A comparison of automatic cell identification methods for single-cell RNA sequencing data

devCellPy is a machine learning-enabled pipeline for automated annotation of complex multilayered single-cell transcriptomic data

A major informatic challenge in single cell RNA-sequencing analysis is the precise annotation of datasets where cells exhibit complex multilayered identities or transitory states. Here, we present devCellPy a highly accurate and precise machine learning-enabled tool that enables automated prediction of cell types across complex annotation hierarchies. To demonstrate the power of devCellPy, we construct a murine cardiac developmental atlas from published datasets encompassing 104,199 cells from E6.5-E16.5 and train devCellPy to generate a cardiac prediction algorithm. Using this algorithm, we observe a high prediction accuracy (>90%) across multiple layers of annotation and across de novo murine developmental data. Furthermore, we conduct a cross-species prediction of cardiomyocyte subtypes from in vitro-derived human induced pluripotent stem cells and unexpectedly uncover a predominance of left ventricular (LV) identity that we confirmed by an LV-specific TBX5 lineage tracing system. Together, our results show devCellPy to be a useful tool for automated cell prediction across complex cellular hierarchies, species, and experimental systems.

INSISTC: Incorporating network structure information for single-cell type classification

Uncovering gene regulatory mechanisms in individual cells can provide insight into cell heterogeneity and function. Recent accumulated Single-Cell RNA-Seq data have made it possible to analyze gene regulation at single-cell resolution. Understanding cell-type-specific gene regulation can assist in more accurate cell type and state identification. Computational approaches utilizing such relationships are under development. Methods pioneering in integrating gene regulatory mechanism discovery with cell-type classification encounter challenges such as determine gene regulatory relationships and incorporate gene regulatory network structure. To fill this gap, we developed INSISTC, a computational method to incorporate gene regulatory network structure information for single-cell type classification. INSISTC is capable of identifying cell-type-specific gene regulatory mechanisms while performing single-cell type classification. INSISTC demonstrated its accuracy in cell type classification and its potential for providing insight into molecular mechanisms specific to individual cells. In comparison with the alternative methods, INSISTC demonstrated its complementary performance for gene regulation interpretation.

PlaqView 2.0: A comprehensive web portal for cardiovascular single-cell genomics

Single-cell RNA-seq (scRNA-seq) is a powerful genomics technology to interrogate the cellular composition and behaviors of complex systems. While the number of scRNA-seq datasets and available computational analysis tools have grown exponentially, there are limited systematic data sharing strategies to allow rapid exploration and re-analysis of single-cell datasets, particularly in the cardiovascular field. We previously introduced PlaqView, an open-source web portal for the exploration and analysis of published atherosclerosis single-cell datasets. Now, we introduce PlaqView 2.0 (www.plaqview.com), which provides expanded features and functionalities as well as additional cardiovascular single-cell datasets. We showcase improved PlaqView functionality, backend data processing, user-interface, and capacity. PlaqView brings new or improved tools to explore scRNA-seq data, including gene query, metadata browser, cell identity prediction, ad hoc RNA-trajectory analysis, and drug-gene interaction prediction. PlaqView serves as one of the largest central repositories for cardiovascular single-cell datasets, which now includes data from human aortic aneurysm, gene-specific mouse knockouts, and healthy references. PlaqView 2.0 brings advanced tools and high-performance computing directly to users without the need for any programming knowledge. Lastly, we outline steps to generalize and repurpose PlaqView's framework for single-cell datasets from other fields.

scWizard: a web-based automated tool for classifying and annotating single cells and downstream analysis of single-cell RNA-seq data in cancers

•

scWizard provides comprehensive analysis pipeline for integration strategies of cancer scRNA-seq data.

•

scWizard enables classification of 47 cell subtypes within the TME based on hierarchical model by deep neural network.

•

scWizard gives a higher accuracy for annotation cell subtypes within the TME compared with five methods.

•

scWizard packages is a point-and-click tool helping for researchers without proficient programming skills.

The emerging number of single-cell RNA-seq (scRNA-Seq) datasets allows the characterization of cell types across various cancer types. However, there is still lack of effective tools to integrate the various analysis of single-cells, especially for making fine annotation on subtype cells within the tumor microenvironment (TME). We developed scWizard, a point-and-click tool packaging automated process including our developed cell annotation method based on deep neural network learning and 11 downstream analyses methods. scWizard used 113,976 cells across 13 cancer types as a built-in reference dataset for training the hierarchical model enabling to automatedly classify and annotate 7 major cell types and 47 cell subtypes in the TME. scWizard provides a built-in pre-training set for user’s flexible choice, and gives a higher accuracy for annotation subtypes of tumor-derived T-lymphocytes/natural killer cells (T/NK) and myeloid cells from different cancer types compared with the existing five methods. scWizard has good robustness in three independent cancer datasets, with an accuracy of 0.98 in annotating major cell types, 0.85 in annotating myeloid cell subtypes and 0.79 in annotating T/NK cell subtypes, indicting the wide applicability of scWizard in different cell types of cancers. Finally, the automatic analysis and visualization function of scWizard are presented by using the intrahepatic cholangiocarcinoma (ICC) scRNA-Seq dataset as a case. scWizard focuses on decoding TME and covers various analysis flows for cancer scRNA-Seq study, and provides an easy-to-use tool and a user-friendly interface for researchers widely, to further accelerate the biological discovery of cancer research.

Palo: spatially aware color palette optimization for single-cell and spatial data

SUMMARY

In the exploratory data analysis of single-cell or spatial genomic data, single-cells or spatial spots are often visualized using a two-dimensional plot where cell clusters or spot clusters are marked with different colors. With tens of clusters, current visualization methods often assign visually similar colors to spatially neighboring clusters, making it hard to identify the distinction between clusters. To address this issue, we developed Palo that optimizes the color palette assignment for single-cell and spatial data in a spatially aware manner. Palo identifies pairs of clusters that are spatially neighboring to each other and assigns visually distinct colors to those neighboring pairs. We demonstrate that Palo leads to improved visualization in real single-cell and spatial genomic datasets.

AVAILABILITY AND IMPLEMENTATION

Palo R package is freely available at Github (https://github.com/Winnie09/Palo) and Zenodo (https://doi.org/10.5281/zenodo.6562505).

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

SAREV: A review on statistical analytics of single-cell RNA sequencing data

Due to the development of next-generation RNA sequencing (NGS) technologies, there has been tremendous progress in research involving determining the role of genomics, transcriptomics and epigenomics in complex biological systems. However, scientists have realized that information obtained using earlier technology, frequently called 'bulk RNA-seq' data, provides information averaged across all the cells present in a tissue. Relatively newly developed single cell (scRNA-seq) technology allows us to provide transcriptomic information at a single-cell resolution. Nevertheless, these high-resolution data have their own complex natures and demand novel statistical data analysis methods to provide effective and highly accurate results on complex biological systems. In this review, we cover many such recently developed statistical methods for researchers wanting to pursue scRNA-seq statistical and computational research as well as scientific research about these existing methods and free software tools available for their generated data. This review is certainly not exhaustive due to page limitations. We have tried to cover the popular methods starting from quality control to the downstream analysis of finding differentially expressed genes and concluding with a brief description of network analysis.

Forest Fire Clustering for single-cell sequencing combines iterative label propagation with parallelized Monte Carlo simulations

In the era of single-cell sequencing, there is a growing need to extract insights from data with clustering methods. Here, we introduce Forest Fire Clustering, an efficient and interpretable method for cell-type discovery from single-cell data. Forest Fire Clustering makes minimal prior assumptions and, different from current approaches, calculates a non-parametric posterior probability that each cell is assigned a cell-type label. These posterior distributions allow for the evaluation of a label confidence for each cell and enable the computation of "label entropies", highlighting transitions along developmental trajectories. Furthermore, we show that Forest Fire Clustering can make robust, inductive inferences in an online-learning context and can readily scale to millions of cells. Finally, we demonstrate that our method outperforms state-of-the-art clustering approaches on diverse benchmarks of simulated and experimental data. Overall, Forest Fire Clustering is a useful tool for rare cell type discovery in large-scale single-cell analysis.

Disentangling single-cell omics representation with a power spectral density-based feature extraction

Emerging single-cell technologies provide high-resolution measurements of distinct cellular modalities opening new avenues for generating detailed cellular atlases of many and diverse tissues. The high dimensionality, sparsity, and inaccuracy of single cell sequencing measurements, however, can obscure discriminatory information, mask cellular subtype variations and complicate downstream analyses which can limit our understanding of cell function and tissue heterogeneity. Here, we present a novel pre-processing method (scPSD) inspired by power spectral density analysis that enhances the accuracy for cell subtype separation from large-scale single-cell omics data. We comprehensively benchmarked our method on a wide range of single-cell RNA-sequencing datasets and showed that scPSD pre-processing, while being fast and scalable, significantly reduces data complexity, enhances cell-type separation, and enables rare cell identification. Additionally, we applied scPSD to transcriptomics and chromatin accessibility cell atlases and demonstrated its capacity to discriminate over 100 cell types across the whole organism and across different modalities of single-cell omics data.

Cell clustering for spatial transcriptomics data with graph neural networks

Spatial transcriptomics data can provide high-throughput gene expression profiling and the spatial structure of tissues simultaneously. Most studies have relied on only the gene expression information but cannot utilize the spatial information efficiently. Taking advantage of spatial transcriptomics and graph neural networks, we introduce cell clustering for spatial transcriptomics data with graph neural networks, an unsupervised cell clustering method based on graph convolutional networks to improve ab initio cell clustering and discovery of cell subtypes based on curated cell category annotation. On the basis of its application to five in vitro and in vivo spatial datasets, we show that cell clustering for spatial transcriptomics outperforms other spatial clustering approaches on spatial transcriptomics datasets and can clearly identify all four cell cycle phases from multiplexed error-robust fluorescence in situ hybridization data of cultured cells. From enhanced sequential fluorescence in situ hybridization data of brain, cell clustering for spatial transcriptomics finds functional cell subtypes with different micro-environments, which are all validated experimentally, inspiring biological hypotheses about the underlying interactions among the cell state, cell type and micro-environment.

Identifying tumor cells at the single-cell level using machine learning

Tumors are complex tissues of cancerous cells surrounded by a heterogeneous cellular microenvironment with which they interact. Single-cell sequencing enables molecular characterization of single cells within the tumor. However, cell annotation-the assignment of cell type or cell state to each sequenced cell-is a challenge, especially identifying tumor cells within single-cell or spatial sequencing experiments. Here, we propose ikarus, a machine learning pipeline aimed at distinguishing tumor cells from normal cells at the single-cell level. We test ikarus on multiple single-cell datasets, showing that it achieves high sensitivity and specificity in multiple experimental contexts.

Overcoming biases in causal inference of molecular interactions

MOTIVATION

Computer inference of biological mechanisms is increasingly approachable due to dynamically rich data sources such as single-cell genomics. Inferred molecular interactions can prioritize hypotheses for wet-lab experiments to expedite biological discovery. However, complex data often come with unwanted biological or technical variations, exposing biases over marginal distribution and sample size in current methods to favor spurious causal relationships.

RESULTS

Considering function direction and strength as evidence for causality, we present an adapted functional chi-squared test (AdpFunChisq) that rewards functional patterns over non-functional or independent patterns. On synthetic and three biology datasets, we demonstrate the advantages of AdpFunChisq over 10 methods on overcoming biases that give rise to wide fluctuations in the performance of alternative approaches. On single-cell multiomics data of multiple phenotype acute leukemia, we found that the T-cell surface glycoprotein CD3 delta chain may causally mediate specific genes in the viral carcinogenesis pathway. Using the causality-by-functionality principle, AdpFunChisq offers a viable option for robust causal inference in dynamical systems.

AVAILABILITY AND IMPLEMENTATION

The AdpFunChisq test is implemented in the R package 'FunChisq' (2.5.2 or above) at https://cran.r-project.org/package=FunChisq. All other source code along with pre-processed data is available at Code Ocean https://doi.org/10.24433/CO.2907738.v1.

SUPPLEMENTARY INFORMATION

Supplementary materials are available at Bioinformatics online.

Pollock: fishing for cell states

Motivation

The use of single-cell methods is expanding at an ever-increasing rate. While there are established algorithms that address cell classification, they are limited in terms of cross platform compatibility, reliance on the availability of a reference dataset and classification interpretability. Here, we introduce Pollock, a suite of algorithms for cell type identification that is compatible with popular single-cell methods and analysis platforms, provides a set of pretrained human cancer reference models, and reports interpretability scores that identify the genes that drive cell type classifications.

Results

Pollock performs comparably to existing classification methods, while offering easily deployable pretrained classification models across a wide variety of tissue and data types. Additionally, it demonstrates utility in immune pan-cancer analysis.

Availability and implementation

Source code and documentation are available at https://github.com/ding-lab/pollock. Pretrained models and datasets are available for download at https://zenodo.org/record/5895221.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Cross-tissue immune cell analysis reveals tissue-specific features in humans

Despite their crucial role in health and disease, our knowledge of immune cells within human tissues remains limited. We surveyed the immune compartment of 16 tissues from 12 adult donors by single-cell RNA sequencing and VDJ sequencing generating a dataset of ~360,000 cells. To systematically resolve immune cell heterogeneity across tissues, we developed CellTypist, a machine learning tool for rapid and precise cell type annotation. Using this approach, combined with detailed curation, we determined the tissue distribution of finely phenotyped immune cell types, revealing hitherto unappreciated tissue-specific features and clonal architecture of T and B cells. Our multitissue approach lays the foundation for identifying highly resolved immune cell types by leveraging a common reference dataset, tissue-integrated expression analysis, and antigen receptor sequencing.

scMAGIC: accurately annotating single cells using two rounds of reference-based classification

Here, we introduce scMAGIC (Single Cell annotation using MArker Genes Identification and two rounds of reference-based Classification [RBC]), a novel method that uses well-annotated single-cell RNA sequencing (scRNA-seq) data as the reference to assist in the classification of query scRNA-seq data. A key innovation in scMAGIC is the introduction of a second-round RBC in which those query cells whose cell identities are confidently validated in the first round are used as a new reference to again classify query cells, therefore eliminating the batch effects between the reference and the query data. scMAGIC significantly outperforms 13 competing RBC methods with their optimal parameter settings across 86 benchmark tests, especially when the cell types in the query dataset are not completely covered by the reference dataset and when there exist significant batch effects between the reference and the query datasets. Moreover, when no reference dataset is available, scMAGIC can annotate query cells with reasonably high accuracy by using an atlas dataset as the reference.

A parameter-free deep embedded clustering method for single-cell RNA-seq data

Clustering analysis is widely used in single-cell ribonucleic acid (RNA)-sequencing (scRNA-seq) data to discover cell heterogeneity and cell states. While many clustering methods have been developed for scRNA-seq analysis, most of these methods require to provide the number of clusters. However, it is not easy to know the exact number of cell types in advance, and experienced determination is not always reliable. Here, we have developed ADClust, an automatic deep embedding clustering method for scRNA-seq data, which can accurately cluster cells without requiring a predefined number of clusters. Specifically, ADClust first obtains low-dimensional representation through pre-trained autoencoder and uses the representations to cluster cells into initial micro-clusters. The clusters are then compared in between by a statistical test, and similar micro-clusters are merged into larger clusters. According to the clustering, cell representations are updated so that each cell will be pulled toward centers of its assigned cluster and similar clusters, while cells are separated to keep distances between clusters. This is accomplished through jointly optimizing the carefully designed clustering and autoencoder loss functions. This merging process continues until convergence. ADClust was tested on 11 real scRNA-seq datasets and was shown to outperform existing methods in terms of both clustering performance and the accuracy on the number of the determined clusters. More importantly, our model provides high speed and scalability for large datasets.

Modeling climate change effects on spatial distribution of wild Aegilops L. (Poaceae) toward food security management and biodiversity conservation in Iran

The demand for food resources is increasing quickly because human populations are growing; therefore, food security may become one of the largest human challenges of this century. Crop wild relatives (CWRs) are the most valuable plant genetic resources (PGR) for the conservation of genetic diversity in crops. However, climate change is an added pressure on biodiversity, particularly on this valuable group of plants. It is predicted that more than 50% of this group may be lost by 2055 as a result of the effects of climate change. Iran ranks high in the world in its conservation priorities for CWRs. This study investigates the impacts of climate change on Aegilops L. as important CWRs. MaxEnt was applied to predict the spatial distribution of seven Aegilops species under different climatic scenarios (RCP 2.6 and RCP 8.5) of 2050 and 2080. According to the findings, all species exhibited reduction or expansion responses under all of the above-mentioned climatic scenarios. However, the range change was negative for some species (i.e., Aegilops columnaris, Aegilops cylindrica, Aegilops speltoides, Aegilops tauschii [in all scenarios of 2050 and 2080], and Aegilops kotschyi [RCP 2.6 2050 and 2080]), and positive for others (i.e., Aegilops crassa, Aegilops triuncialis [in all scenarios of 2050 and 2080], and Aegilops kotschyi [RCP 8.5 2050 and 2080]). The results of this study emphasize the need for conservation plans for the country's genetic resources, including regular monitoring and assessment of ecological and demographic changes. Integr Environ Assess Manag 2022;18:697-708. © 2021 SETAC.

Mapping and Validation of scRNA-Seq-Derived Cell-Cell Communication Networks in the Tumor Microenvironment

Recent advances in single-cell technologies, particularly single-cell RNA-sequencing (scRNA-seq), have permitted high throughput transcriptional profiling of a wide variety of biological systems. As scRNA-seq supports inference of cell-cell communication, this technology has and continues to anchor groundbreaking studies into the efficacy and mechanism of novel immunotherapies for cancer treatment. In this review, we will highlight methods developed to infer inter- and intracellular signaling from scRNA-seq and discuss how they have contributed to studies of immunotherapeutic intervention in the tumor microenvironment (TME). However, a central challenge remains in validating the hypothesized cell-cell interactions. Therefore, this review will also cover strategies for integration of these scRNA-seq-derived interaction networks with existing experimental and computational approaches. Integration of these networks with imaging, protein secretion measurements, and network analysis and mathematical modeling tools addresses challenges that remain with scRNA-seq to enhance studies of immunosuppressive and immunotherapy-altered signaling in the TME.

A Regularized Multi-Task Learning Approach for Cell Type Detection in Single-Cell RNA Sequencing Data

Cell type prediction is one of the most challenging goals in single-cell RNA sequencing (scRNA-seq) data. Existing methods use unsupervised learning to identify signature genes in each cluster, followed by a literature survey to look up those genes for assigning cell types. However, finding potential marker genes in each cluster is cumbersome, which impedes the systematic analysis of single-cell RNA sequencing data. To address this challenge, we proposed a framework based on regularized multi-task learning (RMTL) that enables us to simultaneously learn the subpopulation associated with a particular cell type. Learning the structure of subpopulations is treated as a separate task in the multi-task learner. Regularization is used to modulate the multi-task model (e.g., W₁, W₂, … W_t) jointly, according to the specific prior. For validating our model, we trained it with reference data constructed from a single-cell RNA sequencing experiment and applied it to a query dataset. We also predicted completely independent data (the query dataset) from the reference data which are used for training. We have checked the efficacy of the proposed method by comparing it with other state-of-the-art techniques well known for cell type detection. Results revealed that the proposed method performed accurately in detecting the cell type in scRNA-seq data and thus can be utilized as a useful tool in the scRNA-seq pipeline.

Spectral clustering of single cells using Siamese nerual network combined with improved affinity matrix

Limitations of bulk sequencing techniques on cell heterogeneity and diversity analysis have been pushed with the development of single-cell RNA-sequencing (scRNA-seq). To detect clusters of cells is a key step in the analysis of scRNA-seq. However, the high-dimensionality of scRNA-seq data and the imbalances in the number of different subcellular types are ubiquitous in real scRNA-seq data sets, which poses a huge challenge to the single-cell-type detection.We propose a meta-learning-based model, SiaClust, which is the combination of Siamese Convolutional Neural Network (CNN) and improved spectral clustering, to achieve scRNA-seq cell type detection. To be specific, with the help of the constrained Sigmoid kernel, the raw high-dimensionality data is mapped to a low-dimensional space, and the Siamese CNN learns the differences between the cell types in the low-dimensional feature space. The similarity matrix learned by Siamese CNN is used in combination with improved spectral clustering and t-distribution Stochastic Neighbor Embedding (t-SNE) for visualization. SiaClust highlights the differences between cell types by comparing the similarity of the samples, whereas blurring the differences within the cell types is better in processing high-dimensional and imbalanced data. SiaClust significantly improves clustering accuracy by using data generated by nine different species and tissues through different scNA-seq protocols for extensive evaluation, as well as analogies to state-of-the-art single-cell clustering models. More importantly, SiaClust accurately locates the exact site of dropout gene, and is more flexible with data size and cell type.

ACTIVA: realistic single-cell RNA-seq generation with automatic cell-type identification using introspective variational autoencoders

MOTIVATION

Single-cell RNA sequencing (scRNAseq) technologies allow for measurements of gene expression at a single-cell resolution. This provides researchers with a tremendous advantage for detecting heterogeneity, delineating cellular maps or identifying rare subpopulations. However, a critical complication remains: the low number of single-cell observations due to limitations by rarity of subpopulation, tissue degradation or cost. This absence of sufficient data may cause inaccuracy or irreproducibility of downstream analysis. In this work, we present Automated Cell-Type-informed Introspective Variational Autoencoder (ACTIVA): a novel framework for generating realistic synthetic data using a single-stream adversarial variational autoencoder conditioned with cell-type information. Within a single framework, ACTIVA can enlarge existing datasets and generate specific subpopulations on demand, as opposed to two separate models [such as single-cell GAN (scGAN) and conditional scGAN (cscGAN)]. Data generation and augmentation with ACTIVA can enhance scRNAseq pipelines and analysis, such as benchmarking new algorithms, studying the accuracy of classifiers and detecting marker genes. ACTIVA will facilitate analysis of smaller datasets, potentially reducing the number of patients and animals necessary in initial studies.

RESULTS

We train and evaluate models on multiple public scRNAseq datasets. In comparison to GAN-based models (scGAN and cscGAN), we demonstrate that ACTIVA generates cells that are more realistic and harder for classifiers to identify as synthetic which also have better pair-wise correlation between genes. Data augmentation with ACTIVA significantly improves classification of rare subtypes (more than 45% improvement compared with not augmenting and 4% better than cscGAN) all while reducing run-time by an order of magnitude in comparison to both models.

AVAILABILITY AND IMPLEMENTATION

The codes and datasets are hosted on Zenodo (https://doi.org/10.5281/zenodo.5879639). Tutorials are available at https://github.com/SindiLab/ACTIVA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

scGraph: a graph neural network-based approach to automatically identify cell types

MOTIVATION

Single cell technologies play a crucial role in revolutionizing biological research over the past decade, which strengthens our understanding in cell differentiation, development, and regulation from a single-cell level perspective. Single-cell RNA sequencing (scRNA-seq) is one of the most common single cell technologies, which enables probing transcriptional states in thousands of cells in one experiment. Identification of cell types from scRNA-seq measurements is a fundamental and crucial question to answer. Most previous studies directly take gene expression as input while ignoring the comprehensive gene-gene interactions.

RESULTS

We propose scGraph, an automatic cell identification algorithm leveraging gene interaction relationships to enhance the performance of the cell type identification. ScGraph is based on a graph neural network to aggregate the information of interacting genes. In a series of experiments, we demonstrate that scGraph is accurate and outperforms eight comparison methods in the task of cell type identification. Moreover, scGraph automatically learns the gene interaction relationships from biological data and the pathway enrichment analysis shows consistent findings with previous analysis, providing insights on the analysis of regulatory mechanism.

AVAILABILITY

scGraph is freely available at https://github.com/QijinYin/scGraph and https://figshare.com/articles/software/scGraph/17157743.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Capybara: A computational tool to measure cell identity and fate transitions

Measuring cell identity in development, disease, and reprogramming is challenging as cell types and states are in continual transition. Here, we present Capybara, a computational tool to classify discrete cell identity and intermediate "hybrid" cell states, supporting a metric to quantify cell fate transition dynamics. We validate hybrid cells using experimental lineage tracing data to demonstrate the multi-lineage potential of these intermediate cell states. We apply Capybara to diagnose shortcomings in several cell engineering protocols, identifying hybrid states in cardiac reprogramming and off-target identities in motor neuron programming, which we alleviate by adding exogenous signaling factors. Further, we establish a putative in vivo correlate for induced endoderm progenitors. Together, these results showcase the utility of Capybara to dissect cell identity and fate transitions, prioritizing interventions to enhance the efficiency and fidelity of stem cell engineering.

Evaluation of machine learning models on protein level inference from prioritized RNA features

The parallel measurement of transcriptome and proteome revealed unmatched profiles. Since proteomic analysis is more expensive and challenging than transcriptomic analysis, the question of how to use messenger RNA (mRNA) expression data to predict protein level is extremely important. Here, we comprehensively evaluated 13 machine learning models on inferring protein expression levels using RNA expression profile. A total of 20 proteogenomic datasets from three mainstream proteomic platforms with >2500 samples of 13 human tissues were collected for model evaluation. Our results highlighted that the appropriate feature selection methods combined with classical machine learning models could achieve excellent predictive performance. The voting ensemble model outperformed other candidate models across datasets. Adding the mRNA proxy model to the regression model further improved the prediction performance. The dataset and gene characteristics could affect the prediction performance. Finally, we applied the model to the brain transcriptome of cerebral cortex regions to infer the protein profile for better understanding the functional characteristics of the brain regions. This benchmarking work not only provides useful hints on the inherent correlation between transcriptome and proteome, but also has practical value of the transcriptome-based prediction of protein expression levels.

Statistical and machine learning methods for spatially resolved transcriptomics data analysis

The recent advancement in spatial transcriptomics technology has enabled multiplexed profiling of cellular transcriptomes and spatial locations. As the capacity and efficiency of the experimental technologies continue to improve, there is an emerging need for the development of analytical approaches. Furthermore, with the continuous evolution of sequencing protocols, the underlying assumptions of current analytical methods need to be re-evaluated and adjusted to harness the increasing data complexity. To motivate and aid future model development, we herein review the recent development of statistical and machine learning methods in spatial transcriptomics, summarize useful resources, and highlight the challenges and opportunities ahead.

A Systematic Evaluation of Supervised Machine Learning Algorithms for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data

The new technology of single-cell RNA sequencing (scRNA-seq) can yield valuable insights into gene expression and give critical information about the cellular compositions of complex tissues. In recent years, vast numbers of scRNA-seq datasets have been generated and made publicly available, and this has enabled researchers to train supervised machine learning models for predicting or classifying various cell-level phenotypes. This has led to the development of many new methods for analyzing scRNA-seq data. Despite the popularity of such applications, there has as yet been no systematic investigation of the performance of these supervised algorithms using predictors from various sizes of scRNA-seq datasets. In this study, 13 popular supervised machine learning algorithms for cell phenotype classification were evaluated using published real and simulated datasets with diverse cell sizes. This benchmark comprises two parts. In the first, real datasets were used to assess the computing speed and cell phenotype classification performance of popular supervised algorithms. The classification performances were evaluated using the area under the receiver operating characteristic curve, F1-score, Precision, Recall, and false-positive rate. In the second part, we evaluated gene-selection performance using published simulated datasets with a known list of real genes. The results showed that ElasticNet with interactions performed the best for small and medium-sized datasets. The NaiveBayes classifier was found to be another appropriate method for medium-sized datasets. With large datasets, the performance of the XGBoost algorithm was found to be excellent. Ensemble algorithms were not found to be significantly superior to individual machine learning methods. Including interactions in the ElasticNet algorithm caused a significant performance improvement for small datasets. The linear discriminant analysis algorithm was found to be the best choice when speed is critical; it is the fastest method, it can scale to handle large sample sizes, and its performance is not much worse than the top performers.

A comprehensive comparison of supervised and unsupervised methods for cell type identification in single-cell RNA-seq

The cell type identification is among the most important tasks in single-cell RNA-sequencing (scRNA-seq) analysis. Many in silico methods have been developed and can be roughly categorized as either supervised or unsupervised. In this study, we investigated the performances of 8 supervised and 10 unsupervised cell type identification methods using 14 public scRNA-seq datasets of different tissues, sequencing protocols and species. We investigated the impacts of a number of factors, including total amount of cells, number of cell types, sequencing depth, batch effects, reference bias, cell population imbalance, unknown/novel cell type, and computational efficiency and scalability. Instead of merely comparing individual methods, we focused on factors' impacts on the general category of supervised and unsupervised methods. We found that in most scenarios, the supervised methods outperformed the unsupervised methods, except for the identification of unknown cell types. This is particularly true when the supervised methods use a reference dataset with high informational sufficiency, low complexity and high similarity to the query dataset. However, such outperformance could be undermined by some undesired dataset properties investigated in this study, which lead to uninformative and biased reference datasets. In these scenarios, unsupervised methods could be comparable to supervised methods. Our study not only explained the cell typing methods' behaviors under different experimental settings but also provided a general guideline for the choice of method according to the scientific goal and dataset properties. Finally, our evaluation workflow is implemented as a modularized R pipeline that allows future evaluation of new methods. Availability: All the source codes are available at https://github.com/xsun28/scRNAIdent.

Fully-automated and ultra-fast cell-type identification using specific marker combinations from single-cell transcriptomic data

Identification of cell populations often relies on manual annotation of cell clusters using established marker genes. However, the selection of marker genes is a time-consuming process that may lead to sub-optimal annotations as the markers must be informative of both the individual cell clusters and various cell types present in the sample. Here, we developed a computational platform, ScType, which enables a fully-automated and ultra-fast cell-type identification based solely on a given scRNA-seq data, along with a comprehensive cell marker database as background information. Using six scRNA-seq datasets from various human and mouse tissues, we show how ScType provides unbiased and accurate cell type annotations by guaranteeing the specificity of positive and negative marker genes across cell clusters and cell types. We also demonstrate how ScType distinguishes between healthy and malignant cell populations, based on single-cell calling of single-nucleotide variants, making it a versatile tool for anticancer applications. The widely applicable method is deployed both as an interactive web-tool (https://sctype.app), and as an open-source R-package.

Cell types are typically identified in single cell transcriptomic data by manual annotation of cell clusters using established marker genes. Here the authors present a fully-automated computational platform that can quickly and accurately distinguish between cell types.

scGate: marker-based purification of cell types from heterogeneous single-cell RNA-seq datasets

Summary

A common bioinformatics task in single-cell data analysis is to purify a cell type or cell population of interest from heterogeneous datasets. Here, we present scGate, an algorithm that automatizes marker-based purification of specific cell populations, without requiring training data or reference gene expression profiles. scGate purifies a cell population of interest using a set of markers organized in a hierarchical structure, akin to gating strategies employed in flow cytometry. scGate outperforms state-of-the-art single-cell classifiers and it can be applied to multiple modalities of single-cell data (e.g. RNA-seq, ATAC-seq, CITE-seq). scGate is implemented as an R package and integrated with the Seurat framework, providing an intuitive tool to isolate cell populations of interest from heterogeneous single-cell datasets.

Availability and implementation

scGate is available as an R package at https://github.com/carmonalab/scGate (https://doi.org/10.5281/zenodo.6202614). Several reproducible workflows describing the main functions and usage of the package on different single-cell modalities, as well as the code to reproduce the benchmark, can be found at https://github.com/carmonalab/scGate.demo (https://doi.org/10.5281/zenodo.6202585) and https://github.com/carmonalab/scGate.benchmark. Test data are available at https://doi.org/10.6084/m9.figshare.16826071.

Supplementary information

Supplementary data are available at Bioinformatics online.

TraSig: inferring cell-cell interactions from pseudotime ordering of scRNA-Seq data

A major advantage of single cell RNA-sequencing (scRNA-Seq) data is the ability to reconstruct continuous ordering and trajectories for cells. Here we present TraSig, a computational method for improving the inference of cell-cell interactions in scRNA-Seq studies that utilizes the dynamic information to identify significant ligand-receptor pairs with similar trajectories, which in turn are used to score interacting cell clusters. We applied TraSig to several scRNA-Seq datasets and obtained unique predictions that improve upon those identified by prior methods. Functional experiments validate the ability of TraSig to identify novel signaling interactions that impact vascular development in liver organoids.Software https://github.com/doraadong/TraSig .

JIND: Joint Integration and Discrimination for Automated Single-Cell Annotation

MOTIVATION

An important step in the transcriptomic analysis of individual cells involves manually determining the cellular identities. To ease this labor-intensive annotation of cell-types, there has been a growing interest in automated cell annotation, which can be achieved by training classification algorithms on previously annotated datasets. Existing pipelines employ dataset integration methods in order to remove potential batch effects between source (annotated) and target (unannotated) datasets. However, the integration and classification steps are usually independent of each other and performed by different tools. We propose JIND, a neural-network-based framework for automated cell-type identification that performs integration in a space suitably chosen to facilitate cell classification. To account for batch effects, JIND performs a novel asymmetric alignment in which unseen cells are mapped onto the previously learned latent space, avoiding the need of retraining the classification model for new datasets. JIND also learns cell-type-specific confidence thresholds to identify cells that cannot be reliably classified.

RESULTS

We show on several batched datasets that the joint approach to integration and classification of JIND outperforms in accuracy existing pipelines, and a smaller fraction of cells is rejected as unlabeled as a result of the cell-specific confidence thresholds. Moreover, we investigate cells misclassified by JIND and provide evidence suggesting that they could be due to outliers in the annotated datasets or errors in the original approach used for annotation of the target batch.

AVAILABILITY

Implementation for JIND is available at https://github.com/mohit1997/JIND and at https://doi.org/10.5281/zenodo.6246322.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

scPretrain: multi-task self-supervised learning for cell-type classification

MOTIVATION

Rapidly generated scRNA-seq datasets enable us to understand cellular differences and the function of each individual cell at single-cell resolution. Cell-type classification, which aims at characterizing and labeling groups of cells according to their gene expression, is one of the most important steps for single-cell analysis. To facilitate the manual curation process, supervised learning methods have been used to automatically classify cells. Most of the existing supervised learning approaches only utilize annotated cells in the training step while ignoring the more abundant unannotated cells. In this article, we proposed scPretrain, a multi-task self-supervised learning approach that jointly considers annotated and unannotated cells for cell-type classification. scPretrain consists of a pre-training step and a fine-tuning step. In the pre-training step, scPretrain uses a multi-task learning framework to train a feature extraction encoder based on each dataset's pseudo-labels, where only unannotated cells are used. In the fine-tuning step, scPretrain fine-tunes this feature extraction encoder using the limited annotated cells in a new dataset.

RESULTS

We evaluated scPretrain on 60 diverse datasets from different technologies, species and organs, and obtained a significant improvement on both cell-type classification and cell clustering. Moreover, the representations obtained by scPretrain in the pre-training step also enhanced the performance of conventional classifiers, such as random forest, logistic regression and support-vector machines. scPretrain is able to effectively utilize the massive amount of unlabeled data and be applied to annotating increasingly generated scRNA-seq datasets.

AVAILABILITY AND IMPLEMENTATION

The data and code underlying this article are available in scPretrain: Multi-task self-supervised learning for cell type classification, at https://github.com/ruiyi-zhang/scPretrain and https://zenodo.org/record/5802306.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

MACA: marker-based automatic cell-type annotation for single-cell expression data

SUMMARY

Accurately identifying cell types is a critical step in single-cell sequencing analyses. Here, we present marker-based automatic cell-type annotation (MACA), a new tool for annotating single-cell transcriptomics datasets. We developed MACA by testing four cell-type scoring methods with two public cell-marker databases as reference in six single-cell studies. MACA compares favorably to four existing marker-based cell-type annotation methods in terms of accuracy and speed. We show that MACA can annotate a large single-nuclei RNA-seq study in minutes on human hearts with ∼290K cells. MACA scales easily to large datasets and can broadly help experts to annotate cell types in single-cell transcriptomics datasets, and we envision MACA provides a new opportunity for integration and standardization of cell-type annotation across multiple datasets.

AVAILABILITY AND IMPLEMENTATION

MACA is written in python and released under GNU General Public License v3.0. The source code is available at https://github.com/ImXman/MACA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Single-cell Transcriptomic Architecture Unraveling the Complexity of Tumor Heterogeneity in Distal Cholangiocarcinoma

BACKGROUND & AIMS

Distal cholangiocarcinoma (dCCA) are a group of epithelial cell malignancies that occurs at the distal common bile duct, and account for approximately 40% of all cholangiocarcinoma cases. dCCA remains a highly lethal disease as it typically features remarkable cellular heterogeneity. A comprehensive exploration of cellular diversity and the tumor microenvironment is essential to depict the mechanisms driving dCCA progression.

METHODS

Single-cell RNA sequencing was used here to dissect the heterogeneity landscape and tumor microenvironment composition of human dCCAs. Seven human dCCAs and adjacent normal bile duct samples were included in the current study for single-cell RNA sequencing and subsequent validation approaches. Additionally, the results of the analyses were compared with bulk transcriptomic datasets from extrahepatic cholangiocarcinoma and single-cell RNA data from intrahepatic cholangiocarcinoma.

RESULTS

We sequenced a total of 49,717 single cells derived from human dCCAs and adjacent tissues, identifying 11 distinct cell types. Malignant cells displayed remarkable inter- and intra-tumor heterogeneity with 5 distinct subsets were defined in tumor samples. The malignant cells displayed variable degree of aneuploidy, which can be classified into low- and high-copy number variation groups based on either amplification or deletion of chr17q12 - chr17q21.2. Additionally, we identified 4 distinct T lymphocytes subsets, of which cytotoxic CD8+ T cells predominated as effectors in tumor tissues, whereas tumor infiltrating FOXP3+ CD4+ regulatory T cells exhibited highly immunosuppressive characteristics.

CONCLUSION

Our single-cell transcriptomic dataset depicts the inter- and intra-tumor heterogeneity of human dCCAs at the expression level.

DevKidCC allows for robust classification and direct comparisons of kidney organoid datasets

BACKGROUND

While single-cell transcriptional profiling has greatly increased our capacity to interrogate biology, accurate cell classification within and between datasets is a key challenge. This is particularly so in pluripotent stem cell-derived organoids which represent a model of a developmental system. Here, clustering algorithms and selected marker genes can fail to accurately classify cellular identity while variation in analyses makes it difficult to meaningfully compare datasets. Kidney organoids provide a valuable resource to understand kidney development and disease. However, direct comparison of relative cellular composition between protocols has proved challenging. Hence, an unbiased approach for classifying cell identity is required.

METHODS

The R package, scPred, was trained on multiple single cell RNA-seq datasets of human fetal kidney. A hierarchical model classified cellular subtypes into nephron, stroma and ureteric epithelial elements. This model, provided in the R package DevKidCC ( github.com/KidneyRegeneration/DevKidCC ), was then used to predict relative cell identity within published kidney organoid datasets generated using distinct cell lines and differentiation protocols, interrogating the impact of such variations. The package contains custom functions for the display of differential gene expression within cellular subtypes.

RESULTS

DevKidCC was used to directly compare between distinct kidney organoid protocols, identifying differences in relative proportions of cell types at all hierarchical levels of the model and highlighting variations in stromal and unassigned cell types, nephron progenitor prevalence and relative maturation of individual epithelial segments. Of note, DevKidCC was able to distinguish distal nephron from ureteric epithelium, cell types with overlapping profiles that have previously confounded analyses. When applied to a variation in protocol via the addition of retinoic acid, DevKidCC identified a consequential depletion of nephron progenitors.

CONCLUSIONS

The application of DevKidCC to kidney organoids reproducibly classifies component cellular identity within distinct single-cell datasets. The application of the tool is summarised in an interactive Shiny application, as are examples of the utility of in-built functions for data presentation. This tool will enable the consistent and rapid comparison of kidney organoid protocols, driving improvements in patterning to kidney endpoints and validating new approaches.

DevKidCC allows for robust classification and direct comparisons of kidney organoid datasets

Background

While single-cell transcriptional profiling has greatly increased our capacity to interrogate biology, accurate cell classification within and between datasets is a key challenge. This is particularly so in pluripotent stem cell-derived organoids which represent a model of a developmental system. Here, clustering algorithms and selected marker genes can fail to accurately classify cellular identity while variation in analyses makes it difficult to meaningfully compare datasets. Kidney organoids provide a valuable resource to understand kidney development and disease. However, direct comparison of relative cellular composition between protocols has proved challenging. Hence, an unbiased approach for classifying cell identity is required.

Methods

The R package, scPred, was trained on multiple single cell RNA-seq datasets of human fetal kidney. A hierarchical model classified cellular subtypes into nephron, stroma and ureteric epithelial elements. This model, provided in the R package DevKidCC (github.com/KidneyRegeneration/DevKidCC), was then used to predict relative cell identity within published kidney organoid datasets generated using distinct cell lines and differentiation protocols, interrogating the impact of such variations. The package contains custom functions for the display of differential gene expression within cellular subtypes.

Results

DevKidCC was used to directly compare between distinct kidney organoid protocols, identifying differences in relative proportions of cell types at all hierarchical levels of the model and highlighting variations in stromal and unassigned cell types, nephron progenitor prevalence and relative maturation of individual epithelial segments. Of note, DevKidCC was able to distinguish distal nephron from ureteric epithelium, cell types with overlapping profiles that have previously confounded analyses. When applied to a variation in protocol via the addition of retinoic acid, DevKidCC identified a consequential depletion of nephron progenitors.

Conclusions

The application of DevKidCC to kidney organoids reproducibly classifies component cellular identity within distinct single-cell datasets. The application of the tool is summarised in an interactive Shiny application, as are examples of the utility of in-built functions for data presentation. This tool will enable the consistent and rapid comparison of kidney organoid protocols, driving improvements in patterning to kidney endpoints and validating new approaches.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13073-022-01023-z.

Vec2image: an explainable artificial intelligence model for the feature representation and classification of high-dimensional biological data by vector-to-image conversion

Feature representation and discriminative learning are proven models and technologies in artificial intelligence fields; however, major challenges for machine learning on large biological datasets are learning an effective model with mechanistical explanation on the model determination and prediction. To satisfy such demands, we developed Vec2image, an explainable convolutional neural network framework for characterizing the feature engineering, feature selection and classifier training that is mainly based on the collaboration of principal component coordinate conversion, deep residual neural networks and embedded k-nearest neighbor representation on pseudo images of high-dimensional biological data, where the pseudo images represent feature measurements and feature associations simultaneously. Vec2image has achieved better performance compared with other popular methods and illustrated its efficiency on feature selection in cell marker identification from tissue-specific single-cell datasets. In particular, in a case study on type 2 diabetes (T2D) by multiple human islet scRNA-seq datasets, Vec2image first displayed robust performance on T2D classification model building across different datasets, then a specific Vec2image model was trained to accurately recognize the cell state and efficiently rank feature genes relevant to T2D which uncovered potential T2D cellular pathogenesis; and next the cell activity changes, cell composition imbalances and cell–cell communication dysfunctions were associated to our finding T2D feature genes from both population-shared and individual-specific perspectives. Collectively, Vec2image is a new and efficient explainable artificial intelligence methodology that can be widely applied in human-readable classification and prediction on the basis of pseudo image representation of biological deep sequencing data.

Hubness reduction improves clustering and trajectory inference in single-cell transcriptomic data

MOTIVATION

Single-cell RNA-seq (scRNAseq) datasets are characterized by large ambient dimensionality, and their analyses can be affected by various manifestations of the dimensionality curse. One of these manifestations is the hubness phenomenon, i.e. existence of data points with surprisingly large incoming connectivity degree in the datapoint neighbourhood graph. Conventional approach to dampen the unwanted effects of high dimension consists in applying drastic dimensionality reduction. It remains unexplored if this step can be avoided thus retaining more information than contained in the low-dimensional projections, by correcting directly hubness.

RESULTS

We investigated hubness in scRNAseq data. We show that hub cells do not represent any visible technical or biological bias. The effect of various hubness reduction methods is investigated with respect to the clustering, trajectory inference and visualization tasks in scRNAseq datasets. We show that hubness reduction generates neighbourhood graphs with properties more suitable for applying machine learning methods; and that it outperforms other state-of-the-art methods for improving neighbourhood graphs. As a consequence, clustering, trajectory inference and visualization perform better, especially for datasets characterized by large intrinsic dimensionality. Hubness is an important phenomenon characterizing data point neighbourhood graphs computed for various types of sequencing datasets. Reducing hubness can be beneficial for the analysis of scRNAseq data with large intrinsic dimensionality in which case it can be an alternative to drastic dimensionality reduction.

AVAILABILITY AND IMPLEMENTATION

The code used to analyze the datasets and produce the figures of this article is available from https://github.com/sysbio-curie/schubness.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Clustering spatial transcriptomics data

MOTIVATION

Recent advancements in fluorescence in situ hybridization (FISH) techniques enable them to concurrently obtain information on the location and gene expression of single cells. A key question in the initial analysis of such spatial transcriptomics data is the assignment of cell types. To date, most studies used methods that only rely on the expression levels of the genes in each cell for such assignments. To fully utilize the data and to improve the ability to identify novel sub-types, we developed a new method, FICT, which combines both expression and neighborhood information when assigning cell types.

RESULTS

FICT optimizes a probabilistic function that we formalize and for which we provide learning and inference algorithms. We used FICT to analyze both simulated and several real spatial transcriptomics data. As we show, FICT can accurately identify cell types and sub-types, improving on expression only methods and other methods proposed for clustering spatial transcriptomics data. Some of the spatial sub-types identified by FICT provide novel hypotheses about the new functions for excitatory and inhibitory neurons.

AVAILABILITY AND IMPLEMENTATION

FICT is available at: https://github.com/haotianteng/FICT.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Analysis and Visualization of Spatial Transcriptomic Data

Human and animal tissues consist of heterogeneous cell types that organize and interact in highly structured manners. Bulk and single-cell sequencing technologies remove cells from their original microenvironments, resulting in a loss of spatial information. Spatial transcriptomics is a recent technological innovation that measures transcriptomic information while preserving spatial information. Spatial transcriptomic data can be generated in several ways. RNA molecules are measured by in situ sequencing, in situ hybridization, or spatial barcoding to recover original spatial coordinates. The inclusion of spatial information expands the range of possibilities for analysis and visualization, and spurred the development of numerous novel methods. In this review, we summarize the core concepts of spatial genomics technology and provide a comprehensive review of current analysis and visualization methods for spatial transcriptomics.

scMRMA: single cell multiresolution marker-based annotation

Single-cell RNA sequencing has become a powerful tool for identifying and characterizing cellular heterogeneity. One essential step to understanding cellular heterogeneity is determining cell identities. The widely used strategy predicts identities by projecting cells or cell clusters unidirectionally against a reference to find the best match. Here, we develop a bidirectional method, scMRMA, where a hierarchical reference guides iterative clustering and deep annotation with enhanced resolutions. Taking full advantage of the reference, scMRMA greatly improves the annotation accuracy. scMRMA achieved better performance than existing methods in four benchmark datasets and successfully revealed the expansion of CD8 T cell populations in squamous cell carcinoma after anti-PD-1 treatment.

Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a significant increase in data collected from single-cell profilings, resulting in computational challenges to process these massive and complicated datasets. To address these challenges, deep learning (DL) is positioned as a competitive alternative for single-cell analyses besides the traditional machine learning approaches. Here, we survey a total of 25 DL algorithms and their applicability for a specific step in the single cell RNA-seq processing pipeline. Specifically, we establish a unified mathematical representation of variational autoencoder, autoencoder, generative adversarial network and supervised DL models, compare the training strategies and loss functions for these models, and relate the loss functions of these models to specific objectives of the data processing step. Such a presentation will allow readers to choose suitable algorithms for their particular objective at each step in the pipeline. We envision that this survey will serve as an important information portal for learning the application of DL for scRNA-seq analysis and inspire innovative uses of DL to address a broader range of new challenges in emerging multi-omics and spatial single-cell sequencing.

Computational Methods for Single-Cell Imaging and Omics Data Integration

Integrating single cell omics and single cell imaging allows for a more effective characterisation of the underlying mechanisms that drive a phenotype at the tissue level, creating a comprehensive profile at the cellular level. Although the use of imaging data is well established in biomedical research, its primary application has been to observe phenotypes at the tissue or organ level, often using medical imaging techniques such as MRI, CT, and PET. These imaging technologies complement omics-based data in biomedical research because they are helpful for identifying associations between genotype and phenotype, along with functional changes occurring at the tissue level. Single cell imaging can act as an intermediary between these levels. Meanwhile new technologies continue to arrive that can be used to interrogate the genome of single cells and its related omics datasets. As these two areas, single cell imaging and single cell omics, each advance independently with the development of novel techniques, the opportunity to integrate these data types becomes more and more attractive. This review outlines some of the technologies and methods currently available for generating, processing, and analysing single-cell omics- and imaging data, and how they could be integrated to further our understanding of complex biological phenomena like ageing. We include an emphasis on machine learning algorithms because of their ability to identify complex patterns in large multidimensional data.

scAnnotatR: framework to accurately classify cell types in single-cell RNA-sequencing data

Background

Automatic cell type identification is essential to alleviate a key bottleneck in scRNA-seq data analysis. While most existing classification tools show good sensitivity and specificity, they often fail to adequately not-classify cells that are missing in the used reference. Additionally, many tools do not scale to the continuously increasing size of current scRNA-seq datasets. Therefore, additional tools are needed to solve these challenges.

Results

scAnnotatR is a novel R package that provides a complete framework to classify cells in scRNA-seq datasets using pre-trained classifiers. It supports both Seurat and Bioconductor’s SingleCellExperiment and is thereby compatible with the vast majority of R-based analysis workflows. scAnnotatR uses hierarchically organised SVMs to distinguish a specific cell type versus all others. It shows comparable or even superior accuracy, sensitivity and specificity compared to existing tools while being able to not-classify unknown cell types. Moreover, scAnnotatR is the only of the best performing tools able to process datasets containing more than 600,000 cells.

Conclusions

scAnnotatR is freely available on GitHub (https://github.com/grisslab/scAnnotatR) and through Bioconductor (from version 3.14). It is consistently among the best performing tools in terms of classification accuracy while scaling to the largest datasets.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04574-5.