Teijo S. Pellinen

This study identifies shared drug vulnerabilities in adult Wilms tumor through multi-omics and functional assays, showing pathway-level dependencies predict drug responses better than single-gene biomarkers.

This study uses deep learning and spatial data to show how tumor architecture and cell states co-evolve, influencing colorectal cancer outcomes.

The paper develops a self-supervised deep learning framework to analyze multiplexed cancer tissue microscopy images, stratifying patients into prognostically distinct groups with different survival outcomes.

The paper identifies FAP-expressing EMT-associated cancer cells in highly inflamed localized ccRCC as an aggressive, immunosuppressive subtype linked to poor prognosis and metastasis.