Selecting gene features for unsupervised analysis of single-cell gene expression data

Controlled Noise: Evidence of epigenetic regulation of Single-Cell expression variability

MOTIVATION

Understanding single-cell expression variability (scEV) or gene expression noise among cells of the same type and state is crucial for delineating population-level cellular function. While epigenetic mechanisms are widely implicated in gene expression regulation, a definitive link between chromatin accessibility and scEV remains elusive. Recent advances in single-cell techniques enable the study of single-cell multiomics data that include the simultaneous measurement of scATAC-seq and scRNA-seq within individual cells, presenting an unprecedented opportunity to address this gap.

RESULTS

This paper introduces an innovative testing pipeline to investigate the association between chromatin accessibility and scEV. With single-cell multiomics data of scATAC-seq and scRNA-seq, the pipeline hinges on comparing the prediction performance of scATAC-seq data on gene expression levels between highly variable genes (HVGs) and non-highly variable genes (non-HVGs). Applying this pipeline to paired scATAC-seq and scRNA-seq data from human hematopoietic stem and progenitor cells, we observed a significantly superior prediction performance of scATAC-seq data for HVGs compared to non-HVGs. Notably, there was substantial overlap between well-predicted genes and HVGs. The gene pathways enriched from well-predicted genes are highly pertinent to cell type-specific functions. Our findings support the notion that scEV largely stems from cell-to-cell variability in chromatin accessibility, providing compelling evidence for the epigenetic regulation of scEV and offering promising avenues for investigating gene regulation mechanisms at the single-cell level.

AVAILABILITY

The source code and data used in this paper can be found at https://github.com/SiweiCui/EpigeneticControlOfSingle-CellExpressionVariability.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Probe-based mass spectrometry approaches for single-cell and single-organelle measurements

Exploring the chemical content of individual cells not only reveals underlying cell-to-cell chemical heterogeneity but is also a key component in understanding how cells combine to form emergent properties of cellular networks and tissues. Recent technological advances in many analytical techniques including mass spectrometry (MS) have improved instrumental limits of detection and laser/ion probe dimensions, allowing the analysis of micron and submicron sized areas. In the case of MS, these improvements combined with MS's broad analyte detection capabilities have enabled the rise of single-cell and single-organelle chemical characterization. As the chemical coverage and throughput of single-cell measurements increase, more advanced statistical and data analysis methods have aided in data visualization and interpretation. This review focuses on secondary ion MS and matrix-assisted laser desorption/ionization MS approaches for single-cell and single-organelle characterization, which is followed by advances in mass spectral data visualization and analysis.

Characterizing efficient feature selection for single-cell expression analysis

Unsupervised feature selection is a critical step for efficient and accurate analysis of single-cell RNA-seq data. Previous benchmarks used two different criteria to compare feature selection methods: (i) proportion of ground-truth marker genes included in the selected features and (ii) accuracy of cell clustering using ground-truth cell types. Here, we systematically compare the performance of 11 feature selection methods for both criteria. We first demonstrate the discordance between these criteria and suggest using the latter. We then compare the distribution of selected genes in their means between feature selection methods. We show that lowly expressed genes exhibit seriously high coefficients of variation and are mostly excluded by high-performance methods. In particular, high-deviation- and high-expression-based methods outperform the widely used in Seurat package in clustering cells and data visualization. We further show they also enable a clear separation of the same cell type from different tissues as well as accurate estimation of cell trajectories.

Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology

Novel hypotheses in biomedical research are often developed or validated in model organisms such as mice and zebrafish and thus play a crucial role. However, due to biological differences between species, translating these findings into human applications remains challenging. Moreover, commonly used orthologous gene information is often incomplete and entails a significant information loss during gene-id conversion. To address these issues, we present a novel methodology for species-agnostic transfer learning with heterogeneous domain adaptation. We extended the cross-domain structure-preserving projection toward out-of-sample prediction. Our approach not only allows knowledge integration and translation across various species without relying on gene orthology but also identifies similar GO among the most influential genes composing the latent space for integration. Subsequently, during the alignment of latent spaces, each composed of species-specific genes, it is possible to identify functional annotations of genes missing from public orthology databases. We evaluated our approach with four different single-cell sequencing datasets focusing on cell-type prediction and compared it against related machine-learning approaches. In summary, the developed model outperforms related methods working without prior knowledge when predicting unseen cell types based on other species' data. The results demonstrate that our novel approach allows knowledge transfer beyond species barriers without the dependency on known gene orthology but utilizing the entire gene sets.

Differential variability analysis of single-cell gene expression data

The advent of single-cell RNA sequencing (scRNA-seq) technologies has enabled gene expression profiling at the single-cell resolution, thereby enabling the quantification and comparison of transcriptional variability among individual cells. Although alterations in transcriptional variability have been observed in various biological states, statistical methods for quantifying and testing differential variability between groups of cells are still lacking. To identify the best practices in differential variability analysis of single-cell gene expression data, we propose and compare 12 statistical pipelines using different combinations of methods for normalization, feature selection, dimensionality reduction and variability calculation. Using high-quality synthetic scRNA-seq datasets, we benchmarked the proposed pipelines and found that the most powerful and accurate pipeline performs simple library size normalization, retains all genes in analysis and uses denSNE-based distances to cluster medoids as the variability measure. By applying this pipeline to scRNA-seq datasets of COVID-19 and autism patients, we have identified cellular variability changes between patients with different severity status or between patients and healthy controls.

scAce: an adaptive embedding and clustering method for single-cell gene expression data

MOTIVATION

Since the development of single-cell RNA sequencing (scRNA-seq) technologies, clustering analysis of single-cell gene expression data has been an essential tool for distinguishing cell types and identifying novel cell types. Even though many methods have been available for scRNA-seq clustering analysis, the majority of them are constrained by the requirement on predetermined cluster numbers or the dependence on selected initial cluster assignment.

RESULTS

In this article, we propose an adaptive embedding and clustering method named scAce, which constructs a variational autoencoder to simultaneously learn cell embeddings and cluster assignments. In the scAce method, we develop an adaptive cluster merging approach which achieves improved clustering results without the need to estimate the number of clusters in advance. In addition, scAce provides an option to perform clustering enhancement, which can update and enhance cluster assignments based on previous clustering results from other methods. Based on computational analysis of both simulated and real datasets, we demonstrate that scAce outperforms state-of-the-art clustering methods for scRNA-seq data, and achieves better clustering accuracy and robustness.

AVAILABILITY AND IMPLEMENTATION

The scAce package is implemented in python 3.8 and is freely available from https://github.com/sldyns/scAce.

UDRN: Unified Dimensional Reduction Neural Network for feature selection and feature projection

Dimensional reduction (DR) maps high-dimensional data into a lower dimensions latent space with minimized defined optimization objectives. The two independent branches of DR are feature selection (FS) and feature projection (FP). FS focuses on selecting a critical subset of dimensions but risks destroying the data distribution (structure). On the other hand, FP combines all the input features into lower dimensions space, aiming to maintain the data structure, but lacks interpretability and sparsity. Moreover, FS and FP are traditionally incompatible categories and have not been unified into an amicable framework. Therefore, we consider that the ideal DR approach combines both FS and FP into a unified end-to-end manifold learning framework, simultaneously performing fundamental feature discovery while maintaining the intrinsic relationships between data samples in the latent space. This paper proposes a unified framework named Unified Dimensional Reduction Network (UDRN) to integrate FS and FP in an end-to-end way. Furthermore, a novel network framework is designed to implement FS and FP tasks separately using a stacked feature selection network and feature projection network. In addition, a stronger manifold assumption and a novel loss function are proposed. Furthermore, the loss function can leverage the priors of data augmentation to enhance the generalization ability of the proposed UDRN. Finally, comprehensive experimental results on four image and four biological datasets, including very high-dimensional data, demonstrate the advantages of DRN over existing methods (FS, FP, and FS&FP pipeline), especially in downstream tasks such as classification and visualization.

Supervised learning of high-confidence phenotypic subpopulations from single-cell data

Accurately identifying phenotype-relevant cell subsets from heterogeneous cell populations is crucial for delineating the underlying mechanisms driving biological or clinical phenotypes. Here, by deploying a learning with rejection strategy, we developed a novel supervised learning framework called PENCIL to identify subpopulations associated with categorical or continuous phenotypes from single-cell data. By embedding a feature selection function into this flexible framework, for the first time, we were able to select informative features and identify cell subpopulations simultaneously, which enables the accurate identification of phenotypic subpopulations otherwise missed by methods incapable of concurrent gene selection. Furthermore, the regression mode of PENCIL presents a novel ability for supervised phenotypic trajectory learning of subpopulations from single-cell data. We conducted comprehensive simulations to evaluate PENCIĽs versatility in simultaneous gene selection, subpopulation identification and phenotypic trajectory prediction. PENCIL is fast and scalable to analyze 1 million cells within 1 hour. Using the classification mode, PENCIL detected T-cell subpopulations associated with melanoma immunotherapy outcomes. Moreover, when applied to scRNA-seq of a mantle cell lymphoma patient with drug treatment across multiple time points, the regression mode of PENCIL revealed a transcriptional treatment response trajectory. Collectively, our work introduces a scalable and flexible infrastructure to accurately identify phenotype-associated subpopulations from single-cell data.

A cofunctional grouping-based approach for non-redundant feature gene selection in unannotated single-cell RNA-seq analysis

Feature gene selection has significant impact on the performance of cell clustering in single-cell RNA sequencing (scRNA-seq) analysis. A well-rounded feature selection (FS) method should consider relevance, redundancy and complementarity of the features. Yet most existing FS methods focus on gene relevance to the cell types but neglect redundancy and complementarity, which undermines the cell clustering performance. We develop a novel computational method GeneClust to select feature genes for scRNA-seq cell clustering. GeneClust groups genes based on their expression profiles, then selects genes with the aim of maximizing relevance, minimizing redundancy and preserving complementarity. It can work as a plug-in tool for FS with any existing cell clustering method. Extensive benchmark results demonstrate that GeneClust significantly improve the clustering performance. Moreover, GeneClust can group cofunctional genes in biological process and pathway into clusters, thus providing a means of investigating gene interactions and identifying potential genes relevant to biological characteristics of the dataset. GeneClust is freely available at https://github.com/ToryDeng/scGeneClust.

Benchmarking cell-type clustering methods for spatially resolved transcriptomics data

Spatially resolved transcriptomics technologies enable the measurement of transcriptome information while retaining the spatial context at the regional, cellular or sub-cellular level. While previous computational methods have relied on gene expression information alone for clustering single-cell populations, more recent methods have begun to leverage spatial location and histology information to improve cell clustering and cell-type identification. In this study, using seven semi-synthetic datasets with real spatial locations, simulated gene expression and histology images as well as ground truth cell-type labels, we evaluate 15 clustering methods based on clustering accuracy, robustness to data variation and input parameters, computational efficiency, and software usability. Our analysis demonstrates that even though incorporating the additional spatial and histology information leads to increased accuracy in some datasets, it does not consistently improve clustering compared with using only gene expression data. Our results indicate that for the clustering of spatial transcriptomics data, there are still opportunities to enhance the overall accuracy and robustness by improving information extraction and feature selection from spatial and histology data.

High-dimensional genomic feature selection with the ordered stereotype logit model

For many high-dimensional genomic and epigenomic datasets, the outcome of interest is ordinal. While these ordinal outcomes are often thought of as the observed cutpoints of some latent continuous variable, some ordinal outcomes are truly discrete and are comprised of the subjective combination of several factors. The nonlinear stereotype logistic model, which does not assume proportional odds, was developed for these 'assessed' ordinal variables. It has previously been extended to the frequentist high-dimensional feature selection setting, but the Bayesian framework provides some distinct advantages in terms of simultaneous uncertainty quantification and variable selection. Here, we review the stereotype model and Bayesian variable selection methods and demonstrate how to combine them to select genomic features associated with discrete ordinal outcomes. We compared the Bayesian and frequentist methods in terms of variable selection performance. We additionally applied the Bayesian stereotype method to an acute myeloid leukemia RNA-sequencing dataset to further demonstrate its variable selection abilities by identifying features associated with the European LeukemiaNet prognostic risk score.

The scINSIGHT Package for Integrating Single-Cell RNA-Seq Data from Different Biological Conditions

Data integration is a critical step in the analysis of multiple single-cell RNA sequencing samples to account for heterogeneity due to both biological and technical variability. scINSIGHT is a new integration method for single-cell gene expression data, and can effectively use the information of biological condition to improve the integration of multiple single-cell samples. scINSIGHT is based on a novel non-negative matrix factorization model that learns common and condition-specific gene modules in samples from different biological or experimental conditions. Using these gene modules, scINSIGHT can further identify cellular identities and active biological processes in different cell types or conditions. Here we introduce the installation and main functionality of the scINSIGHT R package, including how to preprocess the data, apply the scINSIGHT algorithm, and analyze the output.

scINSIGHT for interpreting single-cell gene expression from biologically heterogeneous data

The increasing number of scRNA-seq data emphasizes the need for integrative analysis to interpret similarities and differences between single-cell samples. Although different batch effect removal methods have been developed, none are suitable for heterogeneous single-cell samples coming from multiple biological conditions. We propose a method, scINSIGHT, to learn coordinated gene expression patterns that are common among, or specific to, different biological conditions, and identify cellular identities and processes across single-cell samples. We compare scINSIGHT with state-of-the-art methods using simulated and real data, which demonstrate its improved performance. Our results show the applicability of scINSIGHT in diverse biomedical and clinical problems.

Phitest for analyzing the homogeneity of single-cell populations

MOTIVATION

Single-cell RNA sequencing technologies facilitate the characterization of transcriptomic landscapes in diverse species, tissues and cell types with unprecedented molecular resolution. In order to better understand animal development, physiology, and pathology, unsupervised clustering analysis is often used to identify relevant cell populations. Although considerable progress has been made in terms of clustering algorithms in recent years, it remains challenging to evaluate the quality of the inferred single-cell clusters, which can greatly impact downstream analysis and interpretation.

RESULTS

We propose a bioinformatics tool named Phitest to analyze the homogeneity of single-cell populations. Phitest is able to distinguish between homogeneous and heterogeneous cell populations, providing an objective and automatic method to optimize the performance of single-cell clustering analysis.

AVAILABILITY AND IMPLEMENTATION

The PhitestR package is freely available on both Github (https://github.com/Vivianstats/PhitestR) and the Comprehensive R Archive Network (CRAN). There is no new genomic data associated with this article. Published data used in the analysis are described in detail in the Supplementary Data.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Identification of Helicobacter pylori Membrane Proteins Using Sequence-Based Features

Helicobacter pylori (H. pylori) is the most common risk factor for gastric cancer worldwide. The membrane proteins of the H. pylori are involved in bacterial adherence and play a vital role in the field of drug discovery. Thus, an accurate and cost-effective computational model is needed to predict the uncharacterized membrane proteins of H. pylori. In this study, a reliable benchmark dataset consisted of 114 membrane and 219 nonmembrane proteins was constructed based on UniProt. A support vector machine- (SVM-) based model was developed for discriminating H. pylori membrane proteins from nonmembrane proteins by using sequence information. Cross-validation showed that our method achieved good performance with an accuracy of 91.29%. It is anticipated that the proposed model will be useful for the annotation of H. pylori membrane proteins and the development of new anti-H. pylori agents.

Ensemble feature selection for stable biomarker identification and cancer classification from microarray expression data

Microarray technology facilitates the simultaneous measurement of expression of tens of thousands of genes and enables us to study cancers and tumors at the molecular level. Because microarray data are typically characterized by small sample size and high dimensionality, accurate and stable feature selection is thus of fundamental importance to the diagnostic accuracy and deep understanding of disease mechanism. Hence, we in this study present an ensemble feature selection framework to improve the discrimination and stability of finally selected features. Specifically, we utilize sampling techniques to obtain multiple sampled datasets, from each of which we use a base feature selector to select a subset of features. Afterwards, we develop two aggregation strategies to combine multiple feature subsets into one set. Finally, comparative experiments are conducted on four publicly available microarray datasets covering both binary and multi-class cases in terms of classification accuracy and three stability metrics. Results show that the proposed method obtains better stability scores and achieves comparable to and even better classification performance than its competitors.