Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs
Summary: Combinatorial drug therapy is a promising approach for treating complex diseases by combining drugs with synergistic effects. However, predicting effective drug combinations is challenging due to the complexity of biological systems and the limited understanding of pathophysiological mechan...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004223020977 |
| _version_ | 1797647825341775872 |
|---|---|
| author | Wenyu Shan Cong Shen Lingyun Luo Pingjian Ding |
| author_facet | Wenyu Shan Cong Shen Lingyun Luo Pingjian Ding |
| author_sort | Wenyu Shan |
| collection | DOAJ |
| description | Summary: Combinatorial drug therapy is a promising approach for treating complex diseases by combining drugs with synergistic effects. However, predicting effective drug combinations is challenging due to the complexity of biological systems and the limited understanding of pathophysiological mechanisms and drug targets. In this paper, we proposed a computational framework called VGAETF (Variational Graph Autoencoder Tensor Decomposition), which leveraged multi-relational graph to model complex relationships between entities in biological systems and predicted disease-related synergistic drug combinations in an end-to-end manner. In the computational experiments, VGAETF achieved high performances (AUROC [the area under receiver operating characteristic] = 0.9767, AUPR [the area under precision-recall] = 0.9660), outperforming other compared methods. Moreover, case studies further demonstrated the effectiveness of VGAETF in identifying potential disease-related synergistic drug combinations. |
| first_indexed | 2024-03-11T15:22:07Z |
| format | Article |
| id | doaj.art-784ac7e7b83b4f838af7339a15085b10 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-03-11T15:22:07Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-784ac7e7b83b4f838af7339a15085b102023-10-28T05:09:19ZengElsevieriScience2589-00422023-10-012610108020Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphsWenyu Shan0Cong Shen1Lingyun Luo2Pingjian Ding3School of Computer Science, University of South China, Hengyang, Hunan 421001, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan 410082, ChinaSchool of Computer Science, University of South China, Hengyang, Hunan 421001, China; Hunan Medical Big Data International Science and Technology Innovation Cooperation Base, Hengyang, Hunan 421001, ChinaSchool of Computer Science, University of South China, Hengyang, Hunan 421001, China; Corresponding authorSummary: Combinatorial drug therapy is a promising approach for treating complex diseases by combining drugs with synergistic effects. However, predicting effective drug combinations is challenging due to the complexity of biological systems and the limited understanding of pathophysiological mechanisms and drug targets. In this paper, we proposed a computational framework called VGAETF (Variational Graph Autoencoder Tensor Decomposition), which leveraged multi-relational graph to model complex relationships between entities in biological systems and predicted disease-related synergistic drug combinations in an end-to-end manner. In the computational experiments, VGAETF achieved high performances (AUROC [the area under receiver operating characteristic] = 0.9767, AUPR [the area under precision-recall] = 0.9660), outperforming other compared methods. Moreover, case studies further demonstrated the effectiveness of VGAETF in identifying potential disease-related synergistic drug combinations.http://www.sciencedirect.com/science/article/pii/S2589004223020977Health sciencesMedicineHealth technologyPharmacology |
| spellingShingle | Wenyu Shan Cong Shen Lingyun Luo Pingjian Ding Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs iScience Health sciences Medicine Health technology Pharmacology |
| title | Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs |
| title_full | Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs |
| title_fullStr | Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs |
| title_full_unstemmed | Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs |
| title_short | Multi-task learning for predicting synergistic drug combinations based on auto-encoding multi-relational graphs |
| title_sort | multi task learning for predicting synergistic drug combinations based on auto encoding multi relational graphs |
| topic | Health sciences Medicine Health technology Pharmacology |
| url | http://www.sciencedirect.com/science/article/pii/S2589004223020977 |
| work_keys_str_mv | AT wenyushan multitasklearningforpredictingsynergisticdrugcombinationsbasedonautoencodingmultirelationalgraphs AT congshen multitasklearningforpredictingsynergisticdrugcombinationsbasedonautoencodingmultirelationalgraphs AT lingyunluo multitasklearningforpredictingsynergisticdrugcombinationsbasedonautoencodingmultirelationalgraphs AT pingjianding multitasklearningforpredictingsynergisticdrugcombinationsbasedonautoencodingmultirelationalgraphs |