Josua Stadelmaier

This study identifies genomic features, particularly copy-number alterations, that predict metastatic progression in melanoma and defines a six-gene signature associated with relapse.

This paper introduces Immunotype, a deep learning model that directly types HLA alleles from immunopeptidomics data with 87.2% accuracy.

This study shows resistance training causes time-dependent gut microbiome changes, especially in those with greater strength gains, enriching health-associated taxa like Faecalibacterium and Roseburia hominis.

The paper introduces t2pmhc, a structure-informed graph neural network for predicting TCR-pMHC binding, showing improved generalization to unseen peptides compared to existing methods.