Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network
Abstract In recent years, combined drug screening has played a very important role in modern drug discovery. Generally, synergistic drug combinations are crucial in treatment for many diseases. However, the toxic side effects of drug combinations are probably increased with the increase of drugs num...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-024-06028-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594447770058752 |
|---|---|
| author | Leixia Tian Qi Wang Zhiheng Zhou Xiya Liu Ming Zhang Guiying Yan |
| author_facet | Leixia Tian Qi Wang Zhiheng Zhou Xiya Liu Ming Zhang Guiying Yan |
| author_sort | Leixia Tian |
| collection | DOAJ |
| description | Abstract In recent years, combined drug screening has played a very important role in modern drug discovery. Generally, synergistic drug combinations are crucial in treatment for many diseases. However, the toxic side effects of drug combinations are probably increased with the increase of drugs numbers, so the accurate prediction of toxic side effects of drug combinations is equally important. In this paper, we built a Metapath-based Aggregated Embedding Model on Single Drug–Side Effect Heterogeneous Information Network (MAEM-SSHIN), which extracts feature from a heterogeneous information network of single drug side effects, and a Graph Convolutional Network on Combinatorial drugs and Side effect Heterogeneous Information Network (GCN-CSHIN), which transforms the complex task of predicting multiple side effects between drug pairs into the more manageable prediction of relationships between combinatorial drugs and individual side effects. MAEM-SSHIN and GCN-CSHIN provided a united novel framework for predicting potential side effects in combinatorial drug therapies. This integration enhances prediction accuracy, efficiency, and scalability. Our experimental results demonstrate that this combined framework outperforms existing methodologies in predicting side effects, and marks a significant advancement in pharmaceutical research. |
| format | Article |
| id | doaj-art-ecfbce59056f48ef81cdebf3ae2c6aa2 |
| institution | Kabale University |
| issn | 1471-2105 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj-art-ecfbce59056f48ef81cdebf3ae2c6aa22025-01-19T12:40:53ZengBMCBMC Bioinformatics1471-21052025-01-0126112010.1186/s12859-024-06028-6Predicting drug combination side effects based on a metapath-based heterogeneous graph neural networkLeixia Tian0Qi Wang1Zhiheng Zhou2Xiya Liu3Ming Zhang4Guiying Yan5Beijing SchoolCollege of Science, China Agricultural UniversityAcademy of Mathematics and Systems Science, Chinese Academy of SciencesInstitute of Biophysics, Chinese Academy of SciencesAcademy of Mathematics and Systems Science, Chinese Academy of SciencesAcademy of Mathematics and Systems Science, Chinese Academy of SciencesAbstract In recent years, combined drug screening has played a very important role in modern drug discovery. Generally, synergistic drug combinations are crucial in treatment for many diseases. However, the toxic side effects of drug combinations are probably increased with the increase of drugs numbers, so the accurate prediction of toxic side effects of drug combinations is equally important. In this paper, we built a Metapath-based Aggregated Embedding Model on Single Drug–Side Effect Heterogeneous Information Network (MAEM-SSHIN), which extracts feature from a heterogeneous information network of single drug side effects, and a Graph Convolutional Network on Combinatorial drugs and Side effect Heterogeneous Information Network (GCN-CSHIN), which transforms the complex task of predicting multiple side effects between drug pairs into the more manageable prediction of relationships between combinatorial drugs and individual side effects. MAEM-SSHIN and GCN-CSHIN provided a united novel framework for predicting potential side effects in combinatorial drug therapies. This integration enhances prediction accuracy, efficiency, and scalability. Our experimental results demonstrate that this combined framework outperforms existing methodologies in predicting side effects, and marks a significant advancement in pharmaceutical research.https://doi.org/10.1186/s12859-024-06028-6Combinatorial drugsSide effect predictionMetapathGraph convolutional networkHeterogeneous information network |
| spellingShingle | Leixia Tian Qi Wang Zhiheng Zhou Xiya Liu Ming Zhang Guiying Yan Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network BMC Bioinformatics Combinatorial drugs Side effect prediction Metapath Graph convolutional network Heterogeneous information network |
| title | Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network |
| title_full | Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network |
| title_fullStr | Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network |
| title_full_unstemmed | Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network |
| title_short | Predicting drug combination side effects based on a metapath-based heterogeneous graph neural network |
| title_sort | predicting drug combination side effects based on a metapath based heterogeneous graph neural network |
| topic | Combinatorial drugs Side effect prediction Metapath Graph convolutional network Heterogeneous information network |
| url | https://doi.org/10.1186/s12859-024-06028-6 |
| work_keys_str_mv | AT leixiatian predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork AT qiwang predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork AT zhihengzhou predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork AT xiyaliu predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork AT mingzhang predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork AT guiyingyan predictingdrugcombinationsideeffectsbasedonametapathbasedheterogeneousgraphneuralnetwork |