Fig. 6: Comparison of the Performance of scPML and Three Existing Methods.
From: scPML: pathway-based multi-view learning for cell type annotation from single-cell RNA-seq data
a Boxplots show the accuracy of classifying known cells and Macro F1 score of binary classification with known and unknown cell labels for scPML, Seurat, scGCN, and scmap. In the box plot, the middle line represents the median, the lower and upper hinges represent the first and third quartiles, and the whiskers extend to the range of 1.5 times the interquartile range (IQR). b Heatmap illustrates the correlation between true labels and predicted results for scPML, Seurat, scGCN, and scmap. c Violinplots display the confidence scores provided by scPML and scGCN for GSE72056-GSE103322 data pair, where the white dot represents the median, the left and right hinges in the black area represent the first and third quartiles, the whiskers extend to the range of 1.5 times the interquartile range (IQR), the shape displays the distribution of data and the width of the plot at a given point represents the estimated density of the data at that value. Overall, scPML demonstrates superior performance in single-cell RNA sequencing analysis compared to the other methods evaluated in this study.
