EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction

Guojian Deng, Changsheng Shi, Ruiquan Ge, Riqian Hu, Changmiao Wang, Feiwei Qin, Cheng Pan, Haixia Mao, Qing Yang

Frontiers in Pharmacology · 05.03.2025 · 16

DOI: 10.3389/fphar.2025.1553743 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Pharmacology, online erschienen am 05.03.2025. Verfasst von Guojian Deng und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Hangzhou Dianzi University, Hangzhou, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Predicting drug-target interaction (DTI) is a crucial phase in drug discovery. The core of DTI prediction lies in appropriate representations learning of drug and target. Previous studies have confirmed the effectiveness of graph neural networks (GNNs) in drug compound feature encoding. However, these GNN-based methods do not effectively balance the local substructural features with the overall structural properties of the drug molecular graph.

Methods

In this study, we proposed a novel model named GNNBlockDTI to address the current challenges. We combined multiple layers of GNN as a GNNBlock unit to capture the hidden structural patterns from drug graph within local ranges. Based on the proposed GNNBlock, we introduced a feature enhancement strategy to re-encode the obtained structural features, and utilized gating units for redundant information filtering. To simulate the essence of DTI that only protein fragments in the binding pocket interact with drugs, we provided a local encoding strategy for target protein using variant convolutional networks.

Results

Experimental results on three benchmark datasets demonstrated that GNNBlockDTI is highly competitive compared to the state-of-the-art models. Moreover, the case study of drug candidates ranking against different targets affirms the practical effectiveness of GNNBlockDTI. The source code for this study is available at https://github.com/Ptexys/GNNBlockDTI .

Schlagwörter

Stichwörter der Autor:innen

drug discoverydrug-target interaction predictiongraph neural networkgraph representation learningmolecular substructure

Autor:innen und Institutionen

  • School of Computer Science, Hangzhou Dianzi University, Hangzhou, China.
  • Department of Interventional Vascular Surgery, The Third Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
  • Hangzhou Institute of Advanced Technology, Hangzhou, China.
  • Jacob School of Engineering, University of California, San Diego, CA, United States.
  • Medical Big Data Laboratory, Shenzhen Research Institute of Big Data, Shenzhen, China.
  • School of General Education, Sanda University, Shanghai, China.

Zitieren

APA

Deng, G., Shi, C., Ge, R., Hu, R., Wang, C., Qin, F., Pan, C., Mao, H., & Yang, Q. (2025). Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction. Frontiers in Pharmacology, 16. https://doi.org/10.3389/fphar.2025.1553743

Vancouver

Deng G, Shi C, Ge R, Hu R, Wang C, Qin F, et al. Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction. Frontiers in Pharmacology. 2025;16. doi:10.3389/fphar.2025.1553743

BibTeX
@article{Deng2025,
  author = {Deng, Guojian and Shi, Changsheng and Ge, Ruiquan and Hu, Riqian and Wang, Changmiao and Qin, Feiwei and Pan, Cheng and Mao, Haixia and Yang, Qing},
  title = {Efficient substructure feature encoding based on graph neural network blocks for drug-target interaction prediction},
  journal = {Frontiers in Pharmacology},
  year = {2025},
  volume = {16},
  doi = {10.3389/fphar.2025.1553743}
}
Kostenlos starten →