell/nucleus transcriptomics

Single-cell and single-nucleus RNA-sequencing technologies capture the expression of plant genes at an unprecedented resolution. Therefore, these technologies are gaining traction in plant molecular and developmental biology for elucidating the transcriptional changes across cell types in a specific tissue or organ, upon treatments, in response to biotic and abiotic stresses, or between genotypes. Despite the rapidly accelerating use of these technologies, collective and standardized experimental and analytical procedures to support the acquisition of high-quality data sets are still missing. In this commentary, we discuss common challenges associated with the use of single-cell transcriptomics in plants and propose general guidelines to improve reproducibility, quality, comparability, and interpretation and to make the data readily available to the community in this fast-developing field of research.

HyGAnno: hybrid graph neural network-based cell type annotation for single-cell ATAC sequencing data

Reliable cell type annotations are crucial for investigating cellular heterogeneity in single-cell omics data. Although various computational approaches have been proposed for single-cell RNA sequencing (scRNA-seq) annotation, high-quality cell labels are still lacking in single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq) data, because of extreme sparsity and inconsistent chromatin accessibility between datasets. Here, we present a novel automated cell annotation method that transfers cell type information from a well-labeled scRNA-seq reference to an unlabeled scATAC-seq target, via a parallel graph neural network, in a semi-supervised manner. Unlike existing methods that utilize only gene expression or gene activity features, HyGAnno leverages genome-wide accessibility peak features to facilitate the training process. In addition, HyGAnno reconstructs a reference-target cell graph to detect cells with low prediction reliability, according to their specific graph connectivity patterns. HyGAnno was assessed across various datasets, showcasing its strengths in precise cell annotation, generating interpretable cell embeddings, robustness to noisy reference data and adaptability to tumor tissues.

A hyperparameter-randomized ensemble approach for robust clustering across diverse datasets

Clustering analysis is widely used to group objects by similarity, but for complex datasets such as those produced by single-cell analysis, the currently available clustering methods are limited by accuracy, robustness, ease of use, and interpretability. To address these limitations, we developed an ensemble clustering method with hyperparameter randomization that outperforms other methods across a broad range of single-cell and synthetic datasets, without the need for manual hyperparameter selection. In addition to hard cluster labels, it also outputs soft cluster memberships to characterize continuum-like regions and per cell overlap scores to quantify the uncertainty in cluster assignment. We demonstrate the improved clustering interpretability from these features by tracing the intermediate stages between handwritten digits in the MNIST dataset, and between tanycyte subpopulations in the hypothalamus. This approach improves the quality of clustering and subsequent downstream analyses for single-cell datasets, and may also prove useful in other fields of data analysis.

Characterization of human pluripotent stem cell differentiation by single-cell dual-omics analyses

In vivo differentiation of human pluripotent stem cells (hPSCs) has unique advantages, such as multilineage differentiation, angiogenesis, and close cell-cell interactions. To systematically investigate multilineage differentiation mechanisms of hPSCs, we constructed the in vivo hPSC differentiation landscape containing 239,670 cells using teratoma models. We identified 43 cell types, inferred 18 cell differentiation trajectories, and characterized common and specific gene regulation patterns during hPSC differentiation at both transcriptional and epigenetic levels. Additionally, we developed the developmental single-cell Basic Local Alignment Search Tool (dscBLAST), an R-based cell identification tool, to simplify the identification processes of developmental cells. Using dscBLAST, we aligned cells in multiple differentiation models to normally developing cells to further understand their differentiation states. Overall, our study offers new insights into stem cell differentiation and human embryonic development; dscBLAST shows favorable cell identification performance, providing a powerful identification tool for developmental cells.

Hierarchical and automated cell-type annotation and inference of cancer cell of origin with Census

MOTIVATION

Cell-type annotation is a time-consuming yet critical first step in the analysis of single-cell RNA-seq data, especially when multiple similar cell subtypes with overlapping marker genes are present. Existing automated annotation methods have a number of limitations, including requiring large reference datasets, high computation time, shallow annotation resolution, and difficulty in identifying cancer cells or their most likely cell of origin.

RESULTS

We developed Census, a biologically intuitive and fully automated cell-type identification method for single-cell RNA-seq data that can deeply annotate normal cells in mammalian tissues and identify malignant cells and their likely cell of origin. Motivated by the inherently stratified developmental programs of cellular differentiation, Census infers hierarchical cell-type relationships and uses gradient-boosted \decision trees that capitalize on nodal cell-type relationships to achieve high prediction speed and accuracy. When benchmarked on 44 atlas-scale normal and cancer, human and mouse tissues, Census significantly outperforms state-of-the-art methods across multiple metrics and naturally predicts the cell-of-origin of different cancers. Census is pretrained on the Tabula Sapiens to classify 175 cell-types from 24 organs; however, users can seamlessly train their own models for customized applications.

AVAILABILITY AND IMPLEMENTATION

Census is available at Zenodo https://zenodo.org/records/7017103 and on our Github https://github.com/sjdlabgroup/Census.

Leveraging gene correlations in single cell transcriptomic data

BACKGROUND

Many approaches have been developed to overcome technical noise in single cell RNA-sequencing (scRNAseq). As researchers dig deeper into data-looking for rare cell types, subtleties of cell states, and details of gene regulatory networks-there is a growing need for algorithms with controllable accuracy and fewer ad hoc parameters and thresholds. Impeding this goal is the fact that an appropriate null distribution for scRNAseq cannot simply be extracted from data when ground truth about biological variation is unknown (i.e., usually).

RESULTS

We approach this problem analytically, assuming that scRNAseq data reflect only cell heterogeneity (what we seek to characterize), transcriptional noise (temporal fluctuations randomly distributed across cells), and sampling error (i.e., Poisson noise). We analyze scRNAseq data without normalization-a step that skews distributions, particularly for sparse data-and calculate p-values associated with key statistics. We develop an improved method for selecting features for cell clustering and identifying gene-gene correlations, both positive and negative. Using simulated data, we show that this method, which we call BigSur (Basic Informatics and Gene Statistics from Unnormalized Reads), captures even weak yet significant correlation structures in scRNAseq data. Applying BigSur to data from a clonal human melanoma cell line, we identify thousands of correlations that, when clustered without supervision into gene communities, align with known cellular components and biological processes, and highlight potentially novel cell biological relationships.

CONCLUSIONS

New insights into functionally relevant gene regulatory networks can be obtained using a statistically grounded approach to the identification of gene-gene correlations.

Methods for cell-type annotation on scRNA-seq data: A recent overview

The evolution of single-cell technology is ongoing, continually generating massive amounts of data that reveal many mysteries surrounding intricate diseases. However, their drawbacks continue to constrain us. Among these, annotating cell types in single-cell gene expressions pose a substantial challenge, despite the myriad of tools at our disposal. The rapid growth in data, resources, and tools has consequently brought about significant alterations in this area over the years. In our study, we spotlight all note-worthy cell type annotation techniques developed over the past four years. We provide an overview of the latest trends in this field, showcasing the most advanced methods in taxonomy. Our research underscores the demand for additional tools that incorporate a biological context and also predicts that the rising trend of graph neural network approaches will likely lead this research field in the coming years.

Artificial Intelligence Models for Cell Type and Subtype Identification Based on Single-Cell RNA Sequencing Data in Vision Science

Single-cell RNA sequencing (scRNA-seq) provides a high throughput, quantitative and unbiased framework for scientists in many research fields to identify and characterize cell types within heterogeneous cell populations from various tissues. However, scRNA-seq based identification of discrete cell-types is still labor intensive and depends on prior molecular knowledge. Artificial intelligence has provided faster, more accurate, and user-friendly approaches for cell-type identification. In this review, we discuss recent advances in cell-type identification methods using artificial intelligence techniques based on single-cell and single-nucleus RNA sequencing data in vision science. The main purpose of this review paper is to assist vision scientists not only to select suitable datasets for their problems, but also to be aware of the appropriate computational tools to perform their analysis. Developing novel methods for scRNA-seq data analysis remains to be addressed in future studies.

A Comparison of Cell-Cell Interaction Prediction Tools Based on scRNA-seq Data

Computational prediction of cell-cell interactions (CCIs) is becoming increasingly important for understanding disease development and progression. We present a benchmark study of available CCI prediction tools based on single-cell RNA sequencing (scRNA-seq) data. By comparing prediction outputs with a manually curated gold standard for idiopathic pulmonary fibrosis (IPF), we evaluated prediction performance and processing time of several CCI prediction tools, including CCInx, CellChat, CellPhoneDB, iTALK, NATMI, scMLnet, SingleCellSignalR, and an ensemble of tools. According to our results, CellPhoneDB and NATMI are the best performer CCI prediction tools, among the ones analyzed, when we define a CCI as a source-target-ligand-receptor tetrad. In addition, we recommend specific tools according to different types of research projects and discuss the possible future paths in the field.

sc-ImmuCC: hierarchical annotation for immune cell types in single-cell RNA-seq

Accurately identifying immune cell types in single-cell RNA-sequencing (scRNA-Seq) data is critical to uncovering immune responses in health or disease conditions. However, the high heterogeneity and sparsity of scRNA-Seq data, as well as the similarity in gene expression among immune cell types, poses a great challenge for accurate identification of immune cell types in scRNA-Seq data. Here, we developed a tool named sc-ImmuCC for hierarchical annotation of immune cell types from scRNA-Seq data, based on the optimized gene sets and ssGSEA algorithm. sc-ImmuCC simulates the natural differentiation of immune cells, and the hierarchical annotation includes three layers, which can annotate nine major immune cell types and 29 cell subtypes. The test results showed its stable performance and strong consistency among different tissue datasets with average accuracy of 71-90%. In addition, the optimized gene sets and hierarchical annotation strategy could be applied to other methods to improve their annotation accuracy and the spectrum of annotated cell types and subtypes. We also applied sc-ImmuCC to a dataset composed of COVID-19, influenza, and healthy donors, and found that the proportion of monocytes in patients with COVID-19 and influenza was significantly higher than that in healthy people. The easy-to-use sc-ImmuCC tool provides a good way to comprehensively annotate immune cell types from scRNA-Seq data, and will also help study the immune mechanism underlying physiological and pathological conditions.

Mapping human adult hippocampal neurogenesis with single-cell transcriptomics: Reconciling controversy or fueling the debate?

The notion of exploiting the regenerative potential of the human brain in physiological aging or neurological diseases represents a particularly attractive alternative to conventional strategies for enhancing or restoring brain function. However, a major first question to address is whether the human brain does possess the ability to regenerate. The existence of human adult hippocampal neurogenesis (AHN) has been at the center of a fierce scientific debate for many years. The advent of single-cell transcriptomic technologies was initially viewed as a panacea to resolving this controversy. However, recent single-cell RNA sequencing studies in the human hippocampus yielded conflicting results. Here, we critically discuss and re-analyze previously published AHN-related single-cell transcriptomic datasets. We argue that, although promising, the single-cell transcriptomic profiling of AHN in the human brain can be confounded by methodological, conceptual, and biological factors that need to be consistently addressed across studies and openly discussed within the scientific community.

Cell-type annotation with accurate unseen cell-type identification using multiple references

The recent advances in single-cell RNA sequencing (scRNA-seq) techniques have stimulated efforts to identify and characterize the cellular composition of complex tissues. With the advent of various sequencing techniques, automated cell-type annotation using a well-annotated scRNA-seq reference becomes popular. But it relies on the diversity of cell types in the reference, which may not capture all the cell types present in the query data of interest. There are generally unseen cell types in the query data of interest because most data atlases are obtained for different purposes and techniques. Identifying previously unseen cell types is essential for improving annotation accuracy and uncovering novel biological discoveries. To address this challenge, we propose mtANN (multiple-reference-based scRNA-seq data annotation), a new method to automatically annotate query data while accurately identifying unseen cell types with the aid of multiple references. Key innovations of mtANN include the integration of deep learning and ensemble learning to improve prediction accuracy, and the introduction of a new metric that considers three complementary aspects to distinguish between unseen cell types and shared cell types. Additionally, we provide a data-driven method to adaptively select a threshold for identifying previously unseen cell types. We demonstrate the advantages of mtANN over state-of-the-art methods for unseen cell-type identification and cell-type annotation on two benchmark dataset collections, as well as its predictive power on a collection of COVID-19 datasets. The source code and tutorial are available at https://github.com/Zhangxf-ccnu/mtANN.

A scalable sparse neural network framework for rare cell type annotation of single-cell transcriptome data

Automatic cell type annotation methods are increasingly used in single-cell RNA sequencing (scRNA-seq) analysis due to their fast and precise advantages. However, current methods often fail to account for the imbalance of scRNA-seq datasets and ignore information from smaller populations, leading to significant biological analysis errors. Here, we introduce scBalance, an integrated sparse neural network framework that incorporates adaptive weight sampling and dropout techniques for auto-annotation tasks. Using 20 scRNA-seq datasets with varying scales and degrees of imbalance, we demonstrate that scBalance outperforms current methods in both intra- and inter-dataset annotation tasks. Additionally, scBalance displays impressive scalability in identifying rare cell types in million-level datasets, as shown in the bronchoalveolar cell landscape. scBalance is also significantly faster than commonly used tools and comes in a user-friendly format, making it a superior tool for scRNA-seq analysis on the Python-based platform.

Pan-cancer classification of single cells in the tumour microenvironment

Single-cell RNA sequencing can reveal valuable insights into cellular heterogeneity within tumour microenvironments (TMEs), paving the way for a deep understanding of cellular mechanisms contributing to cancer. However, high heterogeneity among the same cancer types and low transcriptomic variation in immune cell subsets present challenges for accurate, high-resolution confirmation of cells' identities. Here we present scATOMIC; a modular annotation tool for malignant and non-malignant cells. We trained scATOMIC on >300,000 cancer, immune, and stromal cells defining a pan-cancer reference across 19 common cancers and employ a hierarchical approach, outperforming current classification methods. We extensively confirm scATOMIC's accuracy on 225 tumour biopsies encompassing >350,000 cancer and a variety of TME cells. Lastly, we demonstrate scATOMIC's practical significance to accurately subset breast cancers into clinically relevant subtypes and predict tumours' primary origin across metastatic cancers. Our approach represents a broadly applicable strategy to analyse multicellular cancer TMEs.

Hierarchical cell-type identifier accurately distinguishes immune-cell subtypes enabling precise profiling of tissue microenvironment with single-cell RNA-sequencing

Single-cell RNA-seq enabled in-depth study on tissue micro-environment and immune-profiling, where a crucial step is to annotate cell identity. Immune cells play key roles in many diseases, whereas their activities are hard to track due to their diverse and highly variable nature. Existing cell-type identifiers had limited performance for this purpose. We present HiCAT, a hierarchical, marker-based cell-type identifier utilising gene set analysis for statistical scoring for given markers. It features successive identification of major-type, minor-type and subsets utilising subset markers structured in a three-level taxonomy tree. Comparison with manual annotation and pairwise match test showed HiCAT outperforms others in major- and minor-type identification. For subsets, we qualitatively evaluated the marker expression profile demonstrating that HiCAT provide the clearest immune-cell landscape. HiCAT was also used for immune-cell profiling in ulcerative colitis and discovered distinct features of the disease in macrophage and T-cell subsets that could not be identified previously.

Transformer for one stop interpretable cell type annotation

Consistent annotation transfer from reference dataset to query dataset is fundamental to the development and reproducibility of single-cell research. Compared with traditional annotation methods, deep learning based methods are faster and more automated. A series of useful single cell analysis tools based on autoencoder architecture have been developed but these struggle to strike a balance between depth and interpretability. Here, we present TOSICA, a multi-head self-attention deep learning model based on Transformer that enables interpretable cell type annotation using biologically understandable entities, such as pathways or regulons. We show that TOSICA achieves fast and accurate one-stop annotation and batch-insensitive integration while providing biologically interpretable insights for understanding cellular behavior during development and disease progressions. We demonstrate TOSICA's advantages by applying it to scRNA-seq data of tumor-infiltrating immune cells, and CD14+ monocytes in COVID-19 to reveal rare cell types, heterogeneity and dynamic trajectories associated with disease progression and severity.

Multipotent Embryonic Lung Progenitors: Foundational Units of In Vitro and In Vivo Lung Organogenesis

Transient, tissue-specific, embryonic progenitors are important cell populations in vertebrate development. In the course of respiratory system development, multipotent mesenchymal and epithelial progenitors drive the diversification of fates that results to the plethora of cell types that compose the airways and alveolar space of the adult lungs. Use of mouse genetic models, including lineage tracing and loss-of-function studies, has elucidated signaling pathways that guide proliferation and differentiation of embryonic lung progenitors as well as transcription factors that underlie lung progenitor identity. Furthermore, pluripotent stem cell-derived and ex vivo expanded respiratory progenitors offer novel, tractable, high-fidelity systems that allow for mechanistic studies of cell fate decisions and developmental processes. As our understanding of embryonic progenitor biology deepens, we move closer to the goal of in vitro lung organogenesis and resulting applications in developmental biology and medicine.

scWECTA: A weighted ensemble classification framework for cell type assignment based on single cell transcriptome

Rapid advances in single-cell transcriptome analysis provide deeper insights into the study of tissue heterogeneity at the cellular level. Unsupervised clustering can identify potential cell populations in single-cell RNA-sequencing (scRNA-seq) data, but fail to further determine the identity of each cell. Existing automatic annotation methods using scRNA-seq data based on machine learning mainly use single feature set and single classifier. In view of this, we propose a Weighted Ensemble classification framework for Cell Type Annotation, named scWECTA, which improves the accuracy of cell type identification. scWECTA uses five informative gene sets and integrates five classifiers based on soft weighted ensemble framework. And the ensemble weights are inferred through the constrained non-negative least squares. Validated on multiple pairs of scRNA-seq datasets, scWECTA is able to accurately annotate scRNA-seq data across platforms and across tissues, especially for imbalanced data containing rare cell types. Moreover, scWECTA outperforms other comparable methods in balancing the prediction accuracy of common cell types and the unassigned rate of non-common cell types at the same time. The source code of scWECTA is freely available at https://github.com/ttren-sc/scWECTA.

scCapsNet-mask: an updated version of scCapsNet with extended applicability in functional analysis related to scRNA-seq data

BACKGROUND

With the rapid accumulation of scRNA-seq data, more and more automatic cell type identification methods have been developed, especially those based on deep learning. Although these methods have reached relatively high prediction accuracy, many issues still exist. One is the interpretability. The second is how to deal with the non-standard test samples that are not encountered in the training process.

RESULTS

Here we introduce scCapsNet-mask, an updated version of scCapsNet. The scCapsNet-mask provides a reasonable solution to the issues of interpretability and non-standard test samples. Firstly, the scCapsNet-mask utilizes a mask to ease the task of model interpretation in the original scCapsNet. The results show that scCapsNet-mask could constrain the coupling coefficients, and make a one-to-one correspondence between the primary capsules and type capsules. Secondly, the scCapsNet-mask can process non-standard samples more reasonably. In one example, the scCapsNet-mask was trained on the committed cells, and then tested on less differentiated cells as the non-standard samples. It could not only estimate the lineage bias of less differentiated cells, but also distinguish the development stages more accurately than traditional machine learning models. Therefore, the pseudo-temporal order of cells for each lineage could be established. Following these pseudo-temporal order, lineage specific genes exhibit a gradual increase expression pattern and stem cell associated genes exhibit a gradual decrease expression pattern. In another example, the scCapsNet-mask was trained on scRNA-seq data, and then used to assign cell type in spatial transcriptomics that may contain non-standard sample of doublets. The results show that the scCapsNet-mask not only restored the spatial map but also identified several non-standard samples of doublet.

CONCLUSIONS

The scCapsNet-mask offers a suitable solution to the challenge of interpretability and non-standard test samples. By adding a mask, it has the advantages of automatic processing and easy interpretation compared with the original scCapsNet. In addition, the scCapsNet-mask could more accurately reflect the composition of non-standard test samples than traditional machine learning methods. Therefore, it can extend its applicability in functional analysis, such as fate bias prediction in less differentiated cells and cell type assignment in spatial transcriptomics.

ImmCluster: an ensemble resource for immunology cell type clustering and annotations in normal and cancerous tissues

Single-cell transcriptome has enabled the transcriptional profiling of thousands of immune cells in complex tissues and cancers. However, subtle transcriptomic differences in immune cell subpopulations and the high dimensionality of transcriptomic data make the clustering and annotation of immune cells challenging. Herein, we introduce ImmCluster (http://bio-bigdata.hrbmu.edu.cn/ImmCluster) for immunology cell type clustering and annotation. We manually curated 346 well-known marker genes from 1163 studies. ImmCluster integrates over 420 000 immune cells from nine healthy tissues and over 648 000 cells from different tumour samples of 17 cancer types to generate stable marker-gene sets and develop context-specific immunology references. In addition, ImmCluster provides cell clustering using seven reference-based and four marker gene-based computational methods, and the ensemble method was developed to provide consistent cell clustering than individual methods. Five major analytic modules were provided for interactively exploring the annotations of immune cells, including clustering and annotating immune cell clusters, gene expression of markers, functional assignment in cancer hallmarks, cell states and immune pathways, cell-cell communications and the corresponding ligand-receptor interactions, as well as online tools. ImmCluster generates diverse plots and tables, enabling users to identify significant associations in immune cell clusters simultaneously. ImmCluster is a valuable resource for analysing cellular heterogeneity in cancer microenvironments.