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

Gene selection from microarray gene expression datasets and clustering of samples into different groups are important data mining tasks for disease identification. Selection of more interpretable genes from the gene expression dataset is an essential data-preprocessing task, which helps to study on cancer diseases. Gene selection during sample clustering is inherently a difficult task as there is no obvious criterion to guide the search. Simultaneous gene selection and sample clustering is a two-way data analysis technique which has recently gained attention in research area. The traditional clustering techniques are unable to handle noisy data properly. So, effective clustering algorithms are more desirable which can deal with the relevant and noise free data. Therefore, target genes selection before sample clustering is essential and of course effective if both the tasks are done simultaneously. In this chapter, optimal gene subset is selected and sample clustering is performed simultaneously using Multi-Objective Genetic Algorithm (MOGA). Different versions of MOGA are employed to choose the optimal gene subset, where natural number of optimal clusters of samples is automatically obtained at the end of the process. Non-dominated sorting genetic algorithm (NSGA), Strength pareto evolutionary algorithm (SPEA) and its modified version SPEA2 are applied for the purpose. The methods use nonlinear hybrid uniform cellular automata for generating initial population, tournament selection strategy, two-point crossover operation, and a suitable jumping gene mutation mechanism to maintain diversity in the population. It uses mutual correlation coefficient; internal and external cluster validation indices as objective functions to find out the non-dominated solutions. To measure the cluster validation indices, clustering algorithm is applied on data subset associated to chromosomes in the population to find out different clusters. After the convergence of genetic algorithm, the best solution from the non-dominated solutions is identified that provides the important genes and categorizes the samples into clusters. The experimental results express the correctness of the proposed simultaneous gene selection and sample categorization method. The goodness of optimality of the clusters obtained using different genetic algorithms is expressed by comparing various cluster validation indices.

Recent advancements in single-cell RNA sequencing (scRNA-seq) technologies have allowed us to monitor the gene expression of individual cells. This level of detail in monitoring and characterization enables the research of cells in rapidly changing and heterogeneous environments such as early stage embryo or tumor tissue. However, the current scRNA-seq technologies are still facing many outstanding challenges. Due to the low amount of starting material, a large portion of expression values in scRNA-seq data is missing and reported as zeros. Moreover, scRNA-seq platforms are trending toward prioritizing high throughput over sequencing depth, which makes the problem become more serious in large datasets. These missing values can greatly affect the accuracy of downstream analyses. Here we introduce scINN, a neural network-based approach, that can reliably recover the missing values in single-cell data and thus can effectively improve the performance of downstream analyses. To impute the dropouts in single-cell data, we build a neural network that consists of two sub-networks: imputation sub-network and quality assessment sub-network. We compare scINN with state-of-the-art imputation methods using 10 scRNA-seq datasets with a total of more than 100,000 cells. In an extensive analysis, we demonstrate that scINN outperforms existing imputation methods in improving the identification of cell sub-populations and the Quality of transcriptome landscape visualization.

Single-cell technologies have recently gained popularity in cellular differentiation studies regarding their ability to resolve potential heterogeneities in cell populations. Analyzing such high-dimensional single-cell data has its own statistical and computational challenges. Popular multivariate approaches are based on data normalization, followed by dimension reduction and clustering to identify subgroups. However, in the case of cellular differentiation, we would not expect clear clusters to be present but instead expect the cells to follow continuous branching lineages. Here, we propose the use of diffusion maps to deal with the problem of defining differentiation trajectories. We adapt this method to single-cell data by adequate choice of kernel width and inclusion of uncertainties or missing measurement values, which enables the establishment of a pseudotemporal ordering of single cells in a high-dimensional gene expression space. We expect this output to reflect cell differentiation trajectories, where the data originates from intrinsic diffusion-like dynamics. Starting from a pluripotent stage, cells move smoothly within the transcriptional landscape towards more differentiated states with some stochasticity along their path. We demonstrate the robustness of our method with respect to extrinsic noise (e.g. measurement noise) and sampling density heterogeneities on simulated toy data as well as two single-cell quantitative polymerase chain reaction datasets (i.e. mouse haematopoietic stem cells and mouse embryonic stem cells) and an RNA-Seq data of human pre-implantation embryos. We show that diffusion maps perform considerably better than Principal Component Analysis and are advantageous over other techniques for non-linear dimension reduction such as t-distributed Stochastic Neighbour Embedding for preserving the global structures and pseudotemporal ordering of cells. The Matlab implementation of diffusion maps for single-cell data is available at https://www.helmholtz-muenchen.de/icb/single-cell-diffusion-map. fbuettner.phys@gmail.com, fabian.theis@helmholtz-muenchen.de Supplementary data are available at Bioinformatics online.

Single-cell RNA sequencing has been proved to be advantageous in discerning molecular heterogeneity in seemingly similar cells in a tissue. Due to the paucity of starting RNA, a large fraction of transcripts fail to amplify during the polymerase chain reaction cycle. This gets compounded by trivial biological noise such as variability in the cell cycle specific genes. As a result expression matrix obtained from a single-cell study is highly sparse with a large number of missing values. This hinders downstream analysis of single-cell expression data. It has been observed that feature engineering significantly improves the analysis outcomes. Feature extraction methods such as principal component analysis and zero-inflated factor analysis have been shown to be useful for subsequent steps of data analysis including clustering. However, too little or no visible efforts have been observed for developing feature selection techniques, which offer transparency for the analyst's consumption. We propose SelfE, a novel l2,0 -minimization algorithm that determines an optimal subset of feature vectors that preserves sub-space structures as observed in the data. We compared SelfE with the commonly used feature selection methods for single-cell expression data analysis.

Single-cell RNA-sequencing is an invaluable research tool that allows for the investigation of gene expression in heterogeneous cancer cell populations in ways that bulk RNA-seq cannot. However, normal (i.e., non tumor) cells in cancer samples have the potential to confound the downstream analysis of single-cell RNA-seq data. Existing methods for identifying cancer and normal cells include copy number variation inference, marker-gene expression analysis, and expression-based clustering. This work aims to extend the existing approaches for identifying cancer cells in single-cell RNA-seq samples by incorporating variant calling and the identification of putative driver alterations. We found that putative driver alterations can be detected in single-cell RNA-seq data obtained with full-length transcript technologies and noticed that a subset of cells in tumor samples are enriched for putative driver alterations as compared to normal cells. Furthermore, we show that the number of putative driver alterations and inferred copy number variation are not correlated in all samples. Taken together, our findings suggest that augmenting existing cancer-cell filtering methods with variant calling and analysis can increase the number of tumor cells that can be confidently included in downstream analyses of single-cell full-length transcript RNA-seq datasets.

Subpopulation identification, usually via some form of unsupervised clustering, is a fundamental step in the analysis of many single-cell RNA-seq data sets. This has motivated the development and application of a broad range of clustering methods, based on various underlying algorithms. Here, we provide a systematic and extensible performance evaluation of 14 clustering algorithms implemented in R, including both methods developed explicitly for scRNA-seq data and more general-purpose methods. The methods were evaluated using nine publicly available scRNA-seq data sets as well as three simulations with varying degree of cluster separability. The same feature selection approaches were used for all methods, allowing us to focus on the investigation of the performance of the clustering algorithms themselves. We evaluated the ability of recovering known subpopulations, the stability and the run time and scalability of the methods. Additionally, we investigated whether the performance could be improved by generating consensus partitions from multiple individual clustering methods. We found substantial differences in the performance, run time and stability between the methods, with SC3 and Seurat showing the most favorable results. Additionally, we found that consensus clustering typically did not improve the performance compared to the best of the combined methods, but that several of the top-performing methods already perform some type of consensus clustering. All the code used for the evaluation is available on GitHub ( https://github.com/markrobinsonuzh/scRNAseq_clustering_comparison). In addition, an R package providing access to data and clustering results, thereby facilitating inclusion of new methods and data sets, is available from Bioconductor ( https://bioconductor.org/packages/DuoClustering2018).

Background: Although cancer associated fibroblast (CAF) heterogeneity is recognized in oral squamous cell carcinoma (OSCC), the phenotype and role of CAF subpopulations in OSCC is still unknown. Objectives: This study aimed to dissect CAF heterogeneity and spatial location by using imaging mass cytometry on formalin fixed paraffin embedded (FFPE) tissues from primary OSCC. Methods: Imaging mass cytometry (Hyperion technology) was used to identify 24 markers (E-cadherin, EGFR, Ki-67, α-SMA, CD140β, FAP, FSP-1/S100A4, CD90/Thy-1, integrin α-11, collagen-1, tenascin-C, caveolin-1, CD4, CD8a, CD16, CD20, CD68, CD163, FoxP3, granzyme B, CD31, podoplanin, CD146, and YAP-1) in HPV-negative OSCC lesions (n=10). Tissue images were segmented employing the Steinbock framework. Unsupervised clustering of single-cell data was carried out using a bioinformatics pipeline developed in R language. Results: Unsupervised clustering identified several major cell types, with E-cadherin+ cells being the most abundant (30%) and CD146+ being the least abundant cell type (0.62%). Within the immune compartment CD4+ cells were most abundant (11.72%) followed by CD8+ cells (10.6%) and CD68+ cells (10.25%). Cells negative for other major lineage markers and positive for stromal markers were considered as CAFs and they clustered in 6 clusters defined as CAF1 to CAF6. CAF1-3 were high in FAP and CD140β while CAF 4-6 were low expressing FAP and CD140β. CAF1 and 6 expressed high αSMA, while CAF 3 and 5 expressed high collagen-1. CAF6 had high expression of integrin α-11. CAF1 and 3 subtypes were found closer to immune cells whereas CAF2 and 6 were closely located to cancer cells. Conclusions: We identified six distinct subpopulations of CAFs in OSCC by using imaging mass cytometry. Their clinical implications can be further revealed by using this method on larger patient cohorts with FFPE tissues available in diagnostic biobanks. Citation Format: Stian Tornaas, Siren Fromreide, Dimitrios Kleftogiannis, Hans Jørgen Aarstad, Olav K. Vintermyr, Lars Akslen, Harsh Dongre, Daniela Elena Costea. Identification of distinct subpopulations of cancer associated fibroblasts in oral squamous cell carcinoma by imaging mass cytometry [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Tumor-body Interactions: The Roles of Micro- and Macroenvironment in Cancer; 2024 Nov 17-20; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(22_Suppl):Abstract nr B004.

Dual-Stream Subspace Clustering Network for revealing gene targets in Alzheimer's disease

When analyzing scRNA-seq data containing heterogeneous cell populations, an important task is to select informative marker genes to distinguish various cell clusters and annotate the clusters with biologically meaningful cell types. In existing analysis methods and pipelines, marker genes are typically identified using a one-vs-all strategy, examining differential expression between one cell cluster versus the combination of all other cell clusters. However, this strategy applied to cell clusters belonging to closely related cell types often generates overlapping marker genes, which capture the common signature of closely related cell clusters but provide limited information for distinguishing them. To address the limitations of the one-vs-all strategy, we propose a hierarchical marker gene selection strategy that groups similar cell clusters and selects marker genes in a hierarchical manner. This strategy is able to improve the accuracy and interpretability of cell type identification in single-cell RNA-seq data.

When analyzing scRNA-seq data containing heterogeneous cell populations, an important task is to select informative marker genes to distinguish various cell clusters and annotate the clusters with biologically meaningful cell types. In existing analysis methods and pipelines, marker genes are typically identified using a one-vs-all strategy, examining differential expression between one cell cluster versus the combination of all other cell clusters. However, this strategy applied to cell clusters belonging to closely related cell types often generates overlapping marker genes, which capture the common signature of closely related cell clusters but provide limited information for distinguishing them. To address the limitations of the one-vs-all strategy, we propose a hierarchical marker gene selection strategy that groups similar cell clusters and selects marker genes in a hierarchical manner. This strategy is able to improve the accuracy and interpretability of cell type identification in single-cell RNA-seq data.

In recent years, the application of single-cell transcriptomics and spatial transcriptomics analysis techniques has become increasingly widespread. Whether dealing with single-cell transcriptomic or spatial transcriptomic data, dimensionality reduction and clustering are indispensable. Both single-cell and spatial transcriptomic data are often high-dimensional, making the analysis and visualization of such data challenging. Through dimensionality reduction, it becomes possible to visualize the data in a lower-dimensional space, allowing for the observation of relationships and differences between cell subpopulations. Clustering enables the grouping of similar cells into the same cluster, aiding in the identification of distinct cell subpopulations and revealing cellular diversity, providing guidance for downstream analyses. In this review, we systematically summarized the most widely recognized algorithms employed for the dimensionality reduction and clustering analysis of single-cell transcriptomic and spatial transcriptomic data. This endeavor provides valuable insights and ideas that can contribute to the development of novel tools in this rapidly evolving field.

The development and widespread utilization of high-throughput sequencing technologies in biology has fueled the rapid growth of single-cell RNA sequencing (scRNA-seq) data over the past decade. The development of scRNA-seq technology has significantly expanded researchers’ understanding of cellular heterogeneity. Accurate cell type identification is the prerequisite for any research on heterogeneous cell populations. However, due to the high noise and high dimensionality of scRNA-seq data, improving the effectiveness of cell type identification remains a challenge. As an effective dimensionality reduction method, Principal Component Analysis (PCA) is an essential tool for visualizing high-dimensional scRNA-seq data and identifying cell subpopulations. However, traditional PCA has some defects when used in mining the nonlinear manifold structure of the data and usually suffers from over-density of principal components (PCs). Therefore, we present a novel method in this paper called joint -norm and random walk graph constrained PCA (RWPPCA). RWPPCA aims to retain the data’s local information in the process of mapping high-dimensional data to low-dimensional space, to more accurately obtain sparse principal components and to then identify cell types more precisely. Specifically, RWPPCA combines the random walk (RW) algorithm with graph regularization to more accurately determine the local geometric relationships between data points. Moreover, to mitigate the adverse effects of dense PCs, the -norm is introduced to make the PCs sparser, thus increasing their interpretability. Then, we evaluate the effectiveness of RWPPCA on simulated data and scRNA-seq data. The results show that RWPPCA performs well in cell type identification and outperforms other comparison methods.

Single-cell heterogeneity analysis faces significant challenges due to the high dimensionality, complexity, and noise inherent in scRNA-seq data, especially when aiming for precise cell type classification. Existing analytical methods often exhibit limited generalization ability and adaptability across different biological contexts, leading to biased identification of cell subpopulations and hindering a comprehensive understanding of diseases, therapeutic responses, and biological processes. To address these issues, we propose a novel method named scKD, which integrates a hybrid neighbourhood-enhanced comparative learning model with a self-knowledge distillation strategy. scKD enhances clustering accuracy and is capable of accurately identifying both major cell types and rare cell subtypes. Extensive evaluations on multiple real-world datasets demonstrate that scKD achieves superior performance in subpopulation identification, clustering stability, and robustness. These results suggest that scKD is a powerful and reliable tool for analyzing single-cell transcriptomic data, facilitating deeper insights into cellular heterogeneity. All datasets used in this study are publicly available. Detailed information about all the single-cell datasets analyzed in this paper is provided in Supplementary Table 1. All datasets can be accessed at https://zenodo.org/records/15412380. The source code is available at https://github.com/A-qlh/sckd. Supplementary data are available at Bioinformatics online.

The identification of small subpopulations of cancer stem cells (CSCs) from blood mononuclear cells in human acute myeloid leukemia (AML) in 1997 was a landmark observation that recognized the potential role of CSCs in tumor aggressiveness. Two critical properties contribute to the functional role of CSCs in the establishment and recurrence of cancerous tumors: their capacity for self-renewal and their potential to differentiate into unlimited heterogeneous populations of cancer cells. These findings suggest that CSCs may represent novel therapeutic targets for the treatment and/or prevention of tumor progression, since they appear to be involved in cell migration, invasion, metastasis, and treatment resistance-all of which lead to poor clinical outcomes. The identification of CSC-specific markers, the isolation and characterization of CSCs from malignant tissues, and targeting strategies for the destruction of CSCs provide a novel opportunity for cancer research. This overview describes the potential implications of several common CSC markers in the identification of CSC subpopulations that are restricted to common malignant diseases, e.g., leukemia, and breast, prostate, pancreatic, and lung cancers. The role of microRNAs (miRNAs) in the regulation of CSC function is also discussed, as are several methods commonly used in CSC research. The potential role of the antidiabetic drug metformin- which has been shown to have effects on CSCs, and is known to function as an antitumor agent-is discussed as an example of this new class of chemotherapeutics.

An important challenge in pre-processing data from droplet-based single-cell RNA sequencing protocols is distinguishing barcodes associated with real cells from those binding background reads. Existing methods test barcodes individually and consequently do not leverage the strong cell-to-cell correlation present in most datasets. To improve cell detection, we introduce CB2, a cluster-based approach for distinguishing real cells from background barcodes. As demonstrated in simulated and case study datasets, CB2 has increased power for identifying real cells which allows for the identification of novel subpopulations and improves the precision of downstream analyses.