Tyler J. Aprati

The paper expands P-NET, a deep learning framework that uses biological pathways for genomic and transcriptomic predictions, showing competitive performance and interpretability.

The paper identifies melanoma differentiation and immune exhaustion as predictors of tumor progression and therapy response in in-transit melanoma patients through multiomic profiling.

This study identifies distinct metastatic phenotypes in cutaneous melanoma using clinico-genomic data and machine learning, linking specific mutations and clinical factors to organ-specific metastasis.

The paper identifies HIF-2α as a therapeutic target for immune-infiltrated melanomas through stratified analysis of clinical and molecular data.