Skip to main content

Advertisement

Springer Nature Link
Log in

FSRM-DDIE :  few-shot learning methods based on relation metrics for the prediction of drug-drug interaction events

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Drug-drug interaction (DDI) prediction aims to predict and evaluate potential interactions between different drugs, assisting healthcare professionals in optimizing drug therapy, enhancing treatment outcomes, and minimizing adverse effects from drug combinations. Traditional research has extensively focused on whether two drugs interact, but predicting the specific events or effects resulting from these interactions may be more effective in understanding the underlying mechanisms of drug combinations. However, data scarcity in drug research significantly hampers the effectiveness of computational models. To address these challenges, we propose FSRM-DDIE, a novel few-shot drug-drug interaction events (DDIE) prediction model. This metric-based meta-learning framework first learns the features of a DDIE using a feature extractor fusing a graph neural network and an auto-encoder Siamese network. Subsequently, a relation metrics module is proposed to capture similar relations between events for classification. By employing meta-learning, our model could perform effectively even with fewer and rare events. Through the comparative experiments, FSRM-DDIE outperforms state-of-the-art methods, demonstrating its potential for accurately predicting DDIE and providing options for understanding drug-drug interactions despite data limitations. In addition, we discuss limitations of the methodology and possible future research trends.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The complete source code is available at: https://github.com/Bombtsti/FSRM-DDIE. All the data are available at:https://github.com/Bombtsti/FSRM-DDIE/tree/main/METADDIEdata.

References

  1. Yu H, Wang J, Zhao SY et al (2024) Ggi-ddi: identification for key molecular substructures by granule learning to interpret predicted drug–drug interactions. Expert Syst Appl 240:122500. https://doi.org/10.1016/j.eswa.2023.122500

    Article  Google Scholar 

  2. Hauben M (2023) Artificial intelligence and data mining for the pharmacovigilance of drug–drug interactions. Clin Ther 45(2):117–133. https://doi.org/10.1016/j.clinthera.2023.01.002

    Article  Google Scholar 

  3. Bassani D, Moro S (2023) Past, present, and future perspectives on computer-aided drug design methodologies. Molecules 28(9):1–20. https://doi.org/10.3390/molecules28093906

    Article  Google Scholar 

  4. Zhao X, Huang L, Nie J et al (2024) Towards adaptive multi-scale intermediate domain via progressive training for unsupervised domain adaptation. IEEE Trans Multimedia 26:5054–5064. https://doi.org/10.1109/TMM.2023.3330088

    Article  Google Scholar 

  5. Cao H, Huang L, Nie J et al (2023) Unsupervised deep hashing with fine-grained similarity-preserving contrastive learning for image retrieval. IEEE Trans Circuits Syst Video Technol:1–15. https://doi.org/10.1109/TCSVT.2023.3320444

  6. Xu L, Xia L, Pan S et al (2024) Triple generative self-supervised learning method for molecular property prediction. Int J Mol Sci 25(7):1–19. https://doi.org/10.3390/ijms25073794

    Article  Google Scholar 

  7. Dou M, Tang J, Tiwari P et al (2024) Drug–drug interaction relation extraction based on deep learning: a review. ACM Comput Surv 56(6):1–33. https://doi.org/10.1145/3645089

    Article  Google Scholar 

  8. Li Z, Jiang M, Wang S et al (2022) Deep learning methods for molecular representation and property prediction. Drug Discov Today 27(12):103373. https://doi.org/10.1016/j.drudis.2022.103373

    Article  Google Scholar 

  9. Schwarz K, Allam A, Perez Gonzalez NA et al (2021) Attentionddi: Siamese attention-based deep learning method for drug-drug interaction predictions. BMC Bioinf 22(1):412. https://doi.org/10.1186/s12859-021-04325-y

    Article  Google Scholar 

  10. Vo TH, Nguyen NTK, Le NQK (2023) Improved prediction of drug-drug interactions using ensemble deep neural networks. Med Drug Discov 17:100149. https://doi.org/10.1016/j.medidd.2022.100149

    Article  Google Scholar 

  11. Veličković P (2023) Everything is connected: graph neural networks. Curr Opin Struct Biol 79:102538. https://doi.org/10.1016/j.sbi.2023.102538

    Article  Google Scholar 

  12. Niu D, Xu L, Pan S et al (2024) Srr-ddi: a drug–drug interaction prediction model with substructure refined representation learning based on self-attention mechanism. Knowl-Based Syst 285:111337. https://doi.org/10.1016/j.knosys.2023.111337

    Article  Google Scholar 

  13. Xu L, Pan S, Xia L et al (2023) Molecular property prediction by combining lstm and gat. Biomolecules 13(3):1–15. https://doi.org/10.3390/biom13030503

    Article  Google Scholar 

  14. Niu D, Zhang L, Zhang B et al (2024) Das-ddi: a dual-view framework with drug association and drug structure for drug–drug interaction prediction. J Biomed Inf 156:104672. https://doi.org/10.1016/j.jbi.2024.104672

    Article  Google Scholar 

  15. Jin Q, Xie J, Huang D et al (2024) Msff-ma-ddi: multi-source feature fusion with multiple attention blocks for predicting drug–drug interaction events. Comput Biol Chem 108:108001. https://doi.org/10.1016/j.compbiolchem.2023.108001

    Article  Google Scholar 

  16. Ryu JY, Kim HU, Lee SY (2018) Deep learning improves prediction of drug–drug and drug–food interactions. Proc Natl Acad Sci 115(18):E4304–E4311. https://doi.org/10.1073/pnas.1803294115

    Article  Google Scholar 

  17. Lee G, Park C, Ahn J (2019) Novel deep learning model for more accurate prediction of drug-drug interaction effects. BMC Bioinf 20:1–8. https://doi.org/10.1186/s12859-019-3013-0

    Article  Google Scholar 

  18. Hou LX, Yi HC, You ZH et al (2024) Matheagle: accurate prediction of drug-drug interaction events via multi-head attention and heterogeneous attribute graph learning. Comput Biol Med 177:108642. https://doi.org/10.1016/j.compbiomed.2024.108642

    Article  Google Scholar 

  19. Song Y, Wang T, Cai P et al (2023) A comprehensive survey of few-shot learning: evolution, applications, challenges, and opportunities. ACM Comput Surv 55(13s):1–40. https://doi.org/10.1145/3582688

    Article  Google Scholar 

  20. Deng Y, Xu X, Qiu Y et al (2020) A multimodal deep learning framework for predicting drug–drug interaction events. Bioinformatics 36(15):4316–4322. https://doi.org/10.1093/bioinformatics/btaa501

    Article  Google Scholar 

  21. He J, Yao L, Li X et al (2024) Model-agnostic generation-enhanced technology for few-shot intrusion detection. Appl Intell 54:1–24. https://doi.org/10.1007/s10489-024-05290-8

    Article  Google Scholar 

  22. Vettoruzzo A, Bouguelia MR, Vanschoren J et al (2024) Advances and challenges in meta-learning: a technical review. IEEE Trans Pattern Anal Mach Intell TPAMI 46(7):4763–4779. https://doi.org/10.1109/TPAMI.2024.3357847

    Article  Google Scholar 

  23. Zhang L, Niu D, Zhang B et al (2024) Property-guided few-shot learning for molecular property prediction with dual-view encoder and relation graph learning network. IEEE J Biomed Health Inf:1–12. https://doi.org/10.1109/JBHI.2024.3381896

  24. Wang Y, Abuduweili A, Yao Q, et al (2021) Property-aware relation networks for few-shot molecular property prediction. In: Ranzato M, Beygelzimer A, Dauphin Y, et al (eds) Proceedings of advances in neural information processing systems, Curran Associates, Inc., vol 34, pp17441–17454

  25. Ju W, Liu Z, Qin Y et al (2023) Few-shot molecular property prediction via hierarchically structured learning on relation graphs. Neural Netw 163:122–131. https://doi.org/10.1016/j.neunet.2023.03.034

    Article  Google Scholar 

  26. Nyamabo AK, Yu H, Shi JY (2021) SSI–DDI: substructure–substructure interactions for drug–drug interaction prediction. Briefings Bioinf 22(6):bbab133. https://doi.org/10.1093/bib/bbab133

  27. Ma M, Lei X (2023) A dual graph neural network for drug–drug interactions prediction based on molecular structure and interactions. PLoS Comput Biol 19(1):1–20. https://doi.org/10.1371/journal.pcbi.1010812

    Article  MathSciNet  Google Scholar 

  28. Ning G, Sun Y, Ling J et al (2023) Bdn-ddi: a bilinear dual-view representation learning framework for drug–drug interaction prediction. Comput Biol Med 165:107340. https://doi.org/10.1016/j.compbiomed.2023.107340

    Article  Google Scholar 

  29. Feng J, Liang Y, Yu T (2023) Mm-gann-ddi: multimodal graph-agnostic neural networks for predicting drug–drug interaction events. Comput Biol Med 166:107492. https://doi.org/10.1016/j.compbiomed.2023.107492

    Article  Google Scholar 

  30. Lv Q, Chen G, Yang Z et al (2023) Meta learning with graph attention networks for low-data drug discovery. IEEE Trans Neural Networks Learn Syst:1–13. https://doi.org/10.1109/TNNLS.2023.3250324

  31. Tian Y, Zou Q, Wang C et al (2024) Mamlcda: a meta-learning model for predicting circrna-disease association based on maml combined with cnn. IEEE J Biomed Health Inf 28(7):4325–4335. https://doi.org/10.1109/JBHI.2024.3385352

    Article  Google Scholar 

  32. Quan H, Li X, Hu D et al (2024) Dual-channel prototype network for few-shot pathology image classification. IEEE J Biomed Health Inf 28(7):4132–4144. https://doi.org/10.1109/JBHI.2024.3386197

    Article  Google Scholar 

  33. Qin A, Yuan C, Li Q et al (2024) Few-shot learning with prototype rectification for cross-domain hyperspectral image classification. IEEE Trans Geosci Remote Sens 62:1–15. https://doi.org/10.1109/TGRS.2024.3414392

  34. Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proc. Int. Conf. Mach. Learn. JMLR.org, ICML’17, p 1126–1135, doi:10.48550/arXiv.1703.03400

  35. Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’17, p 4080–4090, https://doi.org/10.48550/arXiv.1703.05175

  36. Sung F, Yang Y, Zhang L, et al (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199–1208, https://doi.org/10.1109/CVPR.2018.00131

  37. Deng Y, Qiu Y, Xu X, et al (2021) META-DDIE: predicting drug–drug interaction events with few-shot learning. Briefings Bioinf 23(1):bbab514. https://doi.org/10.1093/bib/bbab514

  38. Wishart DS, Knox C, Guo AC, et al (2006) Drugbank: a comprehensive resource for in silico drug discovery and exploration. Nucleic Acids Res 34(suppl_1):D668–D672

  39. Veličković P, Cucurull G, Casanova A, et al (2018) Graph attention networks. In: Proc. Int. Conf. Learn. Represent

  40. Lee J, Lee I, Kang J (2019) Self-attention graph pooling. In: Proc. Int. Conf. Mach. Learn., pmlr, pp 3734–3743

  41. Lin S, Wang Y, Zhang L, et al (2021) MDF-SA-DDI: predicting drug–drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism. Briefings Bioinf 23(1):bbab421. https://doi.org/10.1093/bib/bbab421

  42. Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of Advances in neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’16, p 3844–3852

  43. Xu K, Hu W, Leskovec J, et al (2019) How powerful are graph neural networks? In: Proc. Int. Conf. Learn. Represent., pp 1–17

  44. Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of advances in neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS’17, p 1025–1035

  45. Tezcan S, Yılmaz FN (2024) Clinical pharmacy services in cancer patients with hypertension. Oncologie 26(1):175–178. https://doi.org/10.1515/oncologie-2023-0514

    Article  Google Scholar 

  46. Harbell M, Dumitrascu C, Bettini L et al (2021) Anesthetic considerations for patients on psychotropic drug therapies. Neurol Int 13(4):640–658. https://doi.org/10.3390/neurolint13040062

    Article  Google Scholar 

  47. Santiago LG, Morgado FJ, Baptista MS et al (2020) Hypersensitivity to antibiotics in drug reaction with eosinophilia and systemic symptoms (dress) from other culprits. Contact Dermatitis 82(5):290–296. https://doi.org/10.1111/cod.13462

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (12371491).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Qingdao University, No.308 Ningxia Road, Qingdao, 266071, Shandong, China

    Lianwei Zhang, Dongjiang Niu, Beiyi Zhang, Qiang Zhang & Zhen Li

Authors
  1. Lianwei Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Dongjiang Niu
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Beiyi Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Qiang Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Zhen Li
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Lianwei Zhang: Writing - original draft, Conceptualization, Methodology, Writing - review & editing. Dongjiang Niu: Software, Data curation. Beiyi Zhang: Software, Visualization. Qiang Zhang: Data curation, Validation. Zhen Li: Funding acquisition, Supervision, Writing - review & editing.

Corresponding author

Correspondence to Zhen Li.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, L., Niu, D., Zhang, B. et al. FSRM-DDIE :  few-shot learning methods based on relation metrics for the prediction of drug-drug interaction events. Appl Intell 54, 12081–12094 (2024). https://doi.org/10.1007/s10489-024-05832-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-024-05832-0

Keywords