Improving computational drug repositioning through multi-source disease similarity networks

Abstract Computational drug repositioning seeks to identify new therapeutic uses for existing or experimental drugs. Network-based methods are effective as they integrate relationships among drugs, diseases, and target proteins/genes into prediction models. However, traditional approaches often rely...

Full description

Saved in:
Bibliographic Details
Main Author: Duc-Hau Le
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04772-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226271203000320
author Duc-Hau Le
author_facet Duc-Hau Le
author_sort Duc-Hau Le
collection DOAJ
description Abstract Computational drug repositioning seeks to identify new therapeutic uses for existing or experimental drugs. Network-based methods are effective as they integrate relationships among drugs, diseases, and target proteins/genes into prediction models. However, traditional approaches often rely on a single phenotype-based disease similarity network, limiting the diversity of disease information. In this study, we constructed three disease similarity networks—phenotypic, ontological, and molecular—using data from OMIM, Human Phenotype Ontology annotations, and gene interaction network, respectively. These were integrated into disease multiplex networks and multiplex-heterogeneous networks. We applied a tailored Random Walk with Restart (RWR) algorithm to predict novel drug-disease associations. Experimental results show that both disease multiplex and multiplex-heterogeneous networks outperform their single-layer counterparts in leave-one-out cross-validation. Using 10-fold cross-validation, our method, MHDR, outperformed the state-of-the-art methods TP-NRWRH, DDAGDL and RGLDR, demonstrating the advantage of integrating multiple disease similarity networks. We predicted novel drug-disease associations by ranking candidates, identifying 68 associations supported by shared proteins/genes, 1,064 by shared pathways, and 84 by shared protein complexes, with many validated by clinical trials, underscoring the practical impact of our approach.
format Article
id doaj-art-528d776658b04cfd91214372c56efbaa
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-528d776658b04cfd91214372c56efbaa2025-08-24T11:30:46ZengNature PortfolioScientific Reports2045-23222025-08-0115111710.1038/s41598-025-04772-0Improving computational drug repositioning through multi-source disease similarity networksDuc-Hau Le0School of Information and Communications Technology, Hanoi University of Science and TechnologyAbstract Computational drug repositioning seeks to identify new therapeutic uses for existing or experimental drugs. Network-based methods are effective as they integrate relationships among drugs, diseases, and target proteins/genes into prediction models. However, traditional approaches often rely on a single phenotype-based disease similarity network, limiting the diversity of disease information. In this study, we constructed three disease similarity networks—phenotypic, ontological, and molecular—using data from OMIM, Human Phenotype Ontology annotations, and gene interaction network, respectively. These were integrated into disease multiplex networks and multiplex-heterogeneous networks. We applied a tailored Random Walk with Restart (RWR) algorithm to predict novel drug-disease associations. Experimental results show that both disease multiplex and multiplex-heterogeneous networks outperform their single-layer counterparts in leave-one-out cross-validation. Using 10-fold cross-validation, our method, MHDR, outperformed the state-of-the-art methods TP-NRWRH, DDAGDL and RGLDR, demonstrating the advantage of integrating multiple disease similarity networks. We predicted novel drug-disease associations by ranking candidates, identifying 68 associations supported by shared proteins/genes, 1,064 by shared pathways, and 84 by shared protein complexes, with many validated by clinical trials, underscoring the practical impact of our approach.https://doi.org/10.1038/s41598-025-04772-0Drug repositioningMulti-Source disease similarity networksDisease multiplex networksMultiplex-Heterogeneous networksRandom walk with restart (RWR)
spellingShingle Duc-Hau Le
Improving computational drug repositioning through multi-source disease similarity networks
Scientific Reports
Drug repositioning
Multi-Source disease similarity networks
Disease multiplex networks
Multiplex-Heterogeneous networks
Random walk with restart (RWR)
title Improving computational drug repositioning through multi-source disease similarity networks
title_full Improving computational drug repositioning through multi-source disease similarity networks
title_fullStr Improving computational drug repositioning through multi-source disease similarity networks
title_full_unstemmed Improving computational drug repositioning through multi-source disease similarity networks
title_short Improving computational drug repositioning through multi-source disease similarity networks
title_sort improving computational drug repositioning through multi source disease similarity networks
topic Drug repositioning
Multi-Source disease similarity networks
Disease multiplex networks
Multiplex-Heterogeneous networks
Random walk with restart (RWR)
url https://doi.org/10.1038/s41598-025-04772-0
work_keys_str_mv AT duchaule improvingcomputationaldrugrepositioningthroughmultisourcediseasesimilaritynetworks