Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Integration of scRNA-seq data by disentangled representation learning with condition domain adaptation

Fig. 2

The integrated comparation of the simulated dataset. A UMAP plots of Raw and the cell embeddings produced by scDisco, scVI, Harmony, and Seurat. Each point represents a cell, and each column represents a method, while each row corresponds to the UMAP plot with coloring based on true cell types, batch IDs, and condition IDs. B–E Boxplots of ARI, NMI, BASW, and ASW values of each method by applying the nine integration methods to randomly selected subsamples of the complete simulated data

Back to article page