Marta Rosa Sallese

CellBridge improves cell classification in pathology images by transferring molecular information, achieving higher accuracy on fine-grained labels.

TERRA is a foundation model for spatial transcriptomics that predicts tissue behavior under perturbation and identifies multi-scale biological insights across tissues.

MintFlow is a generative AI algorithm that predicts how tissue perturbations reprogram cell states in disease, revealing novel cell populations and therapeutic targets in three human conditions.

This paper develops a novel integration method for highly heterogeneous single-cell transcriptomic data and applies it to high-grade serous ovarian cancer to generate a reference atlas, revealing disease progression and treatment-related cell states.