Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks.

Generalizable and Scalable Visualization of Single-Cell Data Using Neural Networks.
复制标题

使用神经网络对单细胞数据的可概括和可扩展可视化。

DOI:
10.1016/j.cels.2018.05.017
复制
发表时间:
2018-08-22
期刊:
影响因子:
9.3
通讯作者:
Peng J
Peng J
中科院分区:
生物学1区
文献类型:
--
作者:
Cho H;Berger B;Peng J

文献摘要

参考文献

被引文献

相似文献

可视化算法是解释单细胞数据的基本工具。然而,标准方法,如t随机邻居嵌入(t-SNE),不能扩展到具有数百万单元格的数据集,并且所产生的可视化结果不能推广到分析新数据集。在这里,我们介绍net-SNE,这是一种通用的可视化方法,它训练神经网络学习从高维单细胞基因表达谱到低维可视化的映射函数。我们在13个不同的数据集上对net-SNE进行了测试,结果表明它的可视化质量和聚类精度与t-SNE相当。此外,我们表明,net-SNE学习的映射函数可以准确地定位以前未见过的数据集中的整个新亚型细胞,并且还可以用于将可视化130万个细胞的运行时间减少36倍(从1.5天减少到1小时)。我们的工作为从现有数据集启动单细胞分析提供了一个框架。研究人员正在将单细胞RNA测序应用于越来越多的不同组织和生物体中的大量细胞。我们介绍了一个名为net-SNE的数据可视化工具,它可以训练神经网络在2D或3D中嵌入单个细胞。与以前的方法不同,我们的方法允许将新单元映射到现有的可视化中,从而促进不同数据集之间的知识转移。我们的方法还大大减少了可视化包含数百万单元格的大型数据集的运行时间。
Visualization algorithms are fundamental tools for interpreting single-cell data. However, standard methods, such as t-stochastic neighbor embedding (t-SNE), are not scalable to datasets with millions of cells and the resulting visualizations cannot be generalized to analyze new datasets. Here we introduce net-SNE, a generalizable visualization approach that trains a neural network to learn a mapping function from high-dimensional single-cell gene-expression profiles to a low-dimensional visualization. We benchmark net-SNE on 13 different datasets, and show that it achieves visualization quality and clustering accuracy comparable with t-SNE. Additionally we show that the mapping function learned by net-SNE can accurately position entire new subtypes of cells from previously unseen datasets and can also be used to reduce the runtime of visualizing 1.3 million cells by 36-fold (from 1.5 days to an hour). Our work provides a framework for bootstrapping single-cell analysis from existing datasets. Researchers are applying single-cell RNA sequencing to increasingly large numbers of cells in diverse tissues and organisms. We introduce a data visualization tool, named net-SNE, which trains a neural network to embed single cells in 2D or 3D. Unlike previous approaches, our method allows new cells to be mapped onto existing visualizations, facilitating knowledge transfer across different datasets. Our method also vastly reduces the runtime of visualizing large datasets containing millions of cells.
DOI: 10.1016/j.cell.2016.01.047
发表时间: 2016-03-24
期刊: Cell
影响因子: 64.5
作者:
Goolam M;Scialdone A;Graham SJL;Macaulay IC;Jedrusik A;Hupalowska A;Voet T;Marioni JC;Zernicka-Goetz M
通讯作者: Zernicka-Goetz M
DOI: 10.1126/science.1247651
发表时间: 2014-02-14
期刊: Science (New York, N.Y.)
影响因子: --
作者:
Jaitin DA;Kenigsberg E;Keren-Shaul H;Elefant N;Paul F;Zaretsky I;Mildner A;Cohen N;Jung S;Tanay A;Amit I
通讯作者: Amit I
DOI: 10.1038/nprot.2016.066
发表时间: 2016-07-01
期刊: NATURE PROTOCOLS
影响因子: 14.8
作者:
Anchang, Benedict;Hart, Tom D. P.;Plevritis, Sylvia K.
通讯作者: Plevritis, Sylvia K.
DOI: 10.2307/2284239
发表时间: 1971-01-01
影响因子: 3.7
作者:
RAND, WM
通讯作者: RAND, WM
DOI: 10.1038/nmeth.4236
发表时间: 2017-05-01
期刊: NATURE METHODS
影响因子: 48
作者:
Kiselev, Vladimir Yu;Kirschner, Kristina;Hemberg, Martin
通讯作者: Hemberg, Martin