A multi-semantic graph learning framework with a min-cut loss improves spatial clustering, batch integration, and whole-slide scalability in spatial transcriptomics, reporting 10-20% gains over DeepST, GraphST, and IRIS.
Transcriptome-scale super-resolved imaging in tissues by rna seqfish+
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
q-bio.GN 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SemanticST: Spatially Informed Semantic Graph Learning for Clustering, Integration, and Scalable Analysis of Spatial Transcriptomics
A multi-semantic graph learning framework with a min-cut loss improves spatial clustering, batch integration, and whole-slide scalability in spatial transcriptomics, reporting 10-20% gains over DeepST, GraphST, and IRIS.