Extended Data Fig. 7: Clustering results for a human prostate cancer spatial transcriptomics dataset.
From: Resolving tissue complexity by multimodal spatial omics modeling with MISO
a, Clustering results from MISO, MUSE, and SpatialGlue. b, H&E-stained histology image of analyzed tissue section. c, RNA and image ICC distributions across all clusters and features for each method (n = 750 ICC values for each group). The mean ICC for each method and each modality is printed on the corresponding box plot. Test statistics and p-values were obtained using one-sided (<,>) or two-sided (≈) t-tests. d, Clone annotation of cancer spots. e, ARI between the clone annotation and the clustering results across all cancer spots for MISO (0.51), MUSE (0.44), and SpatialGlue (0.50). f, Weighted F1 score for localization of clusters to the annotated clones for MISO (0.61), MUSE (0.52), and SpatialGlue (0.59). To calculate F1 score for a given method, a cluster was assigned to a clone if more than half of the spots from that cluster overlapped with the clone annotation. F1 score was weighted by the number of spots belonging to each clone in the annotation. Box plots: center line, median; box limits, upper and lower quartiles; whiskers, 1.5x interquartile range; points, outliers.
