Yiheng Mao

Spatial-DC improves spatial proteomics deconvolution by using deep learning to infer cell-type composition and reconstruct proteomic profiles from low-resolution data.

The paper introduces SCPro, a multimodal spatial proteomics method, to profile pancreatic tumor heterogeneity by integrating imaging, flow cytometry, and protein aggregation capture, revealing spatial proteome variations and a novel regulatory T cell subtype.

This study creates a spatial proteomic atlas of lung tissues from COVID-19 victims, identifying protein dysregulations and markers of pathological changes.