Fig. 2
From: SAIC: an iterative clustering approach for analysis of single cell RNA-seq data
SAIC performance on the simulated dataset. a Distribution of DB index values for each initial center using SAIC algorithm on the simulated data set. Boxplot was generated using R package “ggplot”. Each box represents a range of p values for the specific initial center parameter (K). Each dot represents the actual DB index value of each p-value (P). The middle line within each box represents the median value. Whiskers stop at lower and upper adjacent values. b Two-dimensional plot (t-SNE) of the 100-cell simulated data. The 619 signature genes were selected using SAIC algorithm. Clusters are colored by predefined groups