Skip to main content
. 2021 Mar 25;12:1873. doi: 10.1038/s41467-021-22008-3

Fig. 3. Latent representation visualization.

Fig. 3

Comparison of 2D visualization of embedded representations of ZINB model-based autoencoder (a, d, g, j), scDeepCluster (b, e, h, k) and scDCC with pairwise constraints (c, f, i, l). The same instances and constraints are visualized for each dataset (a–c, 10X PBMC; d–f Mouse bladder cells; g–i Worm neuron cells; j–l Human kidney cells). The red lines indicate cannot-link and blue lines indicate must-link. The axes are arbitrary units. Each point represents a cell. The distinct colors of the points represent the true labels, and colors are arbitrarily selected.