Fast Interpolation-based t-SNE for Improved Visualization of Single-Cell RNA-Seq Data

By George C. Linderman, M. Rachh, Jeremy G. Hoskins, Stefan Steinerberger, Yuval Kluger. 2017

507 citations recorded by the source corpus.

t-distributed stochastic neighbor embedding (t-SNE) is widely used for visualizing single-cell RNA-sequencing (scRNA-seq) data, but it scales poorly to large datasets. We dramatically accelerate t-SNE, obviating the need for data downsampling, and hence allowing visualization of rare cell populations. Furthermore, we implement a heatmap-style visualization for scRNA-seq based on one-dimensional t-SNE for simultaneously visualizing the expression patterns of thousands of genes. Software is available at https://github.com/KlugerLab/FIt-SNE and https://github.com/KlugerLab/t-SNE-Heatmaps. FIt-SNE, a sped-up version of t-SNE, enables visualization of rare cell types in large datasets by obviating the need for downsampling. One-dimensional t-SNE heatmaps allow simultaneous visualization of expression patterns from thousands of genes.

Subfields: Molecular Biology, Representation & Self-Supervised Learning, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Representation & Self-Supervised Learning

In Computational Biology & Bioinformatics

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, methodology): “The most famous among them are BH t-SNE (van der Maaten, 2014) and FIt-SNE (Linderman et al., 2019).”
Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization (2020, methodology): “Different implementations of t-SNE, such as BH-SNE (van der Maaten, 2014), viSNE (Amir et al., 2013), FIt-SNE (Linderman et al., 2017; Linderman et al., 2019), and opt-SNE (Belkina et al., 2019), have further improved t-SNE so it could converge faster and scale better to larger datasets, while keepi”
A high-bias, low-variance introduction to Machine Learning for physicists (2018, unknown): “More recently extremely efficient tSNE implementation making use of fast Fourier transforms for kernel summations in (136) have been made available on https://github.com/ KlugerLab/FIt-SNE (Linderman et al., 2017).”
Comparison Between UMAP and t-SNE for Multiplex-Immunofluorescence Derived Single-Cell Data from Tissue Sections (2019, background): “Among the 119 biopsies included and with a median follow-up of 73 months (4-160), 5-year overall survival was 39.”
Embedding to reference t-SNE space addresses batch effects in single-cell classification (2019, background): “This approximation enables the visualization of massive data sets, possibly containing millions of data points [16].”
Automated Optimal Parameters for T-Distributed Stochastic Neighbor Embedding Improve Visualization and Allow Analysis of Large Datasets (2018, methodology): “FIt-SNE (Fast Fourier Transform-accelerated Interpolation-based t-SNE 20 plugin for FlowJo was used as indicated.”
A Unifying Perspective on Neighbor Embeddings along the Attraction-Repulsion Spectrum (2020, methodology): “Efficient implementations of t-SNE suitable for large sample sizes n [35, 19] explicitly truncate the affinities and use the k-nearest-neighbor (kNN) graph of the data with k n as the input.”
NOMAD Projection (2025, unknown): “In this map, PubMed documents are vectorized with a custom BERT model, and then reduced to 2 dimensions using OpenTSNE [19], a multi-core CPU implementation of FIt-SNE [12].”