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...
Saved in:
| Main Author: | |
|---|---|
| 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 |