Tian Tian; Cheng Zhong; Xiang Lin; Zhi Wei; Hakon Hakonarson

Complex hierarchical structures in single-cell genomics data unveiled by deep hyperbolic manifold learning

(Downloading may take up to 30 seconds. If the slide opens in your browser, select File -> Save As to save it.)

Click on image to view larger version.

Figure 5.

Embeddings of scDHMap on three real scRNA-seq data sets. (A) Embedding quality metrics of methods on real scRNA-seq data sets. (B) scDHMap embedding of the Paul cells. Colors represent cell types. (C) scDHMap embedding of the colon epithelial cells. Colors represent cell types. Arrowed lines indicate the suggested trajectory paths (B,C). (D,E) scDHMap embedding of the C. elegans embryonic cells. Colors represent cell types (D), and colors represent embryonic time bins (E).