EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PocketDTA: an advanced multimodal architecture for enhanced prediction of drug−target affinity from 3D structural data of target binding pockets

Long Zhao iD, Hongmei Wang, Shaoping Shi iD

Bioinformatics · 01.10.2024 · 40 (10)

DOI: 10.1093/bioinformatics/btae594 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 04.10.2024. Verfasst von Long Zhao und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang 330031, China. Hauptthemen laut MEDLINE: Drug Discovery. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Accurately predicting the drug−target binding affinity (DTA) is crucial to drug discovery and repurposing. Although deep learning has been widely used in this field, it still faces challenges with insufficient generalization performance, inadequate use of 3D information, and poor interpretability. Results To alleviate these problems, we developed the PocketDTA model. This model enhances the generalization performance by pre-trained models ESM-2 and GraphMVP. It ingeniously handles the first 3 (top-3) target binding pockets and drug 3D information through customized GVP-GNN Layers and GraphMVP-Decoder. In addition, it uses a bilinear attention network to enhance interpretability. Comparative analysis with state-of-the-art (SOTA) methods on the optimized Davis and KIBA datasets reveals that the PocketDTA model exhibits significant performance advantages. Further, ablation studies confirm the effectiveness of the model components, whereas cold-start experiments illustrate its robust generalization capabilities. In particular, the PocketDTA model has shown significant advantages in identifying key drug functional groups and amino acid residues via molecular docking and literature validation, highlighting its strong potential for interpretability. Availability and implementation Code and data are available at: https://github.com/zhaolongNCU/PocketDTA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryBinding SitesDeep LearningProtein BindingProteinsMolecular Docking SimulationComputational Biology

Substanzen

Proteins

Autor:innen und Institutionen

  • Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang 330031, China.
  • Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang 330031, China.

ORCID-Profile: Long Zhao, Shaoping Shi

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province

Zitieren

APA

Zhao, L., Wang, H., & Shi, S. (2024). PocketDTA: an advanced multimodal architecture for enhanced prediction of drug−target affinity from 3D structural data of target binding pockets. Bioinformatics, 40(10). https://doi.org/10.1093/bioinformatics/btae594

Vancouver

Zhao L, Wang H, Shi S. PocketDTA: an advanced multimodal architecture for enhanced prediction of drug−target affinity from 3D structural data of target binding pockets. Bioinformatics. 2024;40(10). doi:10.1093/bioinformatics/btae594

BibTeX
@article{Zhao2024,
  author = {Zhao, Long and Wang, Hongmei and Shi, Shaoping},
  title = {PocketDTA: an advanced multimodal architecture for enhanced prediction of drug−target affinity from 3D structural data of target binding pockets},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {10},
  doi = {10.1093/bioinformatics/btae594}
}
Kostenlos starten →