Gian Marco Visani

The paper shows that MULTI-evolve's multimutant predictions correlate closely with additive models, suggesting its performance is not due to epistasis learning.

IMMREP25 evaluates TCR:pMHC binding prediction for unseen peptides, showing improved performance with structural modeling but still below random guessing.

This paper introduces a computational method to predict TCR-pMHC interactions and design immunogenic peptides, achieving high accuracy and demonstrating success in T-cell activation.

The paper designs high specificity binders for peptide-MHC-I complexes using deep learning, achieving specific targeting of pMHCs and enabling T-cell activation.

HERMES predicts mutational effects on protein stability and binding affinity using structure-based models, showing strong performance and identifying antigen-stabilizing mutations for vaccine design.

This paper introduces H-(V)AE, an SO(3)-equivariant autoencoder in Fourier space for unsupervised learning and generation of 3D data, showing it can encode spherical images and predict protein-ligand binding affinity.