KAUST Research Conference
Computational Advances in Structural Biology
May 1 - 3, 2023 Auditorium between building 4 & 5
Abstract:
The continuous evolution of artificial intelligence (AI) algorithms has been affecting multiple scientific and industrial fields, and drug discovery (DD) and development are not an exception. We present a case study of how deep learning-based (DL) approaches can be utilized at different stages of a real-life project with a particular focus on applying structural models predicted with AlphaFold (AF).
Despite outperforming other homology modeling techniques in the CASP14 challenge, our analysis of multiple protein models generated with AF revealed that this approach should be used cautiously for DD purposes. From this perspective, an accurately reconstructed binding pocket is of the highest importance. In order to address the problem of inaccurately, or even mistakenly, generated backbone and side chain conformations, we developed a graph neural network-based (GNN) approach capable of finding inconsistencies in the ATP-binding sites of kinase structural models and then adjusting them accordingly.