A generalization of t-SNE and UMAP to single-cell multimodal omics

Abstract Emerging single-cell technologies profile multiple types of molecules within individual cells. A fundamental step in the analysis of the produced high-dimensional data is their visualization using dimensionality reduction techniques such as t-SNE and UMAP. We introduce j-SNE and j-UMAP as t...

Full description

Bibliographic Details
Main Authors: Van Hoan Do, Stefan Canzar
Format: Article
Language:English
Published: BMC 2021-05-01
Series:Genome Biology
Subjects:
Online Access:https://doi.org/10.1186/s13059-021-02356-5
id doaj-2a2b62b8572a4eb2953fc10359f62288
record_format Article
spelling doaj-2a2b62b8572a4eb2953fc10359f622882021-05-09T11:45:10ZengBMCGenome Biology1474-760X2021-05-012211910.1186/s13059-021-02356-5A generalization of t-SNE and UMAP to single-cell multimodal omicsVan Hoan Do0Stefan Canzar1Gene Center, Ludwig-Maximilians-Universität MünchenGene Center, Ludwig-Maximilians-Universität MünchenAbstract Emerging single-cell technologies profile multiple types of molecules within individual cells. A fundamental step in the analysis of the produced high-dimensional data is their visualization using dimensionality reduction techniques such as t-SNE and UMAP. We introduce j-SNE and j-UMAP as their natural generalizations to the joint visualization of multimodal omics data. Our approach automatically learns the relative contribution of each modality to a concise representation of cellular identity that promotes discriminative features but suppresses noise. On eight datasets, j-SNE and j-UMAP produce unified embeddings that better agree with known cell types and that harmonize RNA and protein velocity landscapes.https://doi.org/10.1186/s13059-021-02356-5Data visualizationSingle-cell sequencingMultimodal omicst-SNEUMAPRNA velocity
collection DOAJ
language English
format Article
sources DOAJ
author Van Hoan Do
Stefan Canzar
spellingShingle Van Hoan Do
Stefan Canzar
A generalization of t-SNE and UMAP to single-cell multimodal omics
Genome Biology
Data visualization
Single-cell sequencing
Multimodal omics
t-SNE
UMAP
RNA velocity
author_facet Van Hoan Do
Stefan Canzar
author_sort Van Hoan Do
title A generalization of t-SNE and UMAP to single-cell multimodal omics
title_short A generalization of t-SNE and UMAP to single-cell multimodal omics
title_full A generalization of t-SNE and UMAP to single-cell multimodal omics
title_fullStr A generalization of t-SNE and UMAP to single-cell multimodal omics
title_full_unstemmed A generalization of t-SNE and UMAP to single-cell multimodal omics
title_sort generalization of t-sne and umap to single-cell multimodal omics
publisher BMC
series Genome Biology
issn 1474-760X
publishDate 2021-05-01
description Abstract Emerging single-cell technologies profile multiple types of molecules within individual cells. A fundamental step in the analysis of the produced high-dimensional data is their visualization using dimensionality reduction techniques such as t-SNE and UMAP. We introduce j-SNE and j-UMAP as their natural generalizations to the joint visualization of multimodal omics data. Our approach automatically learns the relative contribution of each modality to a concise representation of cellular identity that promotes discriminative features but suppresses noise. On eight datasets, j-SNE and j-UMAP produce unified embeddings that better agree with known cell types and that harmonize RNA and protein velocity landscapes.
topic Data visualization
Single-cell sequencing
Multimodal omics
t-SNE
UMAP
RNA velocity
url https://doi.org/10.1186/s13059-021-02356-5
work_keys_str_mv AT vanhoando ageneralizationoftsneandumaptosinglecellmultimodalomics
AT stefancanzar ageneralizationoftsneandumaptosinglecellmultimodalomics
AT vanhoando generalizationoftsneandumaptosinglecellmultimodalomics
AT stefancanzar generalizationoftsneandumaptosinglecellmultimodalomics
_version_ 1721454071199563776