Unknown

Dataset Information

0

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.

SUBMITTER: Belkina AC 

PROVIDER: S-EPMC6882880 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

altmetric image

Publications

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

Belkina Anna C AC   Ciccolella Christopher O CO   Anno Rina R   Halpert Richard R   Spidlen Josef J   Snyder-Cappione Jennifer E JE  

Nature communications 20191128 1


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  ...[more]

Similar Datasets

| S-EPMC5890814 | biostudies-literature
| S-EPMC7344294 | biostudies-literature
| S-EPMC6247646 | biostudies-literature
| S-EPMC6679899 | biostudies-literature
| S-EPMC6175173 | biostudies-literature
| S-EPMC6110518 | biostudies-literature
| S-EPMC6562776 | biostudies-literature
| S-EPMC5838640 | biostudies-literature
2015-06-26 | E-GEOD-69184 | biostudies-arrayexpress
| S-EPMC5927603 | biostudies-literature