.png){kind=icon}
.png){kind=icon}
Return
Digital decoding tissue microenvironment heterogeneity from spatial proteomics through graph-enhanced transfer learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cels.2026.101612.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A transfer learning-based framework is designed for spatial proteomics deconvolution • Superior performance in estimating the cell-type composition is demonstrated • The refined cell-type maps are generated from diverse spatial proteomics platforms • Cell-type-specific interactions in self-collected pancreatic cancer data are identified
Keywords:
transfer learning
spatial proteomics
cell-type composition
tissue microenvironment
graph-enhanced learning
Journal
IF:
7.7
Papers:
1.4K
Citations:
1.0W