Exploring the optimization of autoencoder design for imputing single-cell RNA sequencing data

Autoencoders are the backbones of many imputation methods that aim to relieve the sparsity issue in single-cell RNA sequencing (scRNA-seq) data. The imputation performance of an autoencoder relies on both the neural network architecture and the hyperparameter choice. So far, literature in the single-cell field lacks a formal discussion on how to design the neural network and choose the hyperparameters. Here, we conducted an empirical study to answer this question. Our study used many real and simulated scRNA-seq datasets to examine the impacts of the neural network architecture, the activation function, and the regularization strategy on imputation accuracy and downstream analyses. Our results show that (i) deeper and narrower autoencoders generally lead to better imputation performance; (ii) the sigmoid and tanh activation functions consistently outperform other commonly used functions including ReLU; (iii) regularization improves the accuracy of imputation and downstream cell clustering and DE gene analyses. Notably, our results differ from common practices in the computer vision field regarding the activation function and the regularization strategy. Overall, our study offers practical guidance on how to optimize the autoencoder design for scRNA-seq data imputation.

Inferring cancer common and specific gene networks via multi-layer joint graphical model

Cancer is a complex disease caused primarily by genetic variants. Reconstructing gene networks within tumors is essential for understanding the functional regulatory mechanisms of carcinogenesis. Advances in high-throughput sequencing technologies have provided tremendous opportunities for inferring gene networks via computational approaches. However, due to the heterogeneity of the same cancer type and the similarities between different cancer types, it remains a challenge to systematically investigate the commonalities and specificities between gene networks of different cancer types, which is a crucial step towards precision cancer diagnosis and treatment. In this study, we propose a new sparse regularized multi-layer decomposition graphical model to jointly estimate the gene networks of multiple cancer types. Our model can handle various types of gene expression data and decomposes each cancer-type-specific network into three components, i.e., globally shared, partially shared and cancer-type-unique components. By identifying the globally and partially shared gene network components, our model can explore the heterogeneous similarities between different cancer types, and our identified cancer-type-unique components can help to reveal the regulatory mechanisms unique to each cancer type. Extensive experiments on synthetic data illustrate the effectiveness of our model in joint estimation of multiple gene networks. We also apply our model to two real data sets to infer the gene networks of multiple cancer subtypes or cell lines. By analyzing our estimated globally shared, partially shared, and cancer-type-unique components, we identified a number of important genes associated with common and specific regulatory mechanisms across different cancer types.

Radiotherapy orchestrates natural killer cell dependent antitumor immune responses through CXCL8

Radiotherapy is a mainstay cancer therapy whose antitumor effects partially depend on T cell responses. However, the role of Natural Killer (NK) cells in radiotherapy remains unclear. Here, using a reverse translational approach, we show a central role of NK cells in the radiation-induced immune response involving a CXCL8/IL-8-dependent mechanism. In a randomized controlled pancreatic cancer trial, CXCL8 increased under radiotherapy, and NK cell positively correlated with prolonged overall survival. Accordingly, NK cells preferentially infiltrated irradiated pancreatic tumors and exhibited CD56^dim-like cytotoxic transcriptomic states. In experimental models, NF-κB and mTOR orchestrated radiation-induced CXCL8 secretion from tumor cells with senescence features causing directional migration of CD56^dim NK cells, thus linking senescence-associated CXCL8 release to innate immune surveillance of human tumors. Moreover, combined high-dose radiotherapy and adoptive NK cell transfer improved tumor control over monotherapies in xenografted mice, suggesting NK cells combined with radiotherapy as a rational cancer treatment strategy.

A novel method for single-cell data imputation using subspace regression

Recent advances in biochemistry and single-cell RNA sequencing (scRNA-seq) have allowed us to monitor the biological systems at the single-cell resolution. However, the low capture of mRNA material within individual cells often leads to inaccurate quantification of genetic material. Consequently, a significant amount of expression values are reported as missing, which are often referred to as dropouts. To overcome this challenge, we develop a novel imputation method, named single-cell Imputation via Subspace Regression (scISR), that can reliably recover the dropout values of scRNA-seq data. The scISR method first uses a hypothesis-testing technique to identify zero-valued entries that are most likely affected by dropout events and then estimates the dropout values using a subspace regression model. Our comprehensive evaluation using 25 publicly available scRNA-seq datasets and various simulation scenarios against five state-of-the-art methods demonstrates that scISR is better than other imputation methods in recovering scRNA-seq expression profiles via imputation. scISR consistently improves the quality of cluster analysis regardless of dropout rates, normalization techniques, and quantification schemes. The source code of scISR can be found on GitHub at https://github.com/duct317/scISR.

A review of computational strategies for denoising and imputation of single-cell transcriptomic data

MOTIVATION

The advancements of single-cell sequencing methods have paved the way for the characterization of cellular states at unprecedented resolution, revolutionizing the investigation on complex biological systems. Yet, single-cell sequencing experiments are hindered by several technical issues, which cause output data to be noisy, impacting the reliability of downstream analyses. Therefore, a growing number of data science methods has been proposed to recover lost or corrupted information from single-cell sequencing data. To date, however, no quantitative benchmarks have been proposed to evaluate such methods.

RESULTS

We present a comprehensive analysis of the state-of-the-art computational approaches for denoising and imputation of single-cell transcriptomic data, comparing their performance in different experimental scenarios. In detail, we compared 19 denoising and imputation methods, on both simulated and real-world datasets, with respect to several performance metrics related to imputation of dropout events, recovery of true expression profiles, characterization of cell similarity, identification of differentially expressed genes and computation time. The effectiveness and scalability of all methods were assessed with regard to distinct sequencing protocols, sample size and different levels of biological variability and technical noise. As a result, we identify a subset of versatile approaches exhibiting solid performances on most tests and show that certain algorithmic families prove effective on specific tasks but inefficient on others. Finally, most methods appear to benefit from the introduction of appropriate assumptions on noise distribution of biological processes.

scLink: Inferring Sparse Gene Co-expression Networks from Single-cell Expression Data

A system-level understanding of the regulation and coordination mechanisms of gene expression is essential for studying the complexity of biological processes in health and disease. With the rapid development of single-cell RNA sequencing technologies, it is now possible to investigate gene interactions in a cell type-specific manner. Here we propose the scLink method, which uses statistical network modeling to understand the co-expression relationships among genes and construct sparse gene co-expression networks from single-cell gene expression data. We use both simulation and real data studies to demonstrate the advantages of scLink and its ability to improve single-cell gene network analysis. The scLink R package is available at https://github.com/Vivianstats/scLink.

Machine Intelligence in Single-Cell Data Analysis: Advances and New Challenges

The rapid development of single-cell technologies allows for dissecting cellular heterogeneity at different omics layers with an unprecedented resolution. In-dep analysis of cellular heterogeneity will boost our understanding of complex biological systems or processes, including cancer, immune system and chronic diseases, thereby providing valuable insights for clinical and translational research. In this review, we will focus on the application of machine learning methods in single-cell multi-omics data analysis. We will start with the pre-processing of single-cell RNA sequencing (scRNA-seq) data, including data imputation, cross-platform batch effect removal, and cell cycle and cell-type identification. Next, we will introduce advanced data analysis tools and methods used for copy number variance estimate, single-cell pseudo-time trajectory analysis, phylogenetic tree inference, cell-cell interaction, regulatory network inference, and integrated analysis of scRNA-seq and spatial transcriptome data. Finally, we will present the latest analyzing challenges, such as multi-omics integration and integrated analysis of scRNA-seq data.

Joint probabilistic modeling of single-cell multi-omic data with totalVI

The paired measurement of RNA and surface proteins in single cells with cellular indexing of transcriptomes and epitopes by sequencing (CITE-seq) is a promising approach to connect transcriptional variation with cell phenotypes and functions. However, combining these paired views into a unified representation of cell state is made challenging by the unique technical characteristics of each measurement. Here we present Total Variational Inference (totalVI; https://scvi-tools.org ), a framework for end-to-end joint analysis of CITE-seq data that probabilistically represents the data as a composite of biological and technical factors, including protein background and batch effects. To evaluate totalVI's performance, we profiled immune cells from murine spleen and lymph nodes with CITE-seq, measuring over 100 surface proteins. We demonstrate that totalVI provides a cohesive solution for common analysis tasks such as dimensionality reduction, the integration of datasets with different measured proteins, estimation of correlations between molecules and differential expression testing.

Statistical and Bioinformatics Analysis of Data from Bulk and Single-Cell RNA Sequencing Experiments

High-throughput sequencing (HTS) has revolutionized researchers' ability to study the human transcriptome, particularly as it relates to cancer. Recently, HTS technology has advanced to the point where now one is able to sequence individual cells (i.e., "single-cell sequencing"). Prior to single-cell sequencing technology, HTS would be completed on RNA extracted from a tissue sample consisting of multiple cell types (i.e., "bulk sequencing"). In this chapter, we review the various bioinformatics and statistical methods used in the processing, quality control, and analysis of bulk and single-cell RNA sequencing methods. Additionally, we discuss how these methods are also being used to study tumor heterogeneity.

TooManyCells identifies and visualizes relationships of single-cell clades

Identifying and visualizing transcriptionally similar cells is instrumental for accurate exploration of the cellular diversity revealed by single-cell transcriptomics. However, widely used clustering and visualization algorithms produce a fixed number of cell clusters. A fixed clustering 'resolution' hampers our ability to identify and visualize echelons of cell states. We developed TooManyCells, a suite of graph-based algorithms for efficient and unbiased identification and visualization of cell clades. TooManyCells introduces a visualization model built on a concept intentionally orthogonal to dimensionality-reduction methods. TooManyCells is also equipped with an efficient matrix-free divisive hierarchical spectral clustering different from prevalent single-resolution clustering methods. TooManyCells enables multiresolution and multifaceted exploration of single-cell clades. An advantage of this paradigm is the immediate detection of rare and common populations that outperforms popular clustering and visualization algorithms, as demonstrated using existing single-cell transcriptomic data sets and new data modeling drug-resistance acquisition in leukemic T cells.

Eleven grand challenges in single-cell data science

The recent boom in microfluidics and combinatorial indexing strategies, combined with low sequencing costs, has empowered single-cell sequencing technology. Thousands-or even millions-of cells analyzed in a single experiment amount to a data revolution in single-cell biology and pose unique data science problems. Here, we outline eleven challenges that will be central to bringing this emerging field of single-cell data science forward. For each challenge, we highlight motivating research questions, review prior work, and formulate open problems. This compendium is for established researchers, newcomers, and students alike, highlighting interesting and rewarding problems for the coming years.

netNMF-sc: leveraging gene-gene interactions for imputation and dimensionality reduction in single-cell expression analysis

Single-cell RNA-sequencing (scRNA-seq) enables high-throughput measurement of RNA expression in single cells. However, because of technical limitations, scRNA-seq data often contain zero counts for many transcripts in individual cells. These zero counts, or dropout events, complicate the analysis of scRNA-seq data using standard methods developed for bulk RNA-seq data. Current scRNA-seq analysis methods typically overcome dropout by combining information across cells in a lower-dimensional space, leveraging the observation that cells generally occupy a small number of RNA expression states. We introduce netNMF-sc, an algorithm for scRNA-seq analysis that leverages information across both cells and genes. netNMF-sc learns a low-dimensional representation of scRNA-seq transcript counts using network-regularized non-negative matrix factorization. The network regularization takes advantage of prior knowledge of gene–gene interactions, encouraging pairs of genes with known interactions to be nearby each other in the low-dimensional representation. The resulting matrix factorization imputes gene abundance for both zero and nonzero counts and can be used to cluster cells into meaningful subpopulations. We show that netNMF-sc outperforms existing methods at clustering cells and estimating gene–gene covariance using both simulated and real scRNA-seq data, with increasing advantages at higher dropout rates (e.g., >60%). We also show that the results from netNMF-sc are robust to variation in the input network, with more representative networks leading to greater performance gains.

Differential Variation Analysis Enables Detection of Tumor Heterogeneity Using Single-Cell RNA-Sequencing Data

Tumor heterogeneity provides a complex challenge to cancer treatment and is a critical component of therapeutic response, disease recurrence, and patient survival. Single-cell RNA-sequencing (scRNA-seq) technologies have revealed the prevalence of intratumor and intertumor heterogeneity. Computational techniques are essential to quantify the differences in variation of these profiles between distinct cell types, tumor subtypes, and patients to fully characterize intratumor and intertumor molecular heterogeneity. In this study, we adapted our algorithm for pathway dysregulation, Expression Variation Analysis (EVA), to perform multivariate statistical analyses of differential variation of expression in gene sets for scRNA-seq. EVA has high sensitivity and specificity to detect pathways with true differential heterogeneity in simulated data. EVA was applied to several public domain scRNA-seq tumor datasets to quantify the landscape of tumor heterogeneity in several key applications in cancer genomics such as immunogenicity, metastasis, and cancer subtypes. Immune pathway heterogeneity of hematopoietic cell populations in breast tumors corresponded to the amount of diversity present in the T-cell repertoire of each individual. Cells from head and neck squamous cell carcinoma (HNSCC) primary tumors had significantly more heterogeneity across pathways than cells from metastases, consistent with a model of clonal outgrowth. Moreover, there were dramatic differences in pathway dysregulation across HNSCC basal primary tumors. Within the basal primary tumors, there was increased immune dysregulation in individuals with a high proportion of fibroblasts present in the tumor microenvironment. These results demonstrate the broad utility of EVA to quantify intertumor and intratumor heterogeneity from scRNA-seq data without reliance on low-dimensional visualization. SIGNIFICANCE: This study presents a robust statistical algorithm for evaluating gene expression heterogeneity within pathways or gene sets in single-cell RNA-seq data.

Application of single-cell sequencing in human cancer

Precision medicine is emerging as a cornerstone of future cancer care with the objective of providing targeted therapies based on the molecular phenotype of each individual patient. Traditional bulk-level molecular phenotyping of tumours leads to significant information loss, as the molecular profile represents an average phenotype over large numbers of cells, while cancer is a disease with inherent intra-tumour heterogeneity at the cellular level caused by several factors, including clonal evolution, tissue hierarchies, rare cells and dynamic cell states. Single-cell sequencing provides means to characterize heterogeneity in a large population of cells and opens up opportunity to determine key molecular properties that influence clinical outcomes, including prognosis and probability of treatment response. Single-cell sequencing methods are now reliable enough to be used in many research laboratories, and we are starting to see applications of these technologies for characterization of human primary cancer cells. In this review, we provide an overview of studies that have applied single-cell sequencing to characterize human cancers at the single-cell level, and we discuss some of the current challenges in the field.

Single-cell RNA-seq denoising using a deep count autoencoder

Single-cell RNA sequencing (scRNA-seq) has enabled researchers to study gene expression at a cellular resolution. However, noise due to amplification and dropout may obstruct analyses, so scalable denoising methods for increasingly large but sparse scRNA-seq data are needed. We propose a deep count autoencoder network (DCA) to denoise scRNA-seq datasets. DCA takes the count distribution, overdispersion and sparsity of the data into account using a negative binomial noise model with or without zero-inflation, and nonlinear gene-gene dependencies are captured. Our method scales linearly with the number of cells and can, therefore, be applied to datasets of millions of cells. We demonstrate that DCA denoising improves a diverse set of typical scRNA-seq data analyses using simulated and real datasets. DCA outperforms existing methods for data imputation in quality and speed, enhancing biological discovery.

Single-cell RNA sequencing is a powerful method to study gene expression, but noise in the data can obstruct analysis. Here the authors develop a denoising method based on a deep count autoencoder network that scales linearly with the number of cells, and therefore is compatible with large data sets.

Co-expression in Single-Cell Analysis: Saving Grace or Original Sin?

As a fundamental unit of life, the cell has rightfully been the subject of intense investigation throughout the history of biology. Technical innovations now make it possible to assay cellular features at genomic scale, yielding breakthroughs in our understanding of the molecular organization of tissues, and even whole organisms. As these data accumulate we will soon be faced with a new challenge: making sense of the plethora of results. Early investigations into the replicability of cell type profiles inferred from single-cell RNA sequencing data have indicated that this is likely to be surprisingly straightforward due to consistent gene co-expression. In this opinion article we discuss the evidence for this claim and its implications for interpreting cell type-specific gene expression.

Quantitative assessment of cell population diversity in single-cell landscapes

Single-cell RNA sequencing (scRNA-seq) has become a powerful tool for the systematic investigation of cellular diversity. As a number of computational tools have been developed to identify and visualize cell populations within a single scRNA-seq dataset, there is a need for methods to quantitatively and statistically define proportional shifts in cell population structures across datasets, such as expansion or shrinkage or emergence or disappearance of cell populations. Here we present sc-UniFrac, a framework to statistically quantify compositional diversity in cell populations between single-cell transcriptome landscapes. sc-UniFrac enables sensitive and robust quantification in simulated and experimental datasets in terms of both population identity and quantity. We have demonstrated the utility of sc-UniFrac in multiple applications, including assessment of biological and technical replicates, classification of tissue phenotypes and regional specification, identification and definition of altered cell infiltrates in tumorigenesis, and benchmarking batch-correction tools. sc-UniFrac provides a framework for quantifying diversity or alterations in cell populations across conditions and has broad utility for gaining insight into tissue-level perturbations at the single-cell resolution.

The Human Cell Atlas: Technical approaches and challenges

The Human Cell Atlas is a large, international consortium that aims to identify and describe every cell type in the human body. The comprehensive cellular maps that arise from this ambitious effort have the potential to transform many aspects of fundamental biology and clinical practice. Here, we discuss the technical approaches that could be used today to generate such a resource and also the technical challenges that will be encountered.

Quantitative single-cell transcriptomics

Single-cell RNA sequencing (scRNA-seq) is currently transforming our understanding of biology, as it is a powerful tool to resolve cellular heterogeneity and molecular networks. Over 50 protocols have been developed in recent years and also data processing and analyzes tools are evolving fast. Here, we review the basic principles underlying the different experimental protocols and how to benchmark them. We also review and compare the essential methods to process scRNA-seq data from mapping, filtering, normalization and batch corrections to basic differential expression analysis. We hope that this helps to choose appropriate experimental and computational methods for the research question at hand.

Evaluating methods of inferring gene regulatory networks highlights their lack of performance for single cell gene expression data

BACKGROUND

A fundamental fact in biology states that genes do not operate in isolation, and yet, methods that infer regulatory networks for single cell gene expression data have been slow to emerge. With single cell sequencing methods now becoming accessible, general network inference algorithms that were initially developed for data collected from bulk samples may not be suitable for single cells. Meanwhile, although methods that are specific for single cell data are now emerging, whether they have improved performance over general methods is unknown. In this study, we evaluate the applicability of five general methods and three single cell methods for inferring gene regulatory networks from both experimental single cell gene expression data and in silico simulated data.

RESULTS

Standard evaluation metrics using ROC curves and Precision-Recall curves against reference sets sourced from the literature demonstrated that most of the methods performed poorly when they were applied to either experimental single cell data, or simulated single cell data, which demonstrates their lack of performance for this task. Using default settings, network methods were applied to the same datasets. Comparisons of the learned networks highlighted the uniqueness of some predicted edges for each method. The fact that different methods infer networks that vary substantially reflects the underlying mathematical rationale and assumptions that distinguish network methods from each other.

CONCLUSIONS

This study provides a comprehensive evaluation of network modeling algorithms applied to experimental single cell gene expression data and in silico simulated datasets where the network structure is known. Comparisons demonstrate that most of these assessed network methods are not able to predict network structures from single cell expression data accurately, even if they are specifically developed for single cell methods. Also, single cell methods, which usually depend on more elaborative algorithms, in general have less similarity to each other in the sets of edges detected. The results from this study emphasize the importance for developing more accurate optimized network modeling methods that are compatible for single cell data. Newly-developed single cell methods may uniquely capture particular features of potential gene-gene relationships, and caution should be taken when we interpret these results.

DrImpute: imputing dropout events in single cell RNA sequencing data

BACKGROUND

The single cell RNA sequencing (scRNA-seq) technique begin a new era by allowing the observation of gene expression at the single cell level. However, there is also a large amount of technical and biological noise. Because of the low number of RNA transcriptomes and the stochastic nature of the gene expression pattern, there is a high chance of missing nonzero entries as zero, which are called dropout events.

RESULTS

We develop DrImpute to impute dropout events in scRNA-seq data. We show that DrImpute has significantly better performance on the separation of the dropout zeros from true zeros than existing imputation algorithms. We also demonstrate that DrImpute can significantly improve the performance of existing tools for clustering, visualization and lineage reconstruction of nine published scRNA-seq datasets.

CONCLUSIONS

DrImpute can serve as a very useful addition to the currently existing statistical tools for single cell RNA-seq analysis. DrImpute is implemented in R and is available at https://github.com/gongx030/DrImpute .