Fred Hutchinson Cancer Center

Liquid-biopsy deep learning model that infers transcriptome-wide tumor gene expression from standard-depth cell-free DNA whole-genome sequencing.

Whole-slide pathology embedding framework that ranks tiles, keeps only the 25 most informative, and encodes a slide in 2.27 seconds.

Virtual multiplex immunofluorescence staining from H&E histopathology, imputing the expression and spatial localization of 50 protein biomarkers.

Energy-based diffusion model over protein loop conformations that scores how mutations in peptides and CDR3 loops shift TCR-pMHC binding affinity.

Structure-based mutational effect prediction from local atomic environments, scoring how substitutions change protein stability and binding affinity.