RT Journal Article
SR Electronic
T1 The art of using t-SNE for single-cell transcriptomics
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 453449
DO 10.1101/453449
A1 Dmitry Kobak
A1 Philipp Berens
YR 2019
UL http://biorxiv.org/content/early/2019/05/20/453449.abstract
AB Single-cell transcriptomics yields ever growing data sets containing RNA expression levels for thousands of genes from up to millions of cells. Common data analysis pipelines include a dimensionality reduction step for visualising the data in two dimensions, most frequently performed using t-distributed stochastic neighbour embedding (t-SNE). It excels at revealing local structure in high-dimensional data, but naive applications often suffer from severe shortcomings, e.g. the global structure of the data is not represented accurately. Here we describe how to circumvent such pitfalls, and develop a protocol for creating more faithful t-SNE visualisations. It includes PCA initialisation, a high learning rate, and multi-scale similarity kernels; for very large data sets, we additionally use exaggeration and downsampling-based initialisation. We use published single-cell RNA-seq data sets to demonstrate that this protocol yields superior results compared to the naive application of t-SNE.