scGSL tunes cell-cell graphs with GNN graph structure learning and pairwise alignment transfer, improving cell type annotation over 10 baselines and yielding graphs proposed to reflect tumor microenvironment interactions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.GN 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Structure Learning for Tumor Microenvironment with Cell Type Annotation from non-spatial scRNA-seq data
scGSL tunes cell-cell graphs with GNN graph structure learning and pairwise alignment transfer, improving cell type annotation over 10 baselines and yielding graphs proposed to reflect tumor microenvironment interactions.