Predicting the toxic side effects of drug interactions using chemical structures and protein sequences
Abstract The study aims to address the critical issue of toxic side effects resulting from drug combinations, which can significantly increase health risks, clinical complications, and lead to drug being withdrawn from the market. A model named TSEDDI (toxic side effects of drug-drug interaction) ha...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-12-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82981-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846101170003640320 |
|---|---|
| author | Liyuan Zhang Yongxin Sheng Jinxiang Yang Zuhai Hu Bin Peng |
| author_facet | Liyuan Zhang Yongxin Sheng Jinxiang Yang Zuhai Hu Bin Peng |
| author_sort | Liyuan Zhang |
| collection | DOAJ |
| description | Abstract The study aims to address the critical issue of toxic side effects resulting from drug combinations, which can significantly increase health risks, clinical complications, and lead to drug being withdrawn from the market. A model named TSEDDI (toxic side effects of drug-drug interaction) has been developed to improve the identification of drug pairs that may induce toxicity or adverse reactions. By utilizing drug chemical structures and diverse proteins, we employ a convolutional neural network (CNN) to extract features from molecular images, enzyme proteins, transporter proteins, and target proteins. Furthermore, we introduce a weighted binary cross entropy loss function to tackle class imbalance and integrate the multi-head attention mechanism with residual connections to enhance model performance. Our model outperformed advanced baseline models in predicting drug-drug interaction (DDI) side effects, achieving an accuracy of 0.9059 (± 0.0010) and consistently excelling across various evaluation metrics. The case study confirms the potential mechanisms by which four pairs of drugs cause side effects, thus demonstrating the effectiveness of our model in predicting DDI side effects. The TSEDDI model combines multiple attention mechanisms and residual connections, enhancing its ability to detect toxic and adverse effects related to DDIs. As a result, it becomes a valuable resource for promptly identifying adverse reactions in clinical trials. Future research could investigate drug substructures prone to toxic side effects. |
| format | Article |
| id | doaj-art-2dc4c993398a4e5a9df256eded9af6bf |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2dc4c993398a4e5a9df256eded9af6bf2024-12-29T12:27:15ZengNature PortfolioScientific Reports2045-23222024-12-0114111210.1038/s41598-024-82981-9Predicting the toxic side effects of drug interactions using chemical structures and protein sequencesLiyuan Zhang0Yongxin Sheng1Jinxiang Yang2Zuhai Hu3Bin Peng4School of Public Health, Chongqing Medical UniversitySchool of Public Health, Chongqing Medical UniversitySchool of Public Health, Chongqing Medical UniversitySchool of Public Health, Chongqing Medical UniversitySchool of Public Health, Chongqing Medical UniversityAbstract The study aims to address the critical issue of toxic side effects resulting from drug combinations, which can significantly increase health risks, clinical complications, and lead to drug being withdrawn from the market. A model named TSEDDI (toxic side effects of drug-drug interaction) has been developed to improve the identification of drug pairs that may induce toxicity or adverse reactions. By utilizing drug chemical structures and diverse proteins, we employ a convolutional neural network (CNN) to extract features from molecular images, enzyme proteins, transporter proteins, and target proteins. Furthermore, we introduce a weighted binary cross entropy loss function to tackle class imbalance and integrate the multi-head attention mechanism with residual connections to enhance model performance. Our model outperformed advanced baseline models in predicting drug-drug interaction (DDI) side effects, achieving an accuracy of 0.9059 (± 0.0010) and consistently excelling across various evaluation metrics. The case study confirms the potential mechanisms by which four pairs of drugs cause side effects, thus demonstrating the effectiveness of our model in predicting DDI side effects. The TSEDDI model combines multiple attention mechanisms and residual connections, enhancing its ability to detect toxic and adverse effects related to DDIs. As a result, it becomes a valuable resource for promptly identifying adverse reactions in clinical trials. Future research could investigate drug substructures prone to toxic side effects.https://doi.org/10.1038/s41598-024-82981-9Adverse DDI predictionMulti-head self-attention mechanismDeep learningFeature extraction |
| spellingShingle | Liyuan Zhang Yongxin Sheng Jinxiang Yang Zuhai Hu Bin Peng Predicting the toxic side effects of drug interactions using chemical structures and protein sequences Scientific Reports Adverse DDI prediction Multi-head self-attention mechanism Deep learning Feature extraction |
| title | Predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| title_full | Predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| title_fullStr | Predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| title_full_unstemmed | Predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| title_short | Predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| title_sort | predicting the toxic side effects of drug interactions using chemical structures and protein sequences |
| topic | Adverse DDI prediction Multi-head self-attention mechanism Deep learning Feature extraction |
| url | https://doi.org/10.1038/s41598-024-82981-9 |
| work_keys_str_mv | AT liyuanzhang predictingthetoxicsideeffectsofdruginteractionsusingchemicalstructuresandproteinsequences AT yongxinsheng predictingthetoxicsideeffectsofdruginteractionsusingchemicalstructuresandproteinsequences AT jinxiangyang predictingthetoxicsideeffectsofdruginteractionsusingchemicalstructuresandproteinsequences AT zuhaihu predictingthetoxicsideeffectsofdruginteractionsusingchemicalstructuresandproteinsequences AT binpeng predictingthetoxicsideeffectsofdruginteractionsusingchemicalstructuresandproteinsequences |