Anthony John Iafrate

Weakly supervised deep learning localizes focal tissue regions enriched for therapeutically relevant biology in routine histology, offering a scalable strategy to study therapeutic resistance across large patient populations.

The paper introduces molecular COUPLrs to systematically target protein complexes, identifying new glue classes and their interactions in cancer cell lines.

This study identifies low HLA/B2M class I expression in ACC tumors and shows it can be reversed by interferon-ψ or STING agonists, suggesting a path for immunotherapy.

The paper identifies ERBB2/HOXB13 co-amplification with BRCA1 loss as a unique subset of breast cancers associated with shorter progression-free survival.