DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks
Abstract Drug repositioning, the discovery of new therapeutic uses for existing drugs, is increasingly gaining attention as a cost-effective and high-yield drug discovery strategy. Existing methods integrate diverse biological information into heterogeneous networks, providing a comprehensive framew...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01674-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571201371766784 |
|---|---|
| author | Dongjiang Niu Lianwei Zhang Beiyi Zhang Qiang Zhang Shanyang Ding Hai Wei Zhen Li |
| author_facet | Dongjiang Niu Lianwei Zhang Beiyi Zhang Qiang Zhang Shanyang Ding Hai Wei Zhen Li |
| author_sort | Dongjiang Niu |
| collection | DOAJ |
| description | Abstract Drug repositioning, the discovery of new therapeutic uses for existing drugs, is increasingly gaining attention as a cost-effective and high-yield drug discovery strategy. Existing methods integrate diverse biological information into heterogeneous networks, providing a comprehensive framework for understanding complex drug–disease associations, which also will introduces noise into the data and affect the performance of the model. In this paper, first, a novel drug repositioning method, namely DVGEDR, is proposed, which generates two subgraphs of the target drug–disease pair to fuse biological information and integrate drug–disease associations from two distinct perspectives: drug–disease heterogeneous network and similarity networks. Next, a Multiple Attention Graph encoder (MAGencoder) module is designed to learn subgraph features and explore relationships between entities, which also improve the interpretability of the model. Finally, a graph enhancement mechanism is devised to improve the perception of critical information of model, enabling the model to flexibly process different graph structures. Performance comparisons with baseline models on three public datasets validate the state-of-the-art performance of DVGEDR in the field of drug repositioning. In case study, DVGEDR identifies 10 new candidate drugs for breast cancer and COVID-19, demonstrating not only superior performance in experimental settings but also potential therapeutic advantages in clinical environments. Furthermore, we select two sets of instances and further analyzed the attention distribution of the different nodes in the subgraph to explain the decision process of the model. |
| format | Article |
| id | doaj-art-d6ec045d8d14444992511fa7a1f06141 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-d6ec045d8d14444992511fa7a1f061412025-02-02T12:49:35ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111111410.1007/s40747-024-01674-yDVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networksDongjiang Niu0Lianwei Zhang1Beiyi Zhang2Qiang Zhang3Shanyang Ding4Hai Wei5Zhen Li6College of Computer Science and Technology, Qingdao UniversityCollege of Computer Science and Technology, Qingdao UniversityCollege of Computer Science and Technology, Qingdao UniversityCollege of Computer Science and Technology, Qingdao UniversityCollege of Computer Science and Technology, Qingdao UniversityShouguang Fukang Pharmaceutical Co., Ltd.College of Computer Science and Technology, Qingdao UniversityAbstract Drug repositioning, the discovery of new therapeutic uses for existing drugs, is increasingly gaining attention as a cost-effective and high-yield drug discovery strategy. Existing methods integrate diverse biological information into heterogeneous networks, providing a comprehensive framework for understanding complex drug–disease associations, which also will introduces noise into the data and affect the performance of the model. In this paper, first, a novel drug repositioning method, namely DVGEDR, is proposed, which generates two subgraphs of the target drug–disease pair to fuse biological information and integrate drug–disease associations from two distinct perspectives: drug–disease heterogeneous network and similarity networks. Next, a Multiple Attention Graph encoder (MAGencoder) module is designed to learn subgraph features and explore relationships between entities, which also improve the interpretability of the model. Finally, a graph enhancement mechanism is devised to improve the perception of critical information of model, enabling the model to flexibly process different graph structures. Performance comparisons with baseline models on three public datasets validate the state-of-the-art performance of DVGEDR in the field of drug repositioning. In case study, DVGEDR identifies 10 new candidate drugs for breast cancer and COVID-19, demonstrating not only superior performance in experimental settings but also potential therapeutic advantages in clinical environments. Furthermore, we select two sets of instances and further analyzed the attention distribution of the different nodes in the subgraph to explain the decision process of the model.https://doi.org/10.1007/s40747-024-01674-yDrug repositioningDrug–disease associationHeterogeneous networkGraph enhancement |
| spellingShingle | Dongjiang Niu Lianwei Zhang Beiyi Zhang Qiang Zhang Shanyang Ding Hai Wei Zhen Li DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks Complex & Intelligent Systems Drug repositioning Drug–disease association Heterogeneous network Graph enhancement |
| title | DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks |
| title_full | DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks |
| title_fullStr | DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks |
| title_full_unstemmed | DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks |
| title_short | DVGEDR: a drug repositioning method based on dual-view fusion and graph enhancement mechanism in heterogeneous networks |
| title_sort | dvgedr a drug repositioning method based on dual view fusion and graph enhancement mechanism in heterogeneous networks |
| topic | Drug repositioning Drug–disease association Heterogeneous network Graph enhancement |
| url | https://doi.org/10.1007/s40747-024-01674-y |
| work_keys_str_mv | AT dongjiangniu dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT lianweizhang dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT beiyizhang dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT qiangzhang dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT shanyangding dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT haiwei dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks AT zhenli dvgedradrugrepositioningmethodbasedondualviewfusionandgraphenhancementmechanisminheterogeneousnetworks |