Abstract
Adverse drug–drug interactions (DDIs) can severely damage the body. Thus, it is essential to accurately predict DDIs. DDIs are complex processes in which many factors can cause interactions. Rather than merely considering one or two of the factors, we design a two-pathway drug–drug interaction framework named TP-DDI that uses multimodal data for DDI prediction. TP-DDI effectively explores the combined effect of a topological structure-based pathway and a biomedical object similarity-based pathway to obtain multimodal drug representations. For the topology-based pathway, we focus on drug chemistry structures through the self-attention mechanism, which can capture hidden critical relationships, especially between pairs of atoms at remote topological distances. For the similarity-based pathway, our model can emphasize useful biomedical objects according to the channel weights. Finally, the fusion of multimodal data provides a holistic view of DDIs by learning the complementary features. On a real-world dataset, experiments show that TP-DDI can achieve better performance than the state-of-the-art models. Moreover, we can find the most critical substructures with certain interpretability in the newly predicted DDIs.
Graphical abstract
![](http://media.springernature.com/lw685/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Figa_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12539-022-00524-0/MediaObjects/12539_2022_524_Fig5_HTML.png)
Similar content being viewed by others
References
Han K, Jeng EE, Hess GT et al (2017) Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions. Nat Biotechnol 35:463–474. https://doi.org/10.1038/nbt.3834
Tatonetti NP, Ye PP, Daneshjou R, Altman RB (2012) Data-driven prediction of drug effects and interactions. Sci Transl Med 4(125):125ra31. https://doi.org/10.1126/scitranslmed.3003377
Nagai N (2010) Drug interaction studies on new drug applications: current situations and regulatory views in Japan. Drug Metab Pharmacokinet 25:3–15. https://doi.org/10.2133/dmpk.25.3
Niklas Norén G, Sundberg R, Bate A, Edwards IR (2010) A statistical methodology for drug–drug interaction surveillance. Stat Med 27:3057–3070. https://doi.org/10.1002/sim.3247
Xu B, Shi X, Zhao Z et al (2018) Full-attention based drug drug interaction extraction exploiting user-generated content. In: 2018 IEEE international conference on bioinformatics and biomedicine (BIBM), pp 560–565. https://doi.org/10.1109/BIBM.2018.8621281
Jiang Z, Gu L, Jiang Q (2017) Drug drug interaction extraction from literature using a skeleton long short term memory neural network. In: 2017 IEEE international conference on bioinformatics and biomedicine (BIBM), pp 552–555. https://doi.org/10.1109/BIBM.2017.8217708
Duke JD, Xu H, Zhiping W et al (2012) Literature based drug interaction prediction with clinical assessment using electronic medical records: novel myopathy associated drug interactions. PLoS Comput Biol 8:e1002614. https://doi.org/10.1371/journal.pcbi.1002614
Pathak J, Kiefer RC, Chute CG (2013) Using linked data for mining drug–drug interactions in electronic health records. Stud Health Technol Inform 192:682–686. https://doi.org/10.3233/978-1-61499-289-9-682
Tatonetti NP, Denny JC, Murphy SN et al (2011) Detecting drug interactions from adverse-event reports: interaction between paroxetine and pravastatin increases blood glucose levels. Clin Pharmacol Ther 90(1):133–142. https://doi.org/10.1038/clpt.2011.83
Lu Y, Shen D, Pietsch M et al (2015) A novel algorithm for analyzing drug-drug interactions from MEDLINE literature. Sci Rep 5:17357. https://doi.org/10.1038/srep17357
Linna H, Zhihao Y, Zhehuan Z et al (2013) Extracting drug–drug interaction from the biomedical literature using a stacked generalization-based approach. PLoS ONE 8(6):e65814. https://doi.org/10.1371/journal.pone.0065814
Park C, Park J, Park S (2020) AGCN: attention-based graph convolutional networks for drug–drug interaction extraction. Expert Syst Appl 159:113538. https://doi.org/10.1016/j.eswa.2020.113538
Zheng W, Lin H, Luo L et al (2017) An attention-based effective neural model for drug–drug interactions extraction. BMC Bioinform 18:445. https://doi.org/10.1186/s12859-017-1855-x
Vilar S, Harpaz R et al (2012) Drug–drug interaction through molecular structure similarity analysis. J Am Med Inform Assoc 19(6):1066–1074. https://doi.org/10.1136/amiajnl-2012-000935
Lee G, Park C, Ahn J (2019) Novel deep learning model for more accurate prediction of drug–drug interaction effects. BMC Bioinform 20(1):415. https://doi.org/10.1186/s12859-019-3013-0
Rohani N, Eslahchi C (2019) Drug–drug interaction predicting by neural network using integrated similarity. Sci Rep 9:13645. https://doi.org/10.1038/s41598-019-50121-3
Deng Y, Xu X, Qiu Y et al (2020) A multimodal deep learning framework for predicting drug–drug interaction events. Bioinformatics 36:4316–4322. https://doi.org/10.1093/bioinformatics/btaa501
Schwarz K, Allam A, Gonzalez N, Krauthammer M (2020) AttentionDDI: siamese attention-based deep learning method for drug–drug interaction predictions. BMC Bioinform 22(1):412. https://doi.org/10.1186/s12859-021-04325-y
Fokoue A, Sadoghi M, Hassanzadeh O, Zhang P (2016) Predicting drug–drug interactions through large-scale similarity-based link prediction. Latest Adv New Domains 9678:774–789. https://doi.org/10.1007/978-3-319-34129-3_47
Park K, Kim D, Ha S, Lee D (2015) Predicting pharmacodynamic drug–drug interactions through signaling propagation interference on protein–protein interaction networks. PLoS ONE 10(10):e0140816. https://doi.org/10.1371/journal.pone.0140816
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. https://arxiv.org/abs/1609.02907v4
Shi L, Zhang Y, Cheng J, Lu H (2019) Action recognition via pose-based graph convolutional networks with intermediate dense supervision. Pattern Recognit 121:108170. https://doi.org/10.1016/j.patcog.2021.108170
Hao Z, Lu C, Huang Z et al (2020) ASGN: an active semi-supervised graph neural network for molecular property prediction. ACM. https://doi.org/10.1145/3394486.3403117
Sun B, Zhang H, Wu Z et al (2021) Adaptive spatiotemporal graph convolutional networks for motor imagery classification. IEEE Signal Process Lett. https://doi.org/10.1109/LSP.2021.3049683
Xia H, Gao X (2021) Multi-scale mixed dense graph convolution network for skeleton-based action recognition. IEEE Access. https://doi.org/10.1109/ACCESS.2020.3049029
Marinka Z, Monica A, Jure L (2018) Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics 34(13):i457–i466. https://doi.org/10.1093/bioinformatics/bty294
Feng Y-H, Zhang S-W, Shi J-Y (2022) DPDDI: a deep predictor for drug–drug interactions. BMC Bioinform 21(1):419. https://doi.org/10.1186/s12859-020-03724-x
Zhong Y, Chen X, Zhao Y et al (2019) Graph-augmented convolutional networks on drug–drug interactions prediction. https://arxiv.org/abs/1912.03702
Wang H, Lian D, Zhang Y et al (2020) GoGNN: graph of graphs neural network for predicting structured entity interactions. Proceedings of the Twenty-Ninth international joint conference on artificial intelligence, pp 1317–1323. https://doi.org/10.24963/ijcai.2020/183
Nyamabo AK, Yu H, Shi JY (2021) SSI-DDI: substructure–substructure interactions for drug-drug interaction prediction. Brief Bioinform 22(6):133. https://doi.org/10.1093/bib/bbab133
Zhang W, Chen Y, Liu F et al (2017) Predicting potential drug–drug interactions by integrating chemical, biological, phenotypic and network data. BMC Bioinform 18:18. https://doi.org/10.1186/s12859-016-1415-9
Yanli W, Jewen X, Suzek TO et al (2019) PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic Acids Res 37:W623–W633. https://doi.org/10.1093/nar/gkp456
Defferrard M, Bresson X, Vandergheynst P (2017) Convolutional neural networks on graphs with fast localized spectral filtering. https://arxiv.org/abs/1606.09375
Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? https://arxiv.org/abs/1810.00826
Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J et al (2015) Convolutional networks on graphs for learning molecular fingerprints. https://arxiv.org/abs/1606.09375
Coley CW, Barzilay R, Green WH et al (2017) Convolutional embedding of attributed molecular graphs for physical property prediction. J Chem Inf Model 57(8):1757–1772. https://doi.org/10.1021/acs.jcim.6b00601
Yang ZY, Yang ZJ, Dong J et al (2019) Structural analysis and identification of colloidal aggregators in drug discovery. J Chem Inf Model 59(9):3714–3726. https://doi.org/10.1021/acs.jcim.9b00541
Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. https://arxiv.org/abs/1706.03762
Jie H, Li S, Gang S, Albanie S (2017) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell. https://doi.org/10.1109/TPAMI.2019.2913372
Gong L, Jiang S, Yang Z et al (2019) Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks. Int J Comput Assist Radiol Surg 14(1):1969–1979. https://doi.org/10.1007/s11548-019-01979-1
Sailor HB, Deena S, Jalal MA et al (2019) Unsupervised adaptation of acoustic models for ASR using utterance-level embeddings from squeeze and excitation networks. In: 2019 IEEE automatic speech recognition and understanding workshop (ASRU), pp 980–987. https://doi.org/10.1109/ASRU46091.2019.9003755
Bodapati JD, Shareef SN, Naralasetti V, Mundukur NB (2021) MSENet: multi-modal squeeze-and-excitation network for brain tumor severity prediction. Int J Pattern Recognit Artif Intell 35(7):2157005. https://doi.org/10.1142/S0218001421570056
Breiman L (2001) Random forests. Mach Learn 45(1):5–32. https://doi.org/10.1023/A:1010933404324
Amy SY, Hao MH, Vaishali D, Lai WG (2018) Celecoxib is a substrate of CYP2D6: impact on celecoxib metabolism in individuals with CYP2C9*3 variants. Drug Metab Pharmacokinet 33:S1347436718300600. https://doi.org/10.1016/j.dmpk.2018.06.001
Hisaka A, Ohno Y, Yamamoto T, Suzuki H (2010) Prediction of pharmacokinetic drug–drug interaction caused by changes in cytochrome P450 activity using in vivo information. Pharmacol Ther 125:230–248. https://doi.org/10.1016/j.pharmthera.2009.10.011
Amin SA, Adhikari N, Jha T (2018) Structure–activity relationships of HDAC8 inhibitors: non-hydroxamates as anticancer agents. Pharmacol Res. https://doi.org/10.1016/j.phrs.2018.03.001
Bermúdez-Lugo JA, Perez-Gonzalez O, Rosales-Hernández MC et al (2012) Exploration of the valproic acid binding site on histone deacetylase 8 using docking and molecular dynamic simulations. J Mol Model 18:2301–2310. https://doi.org/10.1007/s00894-011-1240-z
Wang AH, Wei L, Chen L et al (2011) Synergistic effect of bortezomib and valproic acid treatment on the proliferation and apoptosis of acute myeloid leukemia and myelodysplastic syndrome cells. Ann Hematol 90:917–931. https://doi.org/10.1007/s00277-011-1175-6
Acknowledgements
We would like to express our sincere acknowledgements to the anonymous reviewers and all authors of the cited references.
Funding
This work was supported by the National Natural Science Foundation of China (no. 61873156).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
The authors have declared that no competing interests exist.
Rights and permissions
About this article
Cite this article
Xie, J., Zhao, C., Ouyang, J. et al. TP-DDI: A Two-Pathway Deep Neural Network for Drug–Drug Interaction Prediction. Interdiscip Sci Comput Life Sci 14, 895–905 (2022). https://doi.org/10.1007/s12539-022-00524-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12539-022-00524-0