Cristian Tomasetti

This paper uses AlphaFold 3 to predict T cell receptor antigen specificity from sequence, achieving high accuracy on unseen epitopes.

The paper introduces MHCIIFold-GNN, a method combining structural modeling and graph neural networks to predict CD4 T cell epitopes, achieving state-of-the-art performance.

The paper functionally characterizes all CDKN2A missense variants and evaluates in silico pathogenicity models, finding 17.7% are deleterious and models have moderate accuracy.

The paper predicts cancer cell-of-origin from DNA sequences by matching mutational landscapes to chromatin modification patterns in normal tissues.