Skip to main content
. 2019 Sep 30;47(22):e143. doi: 10.1093/nar/gkz826

Figure 3.

Figure 3.

Benchmarking of LCA against Seurat-CCA, Seurat-RegressOut, MNN-SC3, and SC3-scmap on simulated datasets with two equal-size batches. (A) Clustering accuracy by LCA, Seurat-CCA, Seurat-RegressOut, MNN-SC3 and SC3-scmap was compared using NMI on 1000 simulated cells by Splatter: the probability of differential expression ranges from 0.05 to 0.2, and the probability of minor group ranges from 0.01 to 0.5. Each combination of simulation parameters contained 100 randomly generated samples. (B) Clustering accuracy on 4000 simulated cells.