Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data

Linderman, George C.; Rachh, Manas; Hoskins, Jeremy G.; Steinerberger, Stefan; Kluger, Yuval

doi:10.1038/s41592-018-0308-4

Cited by 454 publications

(404 citation statements)

References 22 publications

(30 reference statements)

Supporting

Mentioning

403

Contrasting

Unclassified

Order By: Relevance

“…An overview of the comparison workflow is shown in Figure 1. Because common tSNE software can only extract a small number low-dimensional components [42][43][44], we only included tSNE results based on two low-dimensional components extracted from the recently developed fast FIt-SNE R package [44] in all figures. All data and analysis scripts for reproducing the results in the paper is available at www.xzlab.org/reproduce.html or https://github.com/xzhoulab/DRComparison.…”

Section: Resultsmentioning

confidence: 99%

“…, t-distributed stochastic neighbor embedding (tSNE; FIt-SNE, fftRtnse R function), and uniform manifold approximation and projection (UMAP; Python package). One of these methods, tSNE, can only extract a maximum of two or three low-dimensional components [42][43][44]. Therefore, we only included tSNE results based on two low-dimensional components extracted from the recently developed fast FIt-SNE R package [44] in all figures.…”

Section: Compared Dimensionality Reduction Methodsmentioning

confidence: 99%

“…One of these methods, tSNE, can only extract a maximum of two or three low-dimensional components [42][43][44]. Therefore, we only included tSNE results based on two low-dimensional components extracted from the recently developed fast FIt-SNE R package [44] in all figures. An overview of these 18 DR methods with their corresponding modeling characteristics is provided in Table 1.…”

Section: Compared Dimensionality Reduction Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Accuracy, Robustness and Scalability of Dimensionality Reduction Methods for Single Cell RNAseq Analysis

Sun

Zhu

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: Dimensionality reduction (DR) is an indispensable analytic component for many areas of single cell RNA sequencing (scRNAseq) data analysis. Proper DR can allow for effective noise removal and facilitate many downstream analyses that include cell clustering and lineage reconstruction. Unfortunately, despite the critical importance of DR in scRNAseq analysis and the vast number of DR methods developed for scRNAseq studies, however, few comprehensive comparison studies have been performed to evaluate the effectiveness of different DR methods in scRNAseq.Results: Here, we aim to fill this critical knowledge gap by providing a comparative evaluation of a variety of commonly used DR methods for scRNAseq studies. Specifically, we compared 18 different DR methods on 30 publicly available scRNAseq data sets that cover a range of sequencing techniques and sample sizes. We evaluated the performance of different DR methods for neighborhood preserving in terms of their ability to recover features of the original expression matrix, and for cell clustering and lineage reconstruction in terms of their accuracy and robustness. We also evaluated the computational scalability of different DR methods by recording their computational cost. Conclusions:Based on the comprehensive evaluation results, we provide important guidelines for choosing DR methods for scRNAseq data analysis. We also provide all analysis scripts used in the present study at www.xzlab.org/reproduce.html. Together, we hope that our results will serve as an important practical reference for practitioners to choose DR methods in the field of scRNAseq analysis. our results can serve as an important guideline for practitioners to choose DR methods in the field of scRNAseq analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Compared Dimensionality Reduction Methodsmentioning

confidence: 99%

Section: Compared Dimensionality Reduction Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy, Robustness and Scalability of Dimensionality Reduction Methods for Single Cell RNAseq Analysis

Sun

Zhu

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Notably, the authors of UMAP have pointed out the similarities between the two methods, and described UMAP as belonging to the same class of "kneighbour based graph learning algorithms" as t-SNE. A key advantage of UMAP over t-SNE appears to be its significantly faster runtimes on large datasets, however a recently developed variant of the t-SNE algorithm has been shown to have similarly fast runtimes in some cases 8,13,14 .…”

Section: Discussionmentioning

confidence: 99%

Straightforward clustering of single-cell RNA-Seq data with t-SNE and DBSCAN

Wagner

2019

Preprint

View full text Add to dashboard Cite

Clustering of cells by cell type is arguably the most common and repetitive task encountered during the analysis of single-cell RNA-Seq data. However, as popular clustering methods operate largely independently of visualization techniques, the fine-tuning of clustering parameters can be unintuitive and time-consuming. Here, I propose Galapagos, a simple and effective clustering workflow based on t-SNE and DBSCAN that does not require a gene selection step. In practice, Galapagos only involves the fine-tuning of two parameters, which is straightforward, as clustering is performed directly on the t-SNE visualization results. Using peripheral blood mononuclear cells as a model tissue, I validate the effectiveness of Galapagos in different ways. First, I show that Galapagos generates clusters corresponding to all main cell types present. Then, I demonstrate that the t-SNE results are robust to parameter choices and initialization points. Next, I employ a simulation approach to show that clustering with Galapagos is accurate and robust to the high levels of technical noise present. Finally, to demonstrate Galapagos' accuracy on real data, I compare clustering results to true cell type identities established using CITE-Seq data. In this context, I also provide an example of the primary limitation of Galapagos, namely the difficulty to resolve related cell types in cases where t-SNE fails to clearly separate the cells. Galapagos helps to make clustering scRNA-Seq data more intuitive and reproducible, and can be implemented in most programming languages with only a few lines of code.

show abstract

“…It then performs dimensionality reduction by principal component analysis (PCA) on HVGs, constructs a k nearest neighbor (k-NN) graph on the Principal Component (PC) space, calculates diffusion maps 19,20 and applies community detection algorithms on the graph to find clusters 21,22 . It visualizes cell profiles using either t-SNE 23,24 -based or UMAP 25,26 -based methods.…”

mentioning

confidence: 99%

Cumulus: a cloud-based data analysis framework for large-scale single-cell and single-nucleus RNA-seq

Gould

Yang

et al. 2019

Preprint

View full text Add to dashboard Cite

Massively parallel single-cell and single-nucleus RNA-seq (sc/snRNA-seq) have opened the way to systematic tissue atlases in health and disease, but as the scale of data generation is growing, so does the need for computational pipelines for scaled analysis. Here, we developed Cumulus, a cloud-based framework for analyzing large scale sc/snRNA-seq datasets. Cumulus combines the power of cloud computing with improvements in algorithm implementations to achieve high scalability, low cost, user-friendliness, and integrated support for a comprehensive set of features. We benchmark Cumulus on the Human Cell Atlas Census of Immune Cells dataset of bone marrow cells and show that it substantially improves efficiency over conventional frameworks, while maintaining or improving the quality of results, enabling large-scale studies.where ܷ and ܸ represent two cluster settings, ‫ܪ‬ denotes entropy and ‫ܫ‬ denotes mutual information.

show abstract

Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data

Cited by 454 publications

References 22 publications

Accuracy, Robustness and Scalability of Dimensionality Reduction Methods for Single Cell RNAseq Analysis

Accuracy, Robustness and Scalability of Dimensionality Reduction Methods for Single Cell RNAseq Analysis

Straightforward clustering of single-cell RNA-Seq data with t-SNE and DBSCAN

Cumulus: a cloud-based data analysis framework for large-scale single-cell and single-nucleus RNA-seq

Contact Info

Product

Resources

About