Keith T. Flaherty

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.

This study identifies a novel CD8+ TIL subset that uses lymphotoxin and IFN pathways to kill cancer cells, linking LTB expression to clinical response in melanoma.

This study shows that targeting CD38 improves T cell function and restores response to immunotherapy in melanoma models.

DeepVul predicts gene essentiality and drug response using a multi-task transformer model trained on cancer transcriptome data, improving precision oncology by identifying treatment vulnerabilities.

This study identifies molecular mechanisms of resistance to immune checkpoint blockade in metastatic melanoma using proteogenomic and spatial analyses of tumor and immune microenvironment data.

The paper develops DNA- and RNA-based models combining immune and tumor features to predict outcomes of checkpoint inhibition in melanoma.