基于核函数相似性学习的单细胞 RNA-seq 数据可视化与分析。

Visualization and analysis of single-cell RNA-seq data by kernel-based similarity learning.

机构信息

Department of Computer Science, Stanford University, Stanford, California, USA.

Department of Electrical Engineering, Stanford University, Stanford, California, USA.

出版信息

Nat Methods. 2017 Apr;14(4):414-416. doi: 10.1038/nmeth.4207. Epub 2017 Mar 6.

DOI:10.1038/nmeth.4207

PMID:28263960

Abstract

We present single-cell interpretation via multikernel learning (SIMLR), an analytic framework and software which learns a similarity measure from single-cell RNA-seq data in order to perform dimension reduction, clustering and visualization. On seven published data sets, we benchmark SIMLR against state-of-the-art methods. We show that SIMLR is scalable and greatly enhances clustering performance while improving the visualization and interpretability of single-cell sequencing data.

摘要

我们提出了通过多核学习进行单细胞解析（SIMLR），这是一个分析框架和软件，它从单细胞 RNA-seq 数据中学习相似度度量，以进行降维、聚类和可视化。在七个已发表的数据集中，我们将 SIMLR 与最先进的方法进行了基准测试。我们表明，SIMLR 具有可扩展性，并大大提高了聚类性能，同时改善了单细胞测序数据的可视化和可解释性。