Sandrine Georgeon

This paper computationally designs light-responsive proteins that undergo conformational changes upon light activation, enabling precise control of biological functions.

A parallelized BindCraft pipeline generated 306,146 in silico binder candidates against 8,296 human proteins, each with sequence, predicted complex and confidence metrics, freely accessible online.

This paper introduces an AI-based framework for designing responsive protein oligomers that assemble in response to chemical or phosphorylation triggers, validated through experimental testing.

This study designs polymorph-specific binders for α-synuclein fibrils using a computational pipeline, demonstrating their utility as selective labeling agents without interfering with fibril dynamics.

This paper develops DROP-CARs, drug-regulated CAR-T cells that control cell-cell interactions using small-molecule switches, showing in vitro and in vivo functionality.

The paper identifies 4,500 targetable sites on the human surfaceome and introduces binder seeds for protein design, validated through experimental approaches and supported by a database.

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 paper introduces DiffTopo, a diffusion model for generating novel protein folds, and MirrorTopo, a pipeline to expand known fold space by mirroring native protein topologies.

This paper designs switchable cytokines that are activated by Venetoclax, showing tumor control comparable to native cytokines and enhancing therapeutic safety.

The paper develops caffeine-inducible systems for controlling gene expression in human cells using humanized protein components and demonstrates their use in inducible gene expression in T-cells.

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

This paper designs proteins that target neosurfaces from protein-ligand complexes using a deep learning approach, validated experimentally against three drug-bound protein complexes.

This paper designs chimeric influenza hemagglutinins that combine antigenic surfaces from different strains to elicit cross-group immunity and neutralize multiple strains.

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.

Hallucinating binders by backpropagating through AlphaFold2 weights gave, across 12 targets, binders in 10-100% of the designs tested per target, mostly at nanomolar affinity.

The paper predicts homo-oligomerization across four proteomes using AlphaFold2, finding that 50% of archaea, 45% of bacteria, and 20% of eukaryotes form homomers, with disease mutations enriched at interfaces.

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

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