Davide Provasi

The paper uses computational and experimental methods to identify transition intermediates in the μ-opioid receptor-Gi protein complex that encode ligand efficacy.

This study identifies a novel allosteric site on the mu-opioid receptor using cryo-EM and MD simulations, revealing a lipid-sensitive mechanism for positive allosteric modulation.

BOLD-GPCRs predicts ligand bioactivity and mutational effects for class A GPCRs using a transformer-based deep learning framework, achieving robust performance across understudied receptors.

This paper identifies the structural basis for saxitoxin congener binding and neutralization by saxiphilins, showing how these proteins sequester toxins and reverse sodium channel blockage.

The paper develops fine-tuned deep learning models for predicting safer drugs targeting class A GPCRs by leveraging transfer learning and sequence-based analysis.

The paper investigates the agonist activity of tetracyclic antidepressants at 5-HT1eR and 5-HT1FR, revealing unique binding poses and receptor-specific mechanisms.

This study uses transfer learning with ligand- and structure-based descriptors to improve opioid bioactivity prediction across OR subtypes.

This study uses a generative deep learning framework to design new KOR antagonists, which are prioritized for synthesis and validated through experimental assays.

The paper characterizes the conformational changes in the Gαs protein upon GTP binding and identifies a novel regulator, MAGE D2, using a Bayesian integrative modeling approach.

This study identifies subtype-specific differences in transmembrane domain interactions that influence metabotropic glutamate receptor activation.