The art of using t-SNE for single-cell transcriptomics

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,…

• DF
  Deutsche Forschungsgemeinschaft

  Awards: BE5601/4-1, 390727645, EXC 2064
• BF
  Bundesministerium für Bildung und Forschung

  Awards: FKZ 01GQ1601, FKZ 01GQ1601 and 01IS18039A, 01IS18039A, 01GQ1601
• NI
  National Institutes of Health

  Award: U19MH114830
• NI
  National Institute of Mental Health

  Award: U19MH114830