Fig. 3
From: Inference of single-cell network using mutual information for scRNA-seq data analysis
t-SNE plots for visualizing the k-means clustering performances of SINUM DMs, CSN DMs, and GEMs on Chu-type, Chu-time, and Yan datasets. For visualization, we applied t-distributed stochastic neighbor embedding (t-SNE) to reduce the dimensions to two after reducing by principal component analysis (PCA) to 20 dimensions. The x-axis and y-axis in each plot represent t-SNE-1 and t-SNE-2, respectively. For each dataset, distinct cell types are marked by different colors. Adjusted rand index (ARI) and F-measure index (FMI) were employed in comparison of k-means clustering performances since the cell type labels of each dataset had been known