Antoine Koehl

PEINT simulates realistic protein evolution by modeling sequence changes over time, generating functional proteins that retain enzymatic activity.

This paper develops an engineered nanobody inhibitor to control opioid receptor function with subcellular precision and demonstrates its effectiveness in vivo.

This paper describes a nanobody antagonist of the μ-opioid receptor, revealing its structural basis and designing peptide analogues with antagonistic activity.

This paper introduces a cross-protein transfer learning framework that improves disease variant prediction using deep mutational scanning data from few proteins, achieving better specificity than existing models.

The paper shows that protein dynamics impose evolutionary constraints and that unsupervised language models can predict these constraints from sequence data.