English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Motivation: Single cell RNA sequencing (scRNA-seq) data makes studying thedevelopment of cells possible at unparalleled resolution. Given that manycellular differentiation processes are hierarchical, their scRNA-seq data isexpected to be approximately tree-shaped in gene expression space. Inferenceand representation of this tree-structure in two dimensions is highly desirablefor biological interpretation and exploratory analysis.Results:Our twocontributions are an approach for identifying a meaningful tree structure fromhigh-dimensional scRNA-seq data, and a visualization method respecting thetree-structure. We extract the tree structure by means of a density basedminimum spanning tree on a vector quantization of the data and show that itcaptures biological information well. We then introduce DTAE, a tree-biasedautoencoder that emphasizes the tree structure of the data in low dimensionalspace. We compare to other dimension reduction methods and demonstrate thesuccess of our method both qualitatively and quantitatively on real and toydata.Availability: Our implementation relying on PyTorch and Higra is availableat https://github.com/hci-unihd/DTAE.

Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder