Fig. 3
From: Evaluation of deep learning-based feature selection for single-cell RNA sequencing data analysis
Impact of number of cells on cell type classification using the union of top-10 cell type marker genes selected by each feature selection method. a Mean F1 scores of KNN classification of 10 or 20 cell types (sampled from Tabula Muris atlas) each with number of cells set as 50, 100, 150, 200, and 250. b Coefficients of slopes from least squares fitted lines to F1 scores in a across the number of cells. c For numbers of cells set as 50, 100, 150, 200, and 250 and number of cell types fixed at 20, balloon plots summarizing the ranks of median F1 scores from KNN on datasets sampled from Tabula Muris and Tabula Sapiens atlases. The size of the balloon represents the rank of the method, the larger the better its performance