dropClust: Efficient clustering of ultra-large scRNA-seq data

ABSTRACTDroplet based single cell transcriptomics has recently enabled parallel screening of tens of thousands of single cells. Clustering methods that scale for such high dimensional data without compromising accuracy are scarce. We exploit Locality Sensitive Hashing, an approximate nearest neighbor search technique to develop ade novoclustering algorithm for large-scale single cell data. On a number of real datasets, dropClust outperformed the existing best practice methods in terms of execution time, clustering accuracy and detectability of minor cell sub-types.

Download Full-text

PARC: ultrafast and accurate clustering of phenotypic data of millions of single cells

Bioinformatics ◽

10.1093/bioinformatics/btaa042 ◽

2020 ◽

Vol 36 (9) ◽

pp. 2778-2786 ◽

Cited By ~ 5

Author(s):

Shobana V Stassen ◽

Dickson M D Siu ◽

Kelvin C M Lee ◽

Joshua W K Ho ◽

Hayden K H So ◽

...

Keyword(s):

Single Cell ◽

Large Scale ◽

Clustering Algorithm ◽

Single Cells ◽

Clustering Algorithms ◽

Cellular Heterogeneity ◽

Supplementary Information ◽

Phenotypic Data ◽

Scalable Algorithm ◽

Cell Data

Abstract Motivation New single-cell technologies continue to fuel the explosive growth in the scale of heterogeneous single-cell data. However, existing computational methods are inadequately scalable to large datasets and therefore cannot uncover the complex cellular heterogeneity. Results We introduce a highly scalable graph-based clustering algorithm PARC—Phenotyping by Accelerated Refined Community-partitioning—for large-scale, high-dimensional single-cell data (>1 million cells). Using large single-cell flow and mass cytometry, RNA-seq and imaging-based biophysical data, we demonstrate that PARC consistently outperforms state-of-the-art clustering algorithms without subsampling of cells, including Phenograph, FlowSOM and Flock, in terms of both speed and ability to robustly detect rare cell populations. For example, PARC can cluster a single-cell dataset of 1.1 million cells within 13 min, compared with >2 h for the next fastest graph-clustering algorithm. Our work presents a scalable algorithm to cope with increasingly large-scale single-cell analysis. Availability and implementation https://github.com/ShobiStassen/PARC. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

A Hybrid Clustering Algorithm for Identifying Cell Types from Single-Cell RNA-Seq Data

Genes ◽

10.3390/genes10020098 ◽

2019 ◽

Vol 10 (2) ◽

pp. 98 ◽

Cited By ~ 11

Author(s):

Xiaoshu Zhu ◽

Hong-Dong Li ◽

Yunpei Xu ◽

Lilu Guo ◽

Fang-Xiang Wu ◽

...

Keyword(s):

Single Cell ◽

Clustering Algorithm ◽

Nearest Neighbor ◽

Nonnegative Matrix ◽

Cell Types ◽

Clustering Methods ◽

K Nearest Neighbor ◽

Functional Variation ◽

Minimization Principle ◽

Structural Entropy

Single-cell RNA sequencing (scRNA-seq) has recently brought new insight into cell differentiation processes and functional variation in cell subtypes from homogeneous cell populations. A lack of prior knowledge makes unsupervised machine learning methods, such as clustering, suitable for analyzing scRNA-seq . However, there are several limitations to overcome, including high dimensionality, clustering result instability, and parameter adjustment complexity. In this study, we propose a method by combining structure entropy and k nearest neighbor to identify cell subpopulations in scRNA-seq data. In contrast to existing clustering methods for identifying cell subtypes, minimized structure entropy results in natural communities without specifying the number of clusters. To investigate the performance of our model, we applied it to eight scRNA-seq datasets and compared our method with three existing methods (nonnegative matrix factorization, single-cell interpretation via multikernel learning, and structural entropy minimization principle). The experimental results showed that our approach achieves, on average, better performance in these datasets compared to the benchmark methods.

Download Full-text

PARC: ultrafast and accurate clustering of phenotypic data of millions of single cells

10.1101/765628 ◽

2019 ◽

Author(s):

Shobana V. Stassen ◽

Dickson M. D. Siu ◽

Kelvin C. M. Lee ◽

Joshua W. K. Ho ◽

Hayden K. H. So ◽

...

Keyword(s):

Single Cell ◽

Large Scale ◽

Clustering Algorithm ◽

Single Cells ◽

Clustering Algorithms ◽

Cell Mass ◽

Cellular Heterogeneity ◽

Phenotypic Data ◽

Data Set ◽

Cell Data

AbstractMotivationNew single-cell technologies continue to fuel the explosive growth in the scale of heterogeneous single-cell data. However, existing computational methods are inadequately scalable to large datasets and therefore cannot uncover the complex cellular heterogeneity.ResultsWe introduce a highly scalable graph-based clustering algorithm PARC - phenotyping by accelerated refined community-partitioning – for ultralarge-scale, high-dimensional single-cell data (> 1 million cells). Using large single cell mass cytometry, RNA-seq and imaging-based biophysical data, we demonstrate that PARC consistently outperforms state-of-the-art clustering algorithms without sub-sampling of cells, including Phenograph, FlowSOM, and Flock, in terms of both speed and ability to robustly detect rare cell populations. For example, PARC can cluster a single cell data set of 1.1M cells within 13 minutes, compared to >2 hours to the next fastest graph-clustering algorithm, Phenograph. Our work presents a scalable algorithm to cope with increasingly large-scale single-cell analysis.Availability and Implementationhttps://github.com/ShobiStassen/PARC

Download Full-text

HGC: fast hierarchical clustering for large-scale single-cell data

10.1101/2021.02.07.430106 ◽

2021 ◽

Author(s):

Ziheng Zou ◽

Kui Hua ◽

Xuegong Zhang

Keyword(s):

Single Cell ◽

Hierarchical Clustering ◽

Large Scale ◽

Nearest Neighbor ◽

Linear Time ◽

Fixed Number ◽

Large Datasets ◽

Clustering Methods ◽

Shared Nearest Neighbor ◽

Cell Data

AbstractClustering is a key step in revealing heterogeneities in single-cell data. Cell heterogeneity can be explored at different resolutions and the resulted varying cell states are inherently nested. However, most existing single-cell clustering methods output a fixed number of clusters without the hierarchical information. Classical hierarchical clustering provides dendrogram of cells, but cannot scale to large datasets due to the high computational complexity. We present HGC, a fast Hierarchical Graph-based Clustering method to address both problems. It combines the advantages of graph-based clustering and hierarchical clustering. On the shared nearest neighbor graph of cells, HGC constructs the hierarchical tree with linear time complexity. Experiments showed that HGC enables multiresolution exploration of the biological hierarchy underlying the data, achieves state-of-the-art accuracy on benchmark data, and can scale to large datasets. HGC is freely available for academic use at https://www.github.com/XuegongLab/[email protected], [email protected]

Download Full-text

One Cell At a Time: A Unified Framework to Integrate and Analyze Single-cell RNA-seq Data

10.1101/2021.05.12.443814 ◽

2021 ◽

Author(s):

Chloe Xueqi Wang ◽

Lin Zhang ◽

Bo Wang

Keyword(s):

Single Cell ◽

Large Scale ◽

Gene Selection ◽

De Novo ◽

Single Cells ◽

Cell Types ◽

Biological Information ◽

Rna Seq ◽

Unified Framework ◽

Gene Expressions

The surge of single-cell RNA sequencing technologies enables the accessibility to large single-cell RNA-seq datasets at the scale of hundreds of thousands of single cells. Integrative analysis of large-scale scRNA-seq datasets has the potential of revealing de novo cell types as well as aggregating biological information. However, most existing methods fail to integrate multiple large-scale scRNA-seq datasets in a computational and memory efficient way. We hereby propose OCAT, One Cell At a Time, a graph-based method that sparsely encodes single-cell gene expressions to integrate data from multiple sources without most variable gene selection or explicit batch effect correction. We demonstrate that OCAT efficiently integrates multiple scRNA-seq datasets and achieves the state-of-the-art performance in cell-type clustering, especially in challenging scenarios of non-overlapping cell types. In addition, OCAT facilitates a variety of downstream analyses, such as gene prioritization, trajectory inference, pseudotime inference and cell inference. OCAT is a unifying tool to simplify and expedite single-cell data analysis.

Download Full-text

Leveraging high-powered RNA-Seq datasets to improve inference of regulatory activity in single-cell RNA-Seq data

10.1101/553040 ◽

2019 ◽

Cited By ~ 1

Author(s):

Ning Wang ◽

Andrew E. Teschendorff

Keyword(s):

Transcription Factors ◽

Single Cell ◽

Cell Fate ◽

Regulatory Networks ◽

Large Scale ◽

Single Cells ◽

Differential Expression Analysis ◽

Dropout Rate ◽

Rna Seq ◽

Regulatory Activity

AbstractInferring the activity of transcription factors in single cells is a key task to improve our understanding of development and complex genetic diseases. This task is, however, challenging due to the relatively large dropout rate and noisy nature of single-cell RNA-Seq data. Here we present a novel statistical inference framework called SCIRA (Single Cell Inference of Regulatory Activity), which leverages the power of large-scale bulk RNA-Seq datasets to infer high-quality tissue-specific regulatory networks, from which regulatory activity estimates in single cells can be subsequently obtained. We show that SCIRA can correctly infer regulatory activity of transcription factors affected by high technical dropouts. In particular, SCIRA can improve sensitivity by as much as 70% compared to differential expression analysis and current state-of-the-art methods. Importantly, SCIRA can reveal novel regulators of cell-fate in tissue-development, even for cell-types that only make up 5% of the tissue, and can identify key novel tumor suppressor genes in cancer at single cell resolution. In summary, SCIRA will be an invaluable tool for single-cell studies aiming to accurately map activity patterns of key transcription factors during development, and how these are altered in disease.

Download Full-text

Assessing the measurement transfer function of single-cell RNA sequencing

10.1101/045450 ◽

2016 ◽

Author(s):

Hannah R. Dueck ◽

Rizi Ai ◽

Adrian Camarena ◽

Bo Ding ◽

Reymundo Dominguez ◽

...

Keyword(s):

Transfer Function ◽

Single Cell ◽

Rna Sequencing ◽

Large Scale ◽

Transfer Functions ◽

Single Cells ◽

Biological Information ◽

Gene Detection ◽

Single Cell Rna Sequencing ◽

Scale Control

AbstractRecently, measurement of RNA at single cell resolution has yielded surprising insights. Methods for single-cell RNA sequencing (scRNA-seq) have received considerable attention, but the broad reliability of single cell methods and the factors governing their performance are still poorly known. Here, we conducted a large-scale control experiment to assess the transfer function of three scRNA-seq methods and factors modulating the function. All three methods detected greater than 70% of the expected number of genes and had a 50% probability of detecting genes with abundance greater than 2 to 4 molecules. Despite the small number of molecules, sequencing depth significantly affected gene detection. While biases in detection and quantification were qualitatively similar across methods, the degree of bias differed, consistent with differences in molecular protocol. Measurement reliability increased with expression level for all methods and we conservatively estimate the measurement transfer functions to be linear above ~5-10 molecules. Based on these extensive control studies, we propose that RNA-seq of single cells has come of age, yielding quantitative biological information.

Download Full-text

A Hybrid Deep Clustering Approach for Robust Cell Type Profiling Using Single-cell RNA-seq Data

10.1101/511626 ◽

2019 ◽

Cited By ~ 2

Author(s):

Suhas Srinivasan ◽

Nathan T. Johnson ◽

Dmitry Korkin

Keyword(s):

Deep Learning ◽

Single Cell ◽

Clustering Algorithm ◽

Hybrid Approach ◽

Feature Learning ◽

Specific Cell ◽

Clustering Methods ◽

Model Based Clustering ◽

Clustering And Classification ◽

Living Organisms

AbstractSingle-cell RNA sequencing (scRNA-seq) is a recent technology that enables fine-grained discovery of cellular subtypes and specific cell states. It routinely uses machine learning methods, such as feature learning, clustering, and classification, to assist in uncovering novel information from scRNA-seq data. However, current methods are not well suited to deal with the substantial amounts of noise that is created by the experiments or the variation that occurs due to differences in the cells of the same type. Here, we develop a new hybrid approach, Deep Unsupervised Single-cell Clustering (DUSC), that integrates feature generation based on a deep learning architecture with a model-based clustering algorithm, to find a compact and informative representation of the single-cell transcriptomic data generating robust clusters. We also include a technique to estimate an efficient number of latent features in the deep learning model. Our method outperforms both classical and state-of-the-art feature learning and clustering methods, approaching the accuracy of supervised learning. The method is freely available to the community and will hopefully facilitate our understanding of the cellular atlas of living organisms as well as provide the means to improve patient diagnostics and treatment.

Download Full-text

Characterization of CRISPR/Cas9 RANKL knockout mesenchymal stem cell clones based on single-cell printing technology and emulsion coupling assay as a low-cellularity workflow for single-cell cloning

10.1101/2020.08.17.253559 ◽

2020 ◽

Author(s):

Tobias Groß ◽

Csaba Jeney ◽

Darius Halm ◽

Günter Finkenzeller ◽

G. Björn Stark ◽

...

Keyword(s):

Single Cell ◽

Cell Line ◽

Large Scale ◽

Single Cells ◽

Protein Detection ◽

Cell Line Development ◽

Cell Printing ◽

Cell Clones ◽

The University

AbstractThe homogeneity of the genetically modified single-cells is a necessity for many applications such as cell line development, gene therapy, and tissue engineering and in particular for regenerative medical applications. The lack of tools to effectively isolate and characterize CRISPR/Cas9 engineered cells is considered as a significant bottleneck in these applications. Especially the incompatibility of protein detection technologies to confirm protein expression changes without a preconditional large-scale clonal expansion, creates a gridlock in many applications. To ameliorate the characterization of engineered cells, we propose an improved workflow, including single-cell printing/isolation technology based on fluorescent properties with high yield, a genomic edit screen (surveyor assay), mRNA rtPCR assessing altered gene expression and a versatile protein detection tool called emulsion-coupling to deliver a high-content, unified single-cell workflow. The workflow was exemplified by engineering and functionally validating RANKL knockout immortalized mesenchymal stem cells showing altered bone formation capacity of these cells. The resulting workflow is economical, without the requirement of large-scale clonal expansions of the cells with overall cloning efficiency above 30% of CRISPR/Cas9 edited cells. Nevertheless, as the single-cell clones are comprehensively characterized at an early, highly parallel phase of the development of cells including DNA, RNA, and protein levels, the workflow delivers a higher number of successfully edited cells for further characterization, lowering the chance of late failures in the development process.Author summaryI completed my undergraduate degree in biochemistry at the University of Ulm and finished my master's degree in pharmaceutical biotechnology at the University of Ulm and University of applied science of Biberach with a focus on biotechnology, toxicology and molecular biology. For my master thesis, I went to the University of Freiburg to the department of microsystems engineering, where I developed a novel workflow for cell line development. I stayed at the institute for my doctorate, but changed my scientific focus to the development of the emulsion coupling technology, which is a powerful tool for the quantitative and highly parallel measurement of protein and protein interactions. I am generally interested in being involved in the development of innovative molecular biological methods that can be used to gain new insights about biological issues. I am particularly curious to unravel the complex and often poorly understood protein interaction pathways that are the cornerstone of understanding cellular functionality and are a fundamental necessity to describe life mechanistically.

Download Full-text

Region-Based Graph Learning towards Large Scale Image Annotation

Graph-Based Methods in Computer Vision ◽

10.4018/978-1-4666-1891-6.ch013 ◽

2012 ◽

pp. 244-260

Author(s):

Bao Bing-Kun ◽

Yan Shuicheng

Keyword(s):

Large Scale ◽

Nearest Neighbor ◽

Image Annotation ◽

Learning Algorithm ◽

Label Propagation ◽

Locality Sensitive Hashing ◽

K Nearest Neighbor ◽

Neighbor Graph ◽

Nearest Neighbor Graph ◽

Modeling Data

Graph-based learning provides a useful approach for modeling data in image annotation problems. In this chapter, the authors introduce how to construct a region-based graph to annotate large scale multi-label images. It has been well recognized that analysis in semantic region level may greatly improve image annotation performance compared to that in whole image level. However, the region level approach increases the data scale to several orders of magnitude and lays down new challenges to most existing algorithms. To this end, each image is firstly encoded as a Bag-of-Regions based on multiple image segmentations. And then, all image regions are constructed into a large k-nearest-neighbor graph with efficient Locality Sensitive Hashing (LSH) method. At last, a sparse and region-aware image-based graph is fed into the multi-label extension of the Entropic graph regularized semi-supervised learning algorithm (Subramanya & Bilmes, 2009). In combination they naturally yield the capability in handling large-scale dataset. Extensive experiments on NUS-WIDE (260k images) and COREL-5k datasets well validate the effectiveness and efficiency of the framework for region-aware and scalable multi-label propagation.

Download Full-text