Yongbing Zhang

MorphoProt predicts spatial protein abundance using RNA expression, multiscale histology, and tissue neighborhoods, outperforming baselines in human and mouse tissues.

HCCExplorer translates H&E slides into virtual multiplex immunofluorescence to identify prognostic spatial immune features in hepatocellular carcinoma.

This paper introduces 3D-SpecDIM, a technique that captures both 3D positional and spectral dynamics of biomolecules, demonstrating its application in mitophagy and cellular blebbing.

LETSmix improves cell-type deconvolution in spatial transcriptomics by integrating spatial context and domain adaptation, achieving better accuracy than existing methods.

STEP enhances spatial transcriptome data to single-cell resolution and infers transcriptome-wide expression, enabling precise cell type prediction and intercellular communication analysis.