Application of graph neural networks to ligand–protein affinity prediction: impact of structural environment and weak interactions in SARS-CoV-2 Mpro

Identifier:  TFG:9368

Handle: https://hdl.handle.net/20.500.11797/TFG9368

Authors:  Dastis Fonoll, Arnau

Abstract:
SARS-CoV-2, the cause of the global COVID-19 pandemic, has highlighted the urgent need to develop new computational strategies for the identification of antiviral drugs. This work explores the use of graph neural networks (GNNs) to predict the affinity between ligands and the SARS-CoV-2 Mpro protein, a key target for the development of antiviral drugs. Based on 386 experimental structures, models have been generated that incorporate information from the environment and weak interactions, observing an improvement in predictive performance depending on these.