A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks
PLOS Computational Biology · 13.11.2023 · 19 (11) · e1011597
DOI: 10.1371/journal.pcbi.1011597 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 13.11.2023. Verfasst von Shuting Jin und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China. Hauptthemen laut MEDLINE: Algorithms, Drug-Related Side Effects and Adverse Reactions. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Zhejiang Lab.
Abstract (Originalsprache)
The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces D rug- S ubstructures relationship into M olecular interaction N etworks to construct the micro-to-macro drug centric heterogeneous network ( DSMN ), and develop a multi-branches H yper G raph learning model, called HGDrug , for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, China.
- School of Informatics, Xiamen University, Xiamen, China.
- Department of AIDD, Shanghai Yuyao Biotechnology Co., Ltd., Shanghai, China.
- School of Economics, Innovation, and Technology, Kristiania University College, Bergen, Norway.
- School of Software, Shandong University, Shandong, China.
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai, China.
ORCID-Profile: Shuting Jin, Xiangxiang Zeng, Xiangrong Liu
Förderung
- National Natural Science Foundation of China
- Zhejiang Lab
Zitieren
APA
Jin, S., Hong, Y., Zeng, L., Jiang, Y., Lin, Y., Wei, L., Yu, Z., Zeng, X., & Liu, X. (2023). A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. PLOS Computational Biology, 19(11), e1011597. https://doi.org/10.1371/journal.pcbi.1011597
Vancouver
Jin S, Hong Y, Zeng L, Jiang Y, Lin Y, Wei L, et al. A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks. PLOS Computational Biology. 2023;19(11):e1011597. doi:10.1371/journal.pcbi.1011597
BibTeX
@article{Jin2023,
author = {Jin, Shuting and Hong, Yue and Zeng, Li and Jiang, Yinghui and Lin, Yuan and Wei, Leyi and Yu, Zhuohang and Zeng, Xiangxiang and Liu, Xiangrong},
title = {A general hypergraph learning algorithm for drug multi-task predictions in micro-to-macro biomedical networks},
journal = {PLOS Computational Biology},
year = {2023},
volume = {19},
number = {11},
pages = {e1011597},
doi = {10.1371/journal.pcbi.1011597}
}
EUVIMED