Clustering Of Single-cell Data Research Articles

A deep generative framework with embedded vector arithmetic and classifier for sample generation, label transfer, and clustering of single-cell data

Multiple-source single-cell datasets have accumulated quickly and need computational methods to integrate and decompose into meaningful components. Here, we present inClust (integrated clustering), a flexible deep generative framework that enables embedding auxiliary information, latent space vector arithmetic, and clustering. All functional parts are relatively modular, independent in implementation but interrelated at runtime, resulting in an all-in general framework that could work in supervised, semi-supervised, or unsupervised mode. We show that inClust is superior to most data integration methods in benchmark datasets. Then, we demonstrate the capability of inClust in the tasks of conditional out-of-distribution generation in supervised mode, label transfer in semi-supervised mode, and spatial domain identification in unsupervised mode. In these examples, inClust could accurately express the effect of each covariate, distinguish the query-specific cell types, or segment spatial domains. The results support that inClust is an excellent general framework for multiple-task harmonization and data decomposition.

ScAMACE: model-based approach to the joint analysis of single-cell data on chromatin accessibility, gene expression and methylation.

The advancement in technologies and the growth of available single-cell datasets motivate integrative analysis of multiple single-cell genomic datasets. Integrative analysis of multimodal single-cell datasets combines complementary information offered by single-omic datasets and can offer deeper insights on complex biological process. Clustering methods that identify the unknown cell types are among the first few steps in the analysis of single-cell datasets, and they are important for downstream analysis built upon the identified cell types. We propose scAMACE for the integrative analysis and clustering of single-cell data on chromatin accessibility, gene expression and methylation. We demonstrate that cell types are better identified and characterized through analyzing the three data types jointly. We develop an efficient Expectation-Maximization algorithm to perform statistical inference, and evaluate our methods on both simulation study and real data applications. We also provide the GPU implementation of scAMACE, making it scalable to large datasets. The software and datasets are available at https://github.com/cuhklinlab/scAMACE_py (python implementation) and https://github.com/cuhklinlab/scAMACE (R implementation). Supplementary data are available at Bioinformatics online.

SCHNEL: scalable clustering of high dimensional single-cell data.

Single cell data measures multiple cellular markers at the single-cell level for thousands to millions of cells. Identification of distinct cell populations is a key step for further biological understanding, usually performed by clustering this data. Dimensionality reduction based clustering tools are either not scalable to large datasets containing millions of cells, or not fully automated requiring an initial manual estimation of the number of clusters. Graph clustering tools provide automated and reliable clustering for single cell data, but suffer heavily from scalability to large datasets. We developed SCHNEL, a scalable, reliable and automated clustering tool for high-dimensional single-cell data. SCHNEL transforms large high-dimensional data to a hierarchy of datasets containing subsets of data points following the original data manifold. The novel approach of SCHNEL combines this hierarchical representation of the data with graph clustering, making graph clustering scalable to millions of cells. Using seven different cytometry datasets, SCHNEL outperformed three popular clustering tools for cytometry data, and was able to produce meaningful clustering results for datasets of 3.5 and 17.2 million cells within workable time frames. In addition, we show that SCHNEL is a general clustering tool by applying it to single-cell RNA sequencing data, as well as a popular machine learning benchmark dataset MNIST. Implementation is available on GitHub (https://github.com/biovault/SCHNELpy). All datasets used in this study are publicly available. Supplementary data are available at Bioinformatics online.

Abstract SY14-01: 34+ parameter single-cell mass cytometry of differential immune and drug responses across healthy human hematopoiesis and related malignancies

Abstract Fluorescence flow cytometry is an essential tool for dissecting the functional complexity of hematopoiesis. Using this, intracellular assays of signaling systems can be correlated to functional subsets of cells in complex populations based on active kinase states or other signaling junctions. Such correlations could be important to distinguish changes in signaling status that arise in rare cell subsets during environmental activation or pathogenesis. Historically, fluorescence spectral overlap has stymied the use of an increasing number of phenotypic parameters required to delineate an array of rare cell populations, thus limiting the application of this single-cell approach in studying complex diseases. Using a next-generation single-cell ‘mass cytometry’ platform we avoid these caveats, quantifying 34 parameters simultaneously with no spectral overlap (e.g., 31 antibodies, viability, DNA content and relative cell size). In healthy human blood and bone marrow, we identified cell subsets spanning the hematopoietic hierarchy using a panel of up to 31 surface markers. Additionally, 18 simultaneous functional markers and a battery of ex vivo stimuli and inhibitors were used to interrogate signaling. A novel algorithm for unsupervised high-dimensional clustering of single-cell data revealed a continuum of phenotypically contiguous subpopulations. This continuum was demarcated by surface marker expression, but paralleled by gradual changes in intracellular signaling architecture. These results have exposed unappreciated layers of human hematopoietic organization, and provide an opportunity to reevaluate diseases and pharmacological therapeutics as specific perturbations to this inherent order. Working from a 34-parameter template of normal hematopoiesis, we now are now focused on further dissecting the biology and improving risk stratification in hematopoietic malignancies. The application of these multidimensional approaches to human acute lymphoid leukemia (ALL) and acute myeloid leukemia (AML) samples will be presented. The simultaneous measurement of surface marker, cell cycle, apoptosis, and intracellular signaling parameters has revealed substantial heterogeneity in the blast populations of these diseases. This information is used to provide a high-content view of in vitro drug activity in blast subpopulations. Leveraging the wide variability between human individuals, we have integrated single-cell data from multiple individuals to construct a system-level correlation map of seemingly independent immune compartments. Specifically, we reframe the healthy immune system as a homeostatic network of immune parameters including cell frequency, surface marker intensity, and intracellular signaling capacity. Chronic diseases such as rheumatoid arthritis and prolonged bacterial infection fundamentally disrupt this balance, causing measurable and pathologically relevant shifts in the normal homeostatic balance. Taken together, these early successes point toward a future of actionable clinical information based on single-cell assays for diverse hematological malignancies and autoimmune disorders. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr SY14-01. doi:10.1158/1538-7445.AM2011-SY14-01