Fig. 3: Imputation results comparison for Xenium-based (known as Xenium-breast) and seqFISH-based (known as seqFISH-embryo) datasets.

a Cell-type distribution by spatial location of Xenium-breast dataset (sample size (n) = 160,000). b Cell-type distribution by the spatial location of seqFISH-embryo dataset (sample size (n) = 60,000). c Metrics information of different imputation methods for Xenium-breast dataset (sample size (n) = 10 for each group; center point, median; box limits, upper and lower quartiles; whiskers, up to 1.5 × interquartile range; points, outliers). d Metrics information of different imputation methods for seqFISH dataset (sample size (n) = 10 for each group; center point, median; box limits, upper and lower quartiles; whiskers, up to 1.5 × interquartile range; points, outliers). e Examples of reliable imputed genes produced by VISTA for Xenium-breast dataset. f Examples of reliable imputed genes produced by VISTA for seqFISH-embryo dataset.