Automated optimized parameters for T-distributed stochastic neighbor embedding improve visualization and analysis of large datasets

Abstract

Accurate and comprehensive extraction of information from high-dimensional single cell datasets necessitates faithful visualizations to assess biological populations. A state-of-the-art algorithm for non-linear dimension reduction, t-SNE, requires multiple heuristics and fails to produce clear representations of datasets when millions of cells are projected. We develop opt-SNE, an automated toolkit for t-SNE parameter selection that utilizes Kullback-Leibler divergence evaluation in real time to tailor the early exaggeration and overall number of gradient descent iterations in a dataset-specific manner. The precise calibration of early exaggeration together with opt-SNE adjustment of gradient descent learning rate dramatically improves computation time and enables high-quality visualization of large cytometry and transcriptomics datasets, overcoming limitations of analysis tools with hard-coded parameters that often produce poorly resolved or misleading maps of fluorescent and mass cytometry data. In summary, opt-SNE enables superior data resolution in t-SNE space and thereby more accurate data interpretation.

Generalized EmbedSOM on quadtree-structured self-organizing maps

“…The result in Figure 3 allows easy observation of both the ILC compartment and the CD4 + T cell subset, corresponding to the observations produced by second-level HSNE [12, Figures 3 and 5]. Additionally, the embedding shows presence of many clusters from lower levels of the hierarchical dissection: 13 : (a) CD4 + CD28 -CCR7 + , (b) CD4 + CD28 -CCR7 -CD56 -, (c) CD4 + CD28 -CCR7 -CD56 + , and (d) CD7 + CD3 -CD127 -CD45RA -CD56 partial . Top right: Expressions of separate markers used for the identification.…”

“…3 rd levels of dissection [12, Figures 5b and 3c]. Recently, Belkina et al 13 showed that the opt-SNE algorithm can additionally identify CD4 + CD28 -CCR7 + CD56rare cell type, which is also clearly separated by the GQTSOM-based embedding, using much less computational resources than optSNE.…”

Expression of Inhibitory Receptors on T and NK Cells Defines Immunological Phenotypes of HCV Patients with Advanced Liver Fibrosis

“…In addition, we included GAL-9 expression for the co-expression analysis. The t-SNE analysis was employed to dimensionally reduce the expression data of cell surface markers, inhibitory receptors, and GAL-9 from all 30 patients with HCV and to visualize expression patterns in two dimensions ( Belkina et al., 2019 ). t-SNE analysis of all 30 patients (F0-F4) revealed several clusters, and separating the plot based on the fibrosis scores showed the distribution of cell densities ( Figure 3 A).…”

Subcutaneous nanotherapy repurposes the immunosuppressive mechanism of rapamycin to enhance allogeneic islet graft viability

“…Next, samples from mice that underwent the same treatment and same cell population were concatenated. The tSNE plugin was run on concatenated samples using the Auto opt-SNE learning configuration with 3000 iterations, a perplexity of 50 and a learning rate equivalent to 7% of the number of events 60 . The KNN algorithm was set to exact (vantage point tree) and the Barnes-Hut gradient algorithm was employed.…”