Fig. 5: scBalance shows scalability by revealing immune landscape of BALF cells.

a annotation performances compared with different methods on Cardiac Atlas (~50 K cells) and COVID Atlas (~1.5 M cells). b Running time comparison between scBalance and traditional machine-learning algorithms. Y axis shows running time in second. c UMAP shows the annotation result of scBalance. The reference dataset is COVID Atlas17 and the query dataset is BALF data32. d Dotplot shows the cell subtype distribution in the BALF dataset.