Fig. 10

scDesign2 guides the choice of sequencing depth in rare cell type detection. scDesign2 generates synthetic 10x Genomics data with twelve sequencing depths. Two rare cell type detection methods—FiRE and GiniClust2—are applied to each synthetic dataset to detect rare cell types. a t-SNE visualization of six synthetic datasets and identification results—true positive (TP), false positive (FP), false negative (FN), and true negative (TN) cells—of FiRE in each dataset. b t-SNE visualization of the same six synthetic datasets and identification results of GiniClust2 in each dataset. c Four identification accuracy measures by FiRE (precision, recall, F1-score, and AUPRC) vs. sequencing depth. d Three identification accuracy measures by GiniClust2 (precision, recall, and F1-score) vs. sequencing depth. In c and d, the results of the six sequencing depths in a and b are marked as dots and in the top, and the sequencing depth of the real dataset [83] is marked as vertical dashed lines