Artificial Intelligence: A New Tool for Structure-Based G Protein-Coupled Receptor Drug Discovery
Biomolecules · 17.03.2025 · 15 (3) · 423
DOI: 10.3390/biom15030423 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Biomolecules, online erschienen am 17.03.2025. Verfasst von Jason Chung und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Molecular Pathobiology, New York University College of Dentistry, New York, NY 10010, USA. Hauptthemen laut MEDLINE: Drug Discovery, Receptors, G-Protein-Coupled, Artificial Intelligence. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 114 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIGMS NIH HHS, NIH HHS.
Abstract (Originalsprache)
Understanding protein structures can facilitate the development of therapeutic drugs. Traditionally, protein structures have been determined through experimental approaches such as X-ray crystallography, NMR spectroscopy, and cryo-electron microscopy. While these methods are effective and are considered the gold standard, they are very resource-intensive and time-consuming, ultimately limiting their scalability. However, with recent developments in computational biology and artificial intelligence (AI), the field of protein prediction has been revolutionized. Innovations like AlphaFold and RoseTTAFold enable protein structure predictions to be made directly from amino acid sequences with remarkable speed and accuracy. Despite the enormous enthusiasm associated with these newly developed AI-approaches, their true potential in structure-based drug discovery remains uncertain. In fact, although these algorithms generally predict overall protein structures well, essential details for computational ligand docking, such as the exact location of amino acid side chains within the binding pocket, are not predicted with the necessary accuracy. Additionally, docking methodologies are considered more as a hypothesis generator rather than a precise predictor of ligand–target interactions, and thus, usually identify many false-positive hits among only a few correctly predicted interactions. In this paper, we are reviewing the latest development in this cutting-edge field with emphasis on the GPCR target class to assess the potential role of AI approaches in structure-based drug discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Molecular Pathobiology, New York University College of Dentistry, New York, NY 10010, USA.
- NYU Pain Research Center, New York University College of Dentistry, New York, NY 10010, USA.
ORCID-Profile: Hyunggu Hahn, Emmanuel Flores-Espinoza
Förderung
- NCI NIH HHS
- NIGMS NIH HHS
- NIH HHS
- NIH/NIGMS
- NIH/NCI
Zitieren
APA
Chung, J., Hahn, H., Flores-Espinoza, E., & Thomsen, A. R. B. (2025). Artificial Intelligence: A New Tool for Structure-Based G Protein-Coupled Receptor Drug Discovery. Biomolecules, 15(3), 423. https://doi.org/10.3390/biom15030423
Vancouver
Chung J, Hahn H, Flores-Espinoza E, Thomsen ARB. Artificial Intelligence: A New Tool for Structure-Based G Protein-Coupled Receptor Drug Discovery. Biomolecules. 2025;15(3):423. doi:10.3390/biom15030423
BibTeX
@article{Chung2025,
author = {Chung, Jason and Hahn, Hyunggu and Flores-Espinoza, Emmanuel and Thomsen, Alex R B},
title = {Artificial Intelligence: A New Tool for Structure-Based G Protein-Coupled Receptor Drug Discovery},
journal = {Biomolecules},
year = {2025},
volume = {15},
number = {3},
pages = {423},
doi = {10.3390/biom15030423}
}
EUVIMED