Weighted hypergraph learning and adaptive inductive matrix completion for SARS-CoV-2 drug repositioning
Methods · 2023-11 · 219 · 102-110
DOI: 10.1016/j.ymeth.2023.10.002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Methods, 2023-11. Verfasst von Yingjun Ma und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Xiamen University of Technology, Xiamen 361024, China. Electronic address: 2020000045@xmut.edu.cn. Hauptthemen laut MEDLINE: SARS-CoV-2, COVID-19. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Humanities and Social Science Fund of Ministry of Education of China, Department of Education, Fujian Province, Fujian Provincial Department of Science and Technology.
Abstract (Originalsprache)
MOTIVATION: The outbreak of the human coronavirus (SARS-CoV-2) has placed a huge burden on public health and the world economy. Compared with de novo drug discovery, drug repurposing is a promising therapeutic strategy that facilitates rapid clinical treatment decisions, shortens the development process, and reduces costs. RESULTS: In this study, we propose a weighted hypergraph learning and adaptive inductive matrix completion method, WHAIMC, for predicting potential virus-drug associations. Firstly, we integrate multi-source data to describe viruses and drugs from multiple perspectives, including drug chemical structures, drug targets, virus complete genome sequences, and virus-drug associations. Then, WHAIMC establishes an adaptive inductive matrix completion model to improve performance through adaptive learning of similarity relations. Finally, WHAIMC introduces weighted hypergraph learning into adaptive inductive matrix completion to capture higher-order relationships of viruses (or drugs). The results showed that WHAIMC had a strong predictive performance for new virus-drug associations, new viruses, and new drugs. The case study further demonstrates that WHAIMC is highly effective for repositioning antiviral drugs against SARS-CoV-2 and provides a new perspective for virus-drug association prediction. The code and data in this study is freely available at https://github.com/Mayingjun20179/WHAIMC.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- School of Mathematics and Statistics, Xiamen University of Technology, Xiamen 361024, China. Electronic address: 2020000045@xmut.edu.cn.
- School of Mathematics and Statistics, Xiamen University of Technology, Xiamen 361024, China.
Förderung
- Humanities and Social Science Fund of Ministry of Education of China
- Department of Education, Fujian Province
- Fujian Provincial Department of Science and Technology
- Program for New Century Excellent Talents in University of Ministry of Education of China
- Natural Science Foundation of Fujian Province
Zitieren
APA
Ma, Y., Zhong, J., & Zhu, N. (2023). Weighted hypergraph learning and adaptive inductive matrix completion for SARS-CoV-2 drug repositioning. Methods, 219, 102-110. https://doi.org/10.1016/j.ymeth.2023.10.002
Vancouver
Ma Y, Zhong J, Zhu N. Weighted hypergraph learning and adaptive inductive matrix completion for SARS-CoV-2 drug repositioning. Methods. 2023;219:102-110. doi:10.1016/j.ymeth.2023.10.002
BibTeX
@article{Ma2023,
author = {Ma, Yingjun and Zhong, Junjiang and Zhu, Nenghui},
title = {Weighted hypergraph learning and adaptive inductive matrix completion for SARS-CoV-2 drug repositioning},
journal = {Methods},
year = {2023},
volume = {219},
pages = {102--110},
doi = {10.1016/j.ymeth.2023.10.002}
}
EUVIMED