Fig. 6
From: Evaluation of deep learning-based feature selection for single-cell RNA sequencing data analysis
Computational time of feature selection methods. a Running time of each feature selection method on datasets sampled from Tabula Muris with the number of cell types increases from 5 to 20 with an increment of 5 and the number of cells in each cell type held as 200. b Running time of each feature selection method on datasets with the number of cells increases from 50 to 250 with an increment of 50 and the number of cell types held as 20. Deep learning-based methods were applied with GPU and CPU configurations, respectively