A Novel Deep Learning Model for Drug-drug Interactions


Cite item

Full Text

Abstract

Introduction:Drug-drug interactions (DDIs) can lead to adverse events and compromised treatment efficacy that emphasize the need for accurate prediction and understanding of these interactions.

Methods:in this paper, we propose a novel approach for DDI prediction using two separate message-passing neural network (MPNN) models, each focused on one drug in a pair. By capturing the unique characteristics of each drug and their interactions, the proposed method aims to improve the accuracy of DDI prediction. The outputs of the individual MPNN models combine to integrate the information from both drugs and their molecular features. Evaluating the proposed method on a comprehensive dataset, we demonstrate its superior performance with an accuracy of 0.90, an area under the curve (AUC) of 0.99, and an F1-score of 0.80. These results highlight the effectiveness of the proposed approach in accurately identifying potential drugdrug interactions.

Results:The use of two separate MPNN models offers a flexible framework for capturing drug characteristics and interactions, contributing to our understanding of DDIs. The findings of this study have significant implications for patient safety and personalized medicine, with the potential to optimize treatment outcomes by preventing adverse events. Conclusion: Further research and validation on larger datasets and

Conclusion:Further research and validation on larger datasets and real-world scenarios are necessary to explore the generalizability and practicality of this approach.

About the authors

Ali Abdul Raheem

Department of Software, College of Information, University of Babylon

Author for correspondence.
Email: info@benthamscience.net

Ban Dhannoon

Department of Computer Science,, Al-Nahrain University,

Author for correspondence.
Email: info@benthamscience.net

References

  1. Abdul Raheem, K.A; Dhannoon, N.B. Automating drug discovery using machine learning. Curr. Drug. Discov. Technol., 2023, 20(6), 79-86. doi: 10.2174/1570163820666230607163313
  2. Hu, G; Agarwal, P; Easton, JB Predicting synergism of cancer drugs using NCI-ALMANAC data. BMC Bioinformatics, 2016, 17(19), 478.
  3. Luo, Y.; Zhao, X.; Zhou, J. Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data. BMC Bioinformatics, 2019, 20(2), 72. doi: 10.1186/s12859-019-2624-x
  4. Wang, Y.; Zhang, J.; Li, F. DeepDDI: Predicting drug-drug interactions using attention-based convolutional neural network. Bioinformatics, 2019, 35(17), 3055-3061. doi: 10.1093/bioinformatics/btz044 PMID: 30657866
  5. Yao, Z.; Dong, L.; Han, L. DeepDDI-CNN: A deep learning model for predicting drug-drug interactions. BMC Bioinformatics, 2020, 21(13), 476. doi: 10.1186/s12859-020-03845-7
  6. Cheng, F.; Sun, G.; Li, H. Prediction of drug-drug interactions using multitask deep learning. PLOS Comput. Biol., 2021, 17(1), e1008553. doi: 10.1371/journal.pcbi.1008553
  7. Wang, J.; Zhao, Y.; Liu, B. HANNDDI: A heterogeneous information network-based artificial neural network model for drug-drug interaction prediction. Front. Pharmacol., 2020, 11, 40. doi: 10.3389/fphar.2020.00040
  8. Wang, H.; Liu, W.; Yang, H. Transfer learning-based drug-drug interaction prediction by integrating shared structures and features. Front. Genet., 2021, 12, 681126. doi: 10.3389/fgene.2021.681126
  9. Li, Y.; Yao, Y.; Zhang, M. Domain adaptation-based prediction of drug-drug interactions with matrix factorization. Brief. Bioinform., 2020, 21(6), 2299-2311. doi: 10.1093/bib/bbz070 PMID: 31774907
  10. Liu, C.; Wu, M.; Zhuang, Y. GCNDDI: Graph convolutional network for drug-drug interaction prediction. Molecules, 2019, 24(17), 3075. doi: 10.3390/molecules24173075 PMID: 31450574
  11. Wang, Y.; Zhu, C.; Yang, Y. Network-based prediction of drug-drug interactions using an efficient matrix factorization technique. BMC Bioinformatics, 2022, 23(Suppl. 4), 91. doi: 10.1186/s12859-022-04683-6
  12. Wang, X.; Wu, Z.; Liu, Q.; Luo, J. Predicting drug–drug interactions through deep learning. Comput. Struct. Biotechnol. J., 2020, 18, 2196-2204.
  13. Wei, X.; Tao, L.; Cui, L.; Tian, Y.; Zheng, Y.; Yang, Y. Graph convolutional network-based method for predicting drug-drug interactions. J. Chem. Inf. Model., 2019, 59(7), 3026-3034.
  14. Chen, Q.; Wang, D.; Liu, H.; Liu, S.; Zhang, L. A hybrid deep learning approach for drug–drug interaction detection. Int. J. Mol. Sci., 2020, 21(15), 5473. PMID: 32751833
  15. Peng, S.; Zhang, Y.; Zhang, J.; Lin, W.; Leung, H.C. Compound–protein interaction prediction for new target identification using deep learning. BMC Bioinformatics, 2020, 21(1), 1-25. PMID: 31898485
  16. Chen, X.; Zhang, C.; Ke, G.; Xu, R. Drug combination prediction with deep learning. J. Chem. Inf. Model., 2020, 60(11), 5277-5288. PMID: 32805108
  17. Li, Y.; Li, Y.; Yang, Y. DDIPLM: Predicting drug-drug interactions based on pharmacological pathways, chemical structures, and side effect profiles. J. Chem. Inf. Model., 2020, 60(2), 1197-1204.
  18. Li, Y.; Wu, Z. PDDI: Prediction of drug-drug interactions based on clinical side effects. Molecules, 2018, 23(5), 1066. doi: 10.3390/molecules23051066 PMID: 29751487
  19. Ye, Z.; Wang, X.; Mao, S.; Zhang, J.; Lin, H. Transfer learning improves prediction of drug-drug interactions for drug pairs with few common target proteins. Sci. Rep., 2019, 9(1), 1-11. PMID: 30626917
  20. Available From: http://ddinter.scbdd.com/
  21. Gu, Z.; Luo, X.; Chen, J.; Deng, M.; Lai, L. Hierarchical graph transformer with contrastive learning for protein function prediction. Bioinformatics, 2023, 39(7), 410. doi: 10.1093/bioinformatics/btad410 PMID: 37369035
  22. Ju, W.; Luo, X.; Qu, M.; Wang, Y.; Chen, C.; Deng, M.; Hua, X.; Zhang, M. TGNN: A joint semi-supervised framework for graph-level classification. Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, pp. , 2122-2128.2022 doi: 10.24963/ijcai.2022/295
  23. Yin, N.; Shen, L.; Wang, M.; Lan, L.; Ma, Z.; Chen, C.; Hua, X. CoCo: A coupled contrastive framework for unsupervised domain adaptive graph classification. Proceedings of the 40th International Conference on Machine Learning.,
  24. Al-Rabeah, M.H.; Lakizadeh, A. Prediction of drug-drug interaction events using graph neural networks based feature extraction. Sci. Rep., 2022, 12(1), 15590. doi: 10.1038/s41598-022-19999-4 PMID: 36114278
  25. Lyu, T.; Gao, J.; Tian, L.; Li, Z.; Zhang, P.; Zhang, J. MDNN: A multimodal deep neural network for predicting drug-drug interaction events. .In IJCAI, pp, , 3536-3542.2021 doi: 10.24963/ijcai.2021/487
  26. Zhang, C.; Lu, Y.; Zang, T. CNN-DDI: A learning-based method for predicting drug–drug interactions using convolution neural networks. BMC Bioinformatics, 2022, 23(S1)(1), 88. doi: 10.1186/s12859-022-04612-2 PMID: 35255808
  27. Liu, S. Enhancing Drug-Drug Interaction Prediction Using Deep Attention Neural Networks; Cold Spring Harbor Laboratory, 2021. doi: 10.1101/2021.03.16.435553

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2024 Bentham Science Publishers