The abstract is read at the publisher; the summary is JClub's.
GenVinci reconstructs 3D tissue scenes from routine 2D H&E and predicts spatial gene expression, mapping senescence-associated states across 85.8 million cells with cell-type-specific patterns.
- Why it matters: Spatial omics is high-resolution but computational tools often stay within single modalities and 2D views, limiting 3D mapping of aging and disease-linked senescence.
- What they did: The team built ImageOmicsNet-300M (300M profiles; 24.9M H&E-predicted virtual spatial transcriptomics; 4,623 H&E sections) and trained GenVinci to infer spatial gene expression from H&E, using matched mouse organ and human skin data plus snRNA-seq.
- The result: In human genetics integration, suprabasal keratinocytes are implicated in atopic dermatitis and keratinocyte carcinomas, linked to higher and lower p16 and p21 expression, respectively.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.