iGRLDTI: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network
Bioinformatics · 01.08.2023 · 39 (8)
DOI: 10.1093/bioinformatics/btad451 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 28.07.2023. Verfasst von Bo-Wei Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: The Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Drug Discovery. Die Arbeit wurde bisher 104-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Xinjiang Uygur Autonomous Region.
Abstract (Originalsprache)
Motivation The task of predicting drug–target interactions (DTIs) plays a significant role in facilitating the development of novel drug discovery. Compared with laboratory-based approaches, computational methods proposed for DTI prediction are preferred due to their high-efficiency and low-cost advantages. Recently, much attention has been attracted to apply different graph neural network (GNN) models to discover underlying DTIs from heterogeneous biological information network (HBIN). Although GNN-based prediction methods achieve better performance, they are prone to encounter the over-smoothing simulation when learning the latent representations of drugs and targets with their rich neighborhood information in HBIN, and thereby reduce the discriminative ability in DTI prediction. Results In this work, an improved graph representation learning method, namely iGRLDTI, is proposed to address the above issue by better capturing more discriminative representations of drugs and targets in a latent feature space. Specifically, iGRLDTI first constructs an HBIN by integrating the biological knowledge of drugs and targets with their interactions. After that, it adopts a node-dependent local smoothing strategy to adaptively decide the propagation depth of each biomolecule in HBIN, thus significantly alleviating over-smoothing by enhancing the discriminative ability of feature representations of drugs and targets. Finally, a Gradient Boosting Decision Tree classifier is used by iGRLDTI to predict novel DTIs. Experimental results demonstrate that iGRLDTI yields better performance that several state-of-the-art computational methods on the benchmark dataset. Besides, our case study indicates that iGRLDTI can successfully identify novel DTIs with more distinguishable features of drugs and targets. Availability and implementation Python codes and dataset are available at https://github.com/stevejobws/iGRLDTI/.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- The Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China.
- University of Chinese Academy of Sciences, Beijing 100049, China.
- Xinjiang Laboratory of Minority Speech and Language Information Processing, Urumqi 830011, China.
- School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China.
ORCID-Profile: Bo-Wei Zhao, Xiao-Rui Su, Lun Hu
Förderung
- Natural Science Foundation of Xinjiang Uygur Autonomous Region
Zitieren
APA
Zhao, B. W., Su, X. R., Hu, P. W., Huang, Y. A., You, Z. H., & Hu, L. (2023). iGRLDTI: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network. Bioinformatics, 39(8). https://doi.org/10.1093/bioinformatics/btad451
Vancouver
Zhao BW, Su XR, Hu PW, Huang YA, You ZH, Hu L. iGRLDTI: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network. Bioinformatics. 2023;39(8). doi:10.1093/bioinformatics/btad451
BibTeX
@article{Zhao2023,
author = {Zhao, Bo-Wei and Su, Xiao-Rui and Hu, Peng-Wei and Huang, Yu-An and You, Zhu-Hong and Hu, Lun},
title = {iGRLDTI: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network},
journal = {Bioinformatics},
year = {2023},
volume = {39},
number = {8},
doi = {10.1093/bioinformatics/btad451}
}
EUVIMED