Scalable visualization for high-dimensional single-cell data

Juho Kim, Nate Russell, Jian Peng

Research output: Contribution to journalConference article

Abstract

Single-cell analysis can uncover the mysteries in the state of individual cells and enable us to construct new models about the analysis of heterogeneous tissues. State-of-the-art technologies for single-cell analysis have been developed to measure the properties of single-cells and detect hidden information. They are able to provide the measurements of dozens of features simultaneously in each cell. However, due to the high-dimensionality, heterogeneous complexity and sheer enormity of single-cell data, its interpretation is challenging. Thus, new methods to overcome high-dimensionality are necessary. Here, we present a computational tool that allows efficient visualization of high-dimensional single-cell data onto a low-dimensional (2D or 3D) space while preserving the similarity structure between single-cells. We first construct a network that can represent the similarity structure between the high-dimensional representations of single-cells, and then, embed this network into a low-dimensional space through an efficient online optimization method based on the idea of negative sampling. Using this approach, we can preserve the high-dimensional structure of single-cell data in an embedded low-dimensional space that facilitates visual analyses of the data.

Original languageEnglish (US)
Pages (from-to)623-634
Number of pages12
JournalPacific Symposium on Biocomputing
Volume0
Issue number212679
DOIs
StatePublished - Jan 1 2017
Event22nd Pacific Symposium on Biocomputing, PSB 2017 - Kohala Coast, United States
Duration: Jan 4 2017Jan 8 2017

Fingerprint

Visualization
Tissue
Sampling
Single-Cell Analysis
Technology

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Scalable visualization for high-dimensional single-cell data. / Kim, Juho; Russell, Nate; Peng, Jian.

In: Pacific Symposium on Biocomputing, Vol. 0, No. 212679, 01.01.2017, p. 623-634.

Research output: Contribution to journalConference article

Kim, Juho ; Russell, Nate ; Peng, Jian. / Scalable visualization for high-dimensional single-cell data. In: Pacific Symposium on Biocomputing. 2017 ; Vol. 0, No. 212679. pp. 623-634.
@article{2e8dadeefd3e4dbfb690db55484facd9,
title = "Scalable visualization for high-dimensional single-cell data",
abstract = "Single-cell analysis can uncover the mysteries in the state of individual cells and enable us to construct new models about the analysis of heterogeneous tissues. State-of-the-art technologies for single-cell analysis have been developed to measure the properties of single-cells and detect hidden information. They are able to provide the measurements of dozens of features simultaneously in each cell. However, due to the high-dimensionality, heterogeneous complexity and sheer enormity of single-cell data, its interpretation is challenging. Thus, new methods to overcome high-dimensionality are necessary. Here, we present a computational tool that allows efficient visualization of high-dimensional single-cell data onto a low-dimensional (2D or 3D) space while preserving the similarity structure between single-cells. We first construct a network that can represent the similarity structure between the high-dimensional representations of single-cells, and then, embed this network into a low-dimensional space through an efficient online optimization method based on the idea of negative sampling. Using this approach, we can preserve the high-dimensional structure of single-cell data in an embedded low-dimensional space that facilitates visual analyses of the data.",
author = "Juho Kim and Nate Russell and Jian Peng",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813207813_0057",
language = "English (US)",
volume = "0",
pages = "623--634",
journal = "Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing",
issn = "2335-6936",
number = "212679",

}

TY - JOUR

T1 - Scalable visualization for high-dimensional single-cell data

AU - Kim, Juho

AU - Russell, Nate

AU - Peng, Jian

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Single-cell analysis can uncover the mysteries in the state of individual cells and enable us to construct new models about the analysis of heterogeneous tissues. State-of-the-art technologies for single-cell analysis have been developed to measure the properties of single-cells and detect hidden information. They are able to provide the measurements of dozens of features simultaneously in each cell. However, due to the high-dimensionality, heterogeneous complexity and sheer enormity of single-cell data, its interpretation is challenging. Thus, new methods to overcome high-dimensionality are necessary. Here, we present a computational tool that allows efficient visualization of high-dimensional single-cell data onto a low-dimensional (2D or 3D) space while preserving the similarity structure between single-cells. We first construct a network that can represent the similarity structure between the high-dimensional representations of single-cells, and then, embed this network into a low-dimensional space through an efficient online optimization method based on the idea of negative sampling. Using this approach, we can preserve the high-dimensional structure of single-cell data in an embedded low-dimensional space that facilitates visual analyses of the data.

AB - Single-cell analysis can uncover the mysteries in the state of individual cells and enable us to construct new models about the analysis of heterogeneous tissues. State-of-the-art technologies for single-cell analysis have been developed to measure the properties of single-cells and detect hidden information. They are able to provide the measurements of dozens of features simultaneously in each cell. However, due to the high-dimensionality, heterogeneous complexity and sheer enormity of single-cell data, its interpretation is challenging. Thus, new methods to overcome high-dimensionality are necessary. Here, we present a computational tool that allows efficient visualization of high-dimensional single-cell data onto a low-dimensional (2D or 3D) space while preserving the similarity structure between single-cells. We first construct a network that can represent the similarity structure between the high-dimensional representations of single-cells, and then, embed this network into a low-dimensional space through an efficient online optimization method based on the idea of negative sampling. Using this approach, we can preserve the high-dimensional structure of single-cell data in an embedded low-dimensional space that facilitates visual analyses of the data.

UR - http://www.scopus.com/inward/record.url?scp=85015587342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015587342&partnerID=8YFLogxK

U2 - 10.1142/9789813207813_0057

DO - 10.1142/9789813207813_0057

M3 - Conference article

C2 - 27897012

AN - SCOPUS:85015587342

VL - 0

SP - 623

EP - 634

JO - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

JF - Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing

SN - 2335-6936

IS - 212679

ER -