EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Point Cloud Graph Neural Network for Protein–Ligand Binding Site Prediction

Yanpeng Zhao iD, Song He iD, Yuting Xing, Mengfan Li iD, Yang Cao iD, Xuanze Wang, Dongsheng Zhao, Xiaochen Bo

International Journal of Molecular Sciences · 2024

DOI: 10.3390/ijms25179280 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Yanpeng Zhao und 7 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Military Medical Sciences, Beijing 100850, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Proteins. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting protein–ligand binding sites is an integral part of structural biology and drug design. A comprehensive understanding of these binding sites is essential for advancing drug innovation, elucidating mechanisms of biological function, and exploring the nature of disease. However, accurately identifying protein–ligand binding sites remains a challenging task. To address this, we propose PGpocket, a geometric deep learning-based framework to improve protein–ligand binding site prediction. Initially, the protein surface is converted into a point cloud, and then the geometric and chemical properties of each point are calculated. Subsequently, the point cloud graph is constructed based on the inter-point distances, and the point cloud graph neural network (GNN) is applied to extract and analyze the protein surface information to predict potential binding sites. PGpocket is trained on the scPDB dataset, and its performance is verified on two independent test sets, Coach420 and HOLO4K. The results show that PGpocket achieves a 58% success rate on the Coach420 dataset and a 56% success rate on the HOLO4K dataset. These results surpass competing algorithms, demonstrating PGpocket’s advancement and practicality for protein–ligand binding site prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerProteinsBinding SitesLigandsProtein BindingAlgorithmsDeep LearningDatabases, Protein

Stichwörter der Autor:innen

deep learningdrug discoverygraph neural networkpoint cloudprotein–ligand binding sitestructure representation

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Academy of Military Medical Sciences, Beijing 100850, China.
  • Defense Innovation Institute, Beijing 100071, China.

ORCID-Profile: Yanpeng Zhao, Song He, Mengfan Li, Yang Cao

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • National Key R&D Program of China

Zitieren

APA

Zhao, Y., He, S., Xing, Y., Li, M., Cao, Y., Wang, X., Zhao, D., & Bo, X. (2024). A Point Cloud Graph Neural Network for Protein–Ligand Binding Site Prediction. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms25179280

Vancouver

Zhao Y, He S, Xing Y, Li M, Cao Y, Wang X, et al. A Point Cloud Graph Neural Network for Protein–Ligand Binding Site Prediction. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms25179280

BibTeX
@article{Zhao2024,
  author = {Zhao, Yanpeng and He, Song and Xing, Yuting and Li, Mengfan and Cao, Yang and Wang, Xuanze and Zhao, Dongsheng and Bo, Xiaochen},
  title = {A Point Cloud Graph Neural Network for Protein–Ligand Binding Site Prediction},
  journal = {International Journal of Molecular Sciences},
  year = {2024},
  doi = {10.3390/ijms25179280}
}
Kostenlos starten →