Skip to main content
. 2020 Dec 18;6(51):eaba9031. doi: 10.1126/sciadv.aba9031

Fig. 4. Comparison of scFAN to seven other count matrix–based methods or open chromatin accessibility–based methods applied to the PBMC dataset.

Fig. 4

(A) t-SNEs of all seven different open chromatin–based or peak-cell count matrix–based clustering methods. (B) Comparison of seven different clustering metrics of each method. ARI, NMI, and v-measure score were used to measure each method. The higher the score, the better the clustering performance. (C) t-SNE plot on the PBMC dataset, colored by CEBPB activity score; CEBPB is more active in GMP and monocyte cells as their colors are more red than other cells.