Fig. 7: sCellST discovers cell type morphological features.
From: sCellST predicts single-cell gene expression from H& E images
a Schematic of the approach. First, sCellST is trained on a set of marker genes obtained from prior knowledge. Then, a scoring function is used to compute cell type scores for each cell. b Distribution of scores after min-max scaling per score for several cell types, grouped by CellViT labels and represented as boxplots (center line: median; box limits: upper and lower quartiles; whiskers: 1.5 × interquartile range; points: outliers). The number of cells for CellViT labels is reported in Supplementary Material (SupTable.1) c Image galleries showing the highest-scoring images for each cell type.
