pipette
ENEnglish

GenVinci reconstructs 3D molecular tissue scenes from histology to map senescence across aging and disease

X. Chen, C. Comiter, H. Huang, Y. Wu, Y.-L. Su, J. Zhou, F. Monticolo, M. Condouret, S. Sapantzi, J. Qi, X. Li, Y. Cao, Y. Zhou, K. Zhang, R. Tanaka, K. Todorova, S. Sol, J. Ziegler, D. Sakkas, C. Lian, S. Demehri, A. Mandinova, W. Min, J. C. Silverstein, H. Phatnani, Z. Dou, J. W. Kang, H. Yang, A. Regev, C. M. Stultz, NIH SenNet Consortium, P. T. C. So, J. Shu

PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avance

En palabras de los autores

Spatial omics has generated measurements at unprecedented scale, yet computational approaches remain largely confined to individual modalities and 2D representations. Here we assemble ImageOmicsNet-300M, a corpus of 300 million single-cell and spatial transcriptomic profiles, including 24.9 million H&E-predicted virtual spatial transcriptomics profiles, and 4,623 H&E sections. Of these H&E sections, we generated 1,782 from aging mouse organs and serially sectioned human skin spanning five decades, with matched spatial transcriptomics and snRNA-seq. Building on this resource, we develop GenVinci, a multimodal tissue foundation model that reconstructs 3D tissue scenes from routine 2D histology. GenVinci predicts spatial gene expression from H&E with zero-shot generalization and maps senescence-associated states across 85.8 million cells, revealing cell-type-specific patterns and disease-associated remodeling. Integration with human genetics implicates suprabasal keratinocytes in atopic dermatitis and keratinocyte carcinomas, linked to higher and lower p16 and p21 expression, respectively. These findings establish GenVinci as a framework mapping senescence in 3D across scales.

Resultado principalEl resumen no menciona limitaciones.

Apareció: jueves, 19 de noviembre. bioRxiv. Preprint, todavía sin revisión por pares.

DOI: 10.64898/2026.11.17.767412