Dimensionality reduction for visualizing single-cell data using UMAP

@article{Becht2019DimensionalityRF,
  title={Dimensionality reduction for visualizing single-cell data using UMAP},
  author={E. Becht and Leland McInnes and John Healy and C. Dutertre and I. Kwok and L. Ng and F. Ginhoux and E. Newell},
  journal={Nature Biotechnology},
  year={2019},
  volume={37},
  pages={38-44}
}
Advances in single-cell technologies have enabled high-resolution dissection of tissue composition. [...] Key Method Here we apply it to biological data, using three well-characterized mass cytometry and single-cell RNA sequencing datasets. Comparing the performance of UMAP with five other tools, we find that UMAP provides the fastest run times, highest reproducibility and the most meaningful organization of cell clusters. The work highlights the use of UMAP for improved visualization and interpretation of…Expand

Figures and Topics from this paper

A Quantitative Framework for Evaluating Single-Cell Data Structure Preservation by Dimensionality Reduction Techniques
TLDR
This work uses discrete and continuous real-world and synthetic scRNA-seq datasets to show how input cell distribution and method parameters are largely determinant of global, local, and organizational data structure preservation by 11 common dimensionality reduction methods. Expand
A quantitative framework for evaluating single-cell data structure preservation by dimensionality reduction techniques
TLDR
This work uses discrete and continuous scRNA-seq datasets to find that input cell distribution and method parameters are largely determinant of global, local, and organizational data structure preservation by eleven published dimensionality reduction methods. Expand
Meeting the Challenges of High-Dimensional Single-Cell Data Analysis in Immunology
TLDR
The impact of new analysis techniques for in-depths insights into the dynamics of immune regulation obtained from static snapshot data is discussed to provide tools to immunologists to address the high dimensionality of their single-cell data. Expand
Assessing Single-Cell Transcriptomic Variability through Density-Preserving Data Visualization
TLDR
Den-S NE and densMAP are presented, density-preserving visualization tools based on t-SNE and UMAP, respectively, and their ability to accurately incorporate information about transcriptomic variability into the visual interpretation of single-cell RNA-seq data is demonstrated. Expand
Rapid single-cell cytometry data visualization with EmbedSOM
Efficient unbiased data analysis is a major challenge for laboratories handling large cytometry datasets. We present EmbedSOM, a non-linear embedding algorithm based on FlowSOM that improves theExpand
A Comparison for Dimensionality Reduction Methods of Single-Cell RNA-seq Data
TLDR
It is found that t-distributed stochastic neighbor embedding yielded the best overall performance with the highest accuracy and computing cost, and uniform manifold approximation and projection (UMAP) exhibited the highest stability, as well as moderate accuracy and the second highest computing cost. Expand
Dimensionality Reduction of Single-Cell RNA-Seq Data.
TLDR
This chapter describes the typical dimensionality reduction workflow that is used for scRNA-seq datasets, specifically highlighting the roles of principal component analysis, t-distributed stochastic neighborhood embedding, and uniform manifold approximation and projection in this setting. Expand
Ensemble dimensionality reduction and feature gene extraction for single-cell RNA-seq data
TLDR
Different from existing dimensionality reduction techniques, the proposed method implements an ensemble learning scheme that utilizes massive weak learners for an accurate similarity search and the low-dimensional embedding of the data is estimated and optimized through spectral embedding and stochastic gradient descent. Expand
Density-Preserving Data Visualization Unveils Dynamic Patterns of Single-Cell Transcriptomic Variability
TLDR
Den-SNE and densMAP are presented, the authors' density-preserving visualization tools based on t-S NE and UMAP, respectively, and their ability to facilitate more accurate visual interpretation of single-cell RNA-seq data is demonstrated. Expand
Machine learning for single cell genomics data analysis
TLDR
This review surveys in this review recent advances in ML approaches developed to analyze single-cell omics data, focusing mainly on peer-reviewed publications published in the last two years. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Interpretable dimensionality reduction of single cell transcriptome data with deep generative models
TLDR
A robust statistical model, scvis, is presented, to capture and visualize the low-dimensional structures in single-cell gene expression data and is robust to the number of data points and learns a probabilistic parametric mapping function to add new data points to an existing embedding. Expand
viSNE enables visualization of high dimensional single-cell data and reveals phenotypic heterogeneity of leukemia
New high-dimensional, single-cell technologies offer unprecedented resolution in the analysis of heterogeneous tissues. However, because these technologies can measure dozens of parametersExpand
Single-cell regulatory network inference and clustering from high-dimensional sequencing data
TLDR
NIRP infers a gene regulatory network (GRN) from big scRNA-seq data by transforming the original data space to a lower dimensions space and capturing the similarities among gene expressions, which makes NIRP a reliable tool, able to handle big single-cell data with ultra-high dimensionality and complexity. Expand
Automated Mapping of Phenotype Space with Single-Cell Data
TLDR
X-shift is presented, an algorithm that processes data sets using fast k-nearest-neighbor estimation of cell event density and arranges populations by marker-based classification and enables automated cell-subset clustering and access to biological insights that 'prior knowledge' might prevent the researcher from discovering. Expand
Mapping the Mouse Cell Atlas by Microwell-Seq
TLDR
This study developed Microwell-seq, a high-throughput and low-cost scRNA-seq platform using simple, inexpensive devices, and built a web-based "single-cell MCA analysis" pipeline that accurately defines cell types based on single-cell digital expression. Expand
SCANPY: large-scale single-cell gene expression data analysis
TLDR
This work presents Scanpy, a scalable toolkit for analyzing single-cell gene expression data that includes methods for preprocessing, visualization, clustering, pseudotime and trajectory inference, differential expression testing, and simulation of gene regulatory networks, and AnnData, a generic class for handling annotated data matrices. Expand
Computational flow cytometry: helping to make sense of high-dimensional immunology data
TLDR
This Review provides non-experts with a broad and practical overview of the many recent developments in computational flow cytometry. Expand
Integrating single-cell transcriptomic data across different conditions, technologies, and species
TLDR
An analytical strategy for integrating scRNA-seq data sets based on common sources of variation is introduced, enabling the identification of shared populations across data sets and downstream comparative analysis. Expand
A High-Dimensional Atlas of Human T Cell Diversity Reveals Tissue-Specific Trafficking and Cytokine Signatures.
TLDR
Mass cytometry is utilized to simultaneously analyze T cell trafficking and functional markers across eight different human tissues, revealing a plethora of tissue immune signatures and providing a systemic map of how T-cell phenotypes are altered throughout the human body. Expand
SCENIC: Single-cell regulatory network inference and clustering
TLDR
SCENIC (Single Cell rEgulatory Network Inference and Clustering) is the first method to analyze scRNA-seq data using a network-centric, rather than cell-centric approach and allows for the simultaneous tracing of genomic regulatory programs and the mapping of cellular identities emerging from these programs. Expand
...
1
2
3
4
...