Skip to main content
Fig. 8 | Genome Biology

Fig. 8

From: BASS: multi-scale and multi-sample analysis enables accurate cell type clustering and spatial domain detection in spatial transcriptomic studies

Fig. 8

Detecting spatial domains in the DLPFC 10x Visium dataset. A A hematoxylin and eosin (H&E) staining image for the tissue section 151674. B Manually annotated spatial domain labels for the tissue section 151674. C Boxplots of ARI show the accuracy of different methods for spatial domain detection across 12 tissue sections. The compared methods include BASS that performs single tissue section analysis, BASSMult that performs multi-sample analysis that jointly fitted four tissue sections from each adult donor, the oracle version of HMRF, BayesSpace, and SpaGCN. D The identified spatial domains on the tissue section 151674 are shown for BASS, HMRF, BayesSpace, and SpaGCN. E The identified spatial domains on four tissue sections (151673, 151674, 151675, and 151676) were obtained with BASSMult

Back to article page

Genome Biology

ISSN: 1474-760X

Contact us