Fig. 3From: A deep adversarial variational autoencoder model for dimensionality reduction in single-cell RNA sequencing analysis2-D visualization for the Zheng-73 k dataset. The Zheng-73 k dataset was reduced to 2-D by using (a) DR-A, (b) PCA, (c) ZIFA, (d) scVI, (e) SAUCIE, (f) t-SNE, (g) UMAP, and (h) DR-A combined with t-SNE methods. Each point in the 2-D plot represents a cell in the testing set of the Zheng-73 k dataset, which have 8 distinct cell types. There was an 80% training and 20% testing split from the original dataset in these experimentsBack to article page