MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions
Drug-drug interactions (DDIs) can severely affect patient health and safety. Predicting potential DDIs before administering medication to patients is crucial for drug development as it helps to prevent adverse drug reactions. Many effective DDI prediction methods have been proposed using graph neura...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10786969/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846118292533542912 |
|---|---|
| author | Xiang Li Xiangmin Ji Chengzhen Xu Jie Hou Xiaoyu Zhao Guodong Peng |
| author_facet | Xiang Li Xiangmin Ji Chengzhen Xu Jie Hou Xiaoyu Zhao Guodong Peng |
| author_sort | Xiang Li |
| collection | DOAJ |
| description | Drug-drug interactions (DDIs) can severely affect patient health and safety. Predicting potential DDIs before administering medication to patients is crucial for drug development as it helps to prevent adverse drug reactions. Many effective DDI prediction methods have been proposed using graph neural networks; however, these methods only aggregate information from directly connected nodes restricted to a drug-related manner and fail to capture long-range dependencies in heterogeneous networks. To address this issue, we propose an enhanced multiple-feature hybrid graph method to predict DDIs (MFHG-DDI). Specifically, we constructed a heterogeneous network incorporating multiple drug features and DDI information. We employed an enhanced hybrid graph module that integrates a graph convolutional network, graph attention network, and global average pooling to learn latent features, ultimately applying a prediction function to predict DDIs. MFHG-DDI reframes the heterogeneous network as a graph classification task, capturing DDI information efficiently through an enhanced hybrid graph. Known DDI datasets were used to train and evaluate the proposed model. The experimental results indicate that integrating multiple drug features into the hybrid graph method can enhance the DDI prediction accuracy, increases the success rate of combination therapy, and has the potential to enhance drug safety. |
| format | Article |
| id | doaj-art-a25c5c5a32e04e64a00ee87970049b7d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a25c5c5a32e04e64a00ee87970049b7d2024-12-18T00:01:51ZengIEEEIEEE Access2169-35362024-01-011218842418843410.1109/ACCESS.2024.351416310786969MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug InteractionsXiang Li0Xiangmin Ji1https://orcid.org/0000-0002-4044-0989Chengzhen Xu2Jie Hou3https://orcid.org/0000-0001-5979-8852Xiaoyu Zhao4https://orcid.org/0000-0003-3904-7706Guodong Peng5https://orcid.org/0009-0005-1663-8062School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou, ChinaSchool of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou, ChinaSchool of Computer Science and Technology, Huaibei Normal University, Huaibei, ChinaPublic Teaching and Research Department, Huzhou College, Huzhou, ChinaDepartment of Mathematics and Computer Engineering, Ordos Institute of Technology, Ordos, ChinaSchool of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou, ChinaDrug-drug interactions (DDIs) can severely affect patient health and safety. Predicting potential DDIs before administering medication to patients is crucial for drug development as it helps to prevent adverse drug reactions. Many effective DDI prediction methods have been proposed using graph neural networks; however, these methods only aggregate information from directly connected nodes restricted to a drug-related manner and fail to capture long-range dependencies in heterogeneous networks. To address this issue, we propose an enhanced multiple-feature hybrid graph method to predict DDIs (MFHG-DDI). Specifically, we constructed a heterogeneous network incorporating multiple drug features and DDI information. We employed an enhanced hybrid graph module that integrates a graph convolutional network, graph attention network, and global average pooling to learn latent features, ultimately applying a prediction function to predict DDIs. MFHG-DDI reframes the heterogeneous network as a graph classification task, capturing DDI information efficiently through an enhanced hybrid graph. Known DDI datasets were used to train and evaluate the proposed model. The experimental results indicate that integrating multiple drug features into the hybrid graph method can enhance the DDI prediction accuracy, increases the success rate of combination therapy, and has the potential to enhance drug safety.https://ieeexplore.ieee.org/document/10786969/Drug-drug interactionmultiple featuresheterogeneous networkgraph convolutional networkgraph attention network |
| spellingShingle | Xiang Li Xiangmin Ji Chengzhen Xu Jie Hou Xiaoyu Zhao Guodong Peng MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions IEEE Access Drug-drug interaction multiple features heterogeneous network graph convolutional network graph attention network |
| title | MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions |
| title_full | MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions |
| title_fullStr | MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions |
| title_full_unstemmed | MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions |
| title_short | MFHG-DDI: An Enhanced Hybrid Graph Method Leveraging Multiple Features for Predicting Drug–Drug Interactions |
| title_sort | mfhg ddi an enhanced hybrid graph method leveraging multiple features for predicting drug x2013 drug interactions |
| topic | Drug-drug interaction multiple features heterogeneous network graph convolutional network graph attention network |
| url | https://ieeexplore.ieee.org/document/10786969/ |
| work_keys_str_mv | AT xiangli mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions AT xiangminji mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions AT chengzhenxu mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions AT jiehou mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions AT xiaoyuzhao mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions AT guodongpeng mfhgddianenhancedhybridgraphmethodleveragingmultiplefeaturesforpredictingdrugx2013druginteractions |