Stéphane Rosset

This paper designs small single domain proteins that present three distinct viral epitopes using deep learning, showing improved immunogenicity compared to single-epitope designs.

This study designs stem-epitope mimetics using computational methods to elicit broadly reactive antibodies against influenza viruses.

The paper develops a deep mutational scanning pipeline for anti-CRISPR proteins in E. coli, revealing their mutational tolerance and redundancy, and validates findings in mammalian cells.

This paper introduces a deep learning framework called Genesis to learn protein structural patterns and demonstrates its ability to design novel protein folds with high protease resistance.

This paper inverts the AlphaFold2 network to perform de novo protein design, showing that while the method generates viable sequences with correct folds, it requires post-design optimization to achieve optimal surface properties.

This study designs soluble analogues of integral membrane proteins using deep learning, achieving high thermal stability and functional accuracy.

This paper introduces a framework for de novo protein design that automatically generates structural templates and evaluates their stability through experimental characterization.

RosettaSurf is a computational design method that optimizes protein surfaces for functional sites, showing success in generating epitope mimics through surface-centric design.

The paper designs improved anti-CRISPR proteins with enhanced inhibition potency and expanded specificity through structure-based engineering.

This paper introduces a computational framework for designing functional proteins by integrating folding and sequence design, showing that functional motifs can be embedded without requiring the global energy minimum.