Fig. 5: SMART efficiently integrates large-scale multi-omics datasets.
From: SMART: spatial multi-omic aggregation using graph neural networks and metric learning
a Clustering results of the P22 mouse brain section using PCA features from RNA or H3K27me3, compared with results from different spatial multi-omics integration methods. b Runtime and peak memory usage of various methods on the P22 mouse brain dataset. c Clustering results of the mouse spleen at multiple spatial resolutions using PCA features of RNA, ADT, and SMART’s integrated embedding. d GPU memory usage of different methods across spatial resolutions in the mouse spleen dataset. e Runtime comparison of different methods across spatial resolutions in the mouse spleen dataset. Source data are provided as a Source Data file.
