Abstract
Pharmaceutical drug combinations can effectively treat various medical conditions. However, some combinations can cause serious adverse drug reactions (ADR). Therefore, predicting ADRs is an essential and challenging task. Some existing studies rely on single-modal information, such as drug-drug interaction or drug-drug similarity, to predict ADRs. However, those approaches ignore relationships among multi-source information. Other studies predict ADRs using integrated multi-modal drug information; however, such studies generally describe these relations as heterogeneous unsigned networks rather than signed ones. In fact, multi-modal relations of drugs can be classified as positive or negative. If these two types of relations are depicted simultaneously, semantic correlation of drugs in the real world can be predicted effectively. Therefore, in this study, we propose an innovative heterogeneous signed network model called SC-DDIS, to learn drug representations. SC-DDIS integrates multi-modal features, such as drug-drug interactions, drug-protein interactions, drug-chemical interactions, and other heterogeneous information, into drug embedding. Drug embedding means using feature vectors to express drugs. Then, the SC-DDIS model is also used for ADR prediction tasks. First, we fuse heterogeneous drug relations, positive/negative, to obtain a drug-drug interaction signed network (DDISN). Then, inspired by social network, we extend structural balance theory and apply it to DDISN. Using extended structural balance theory, we constrain sign propagation in DDISN. We learn final embedding of drugs by training a graph spectral convolutional neural network. Finally, we train a decoding matrix to decode the drug embedding to predict ADRs. Experimental results demonstrate effectiveness of the proposed model compared to several conventional multi-relational prediction approaches and the state-of-the-art deep learning-based Decagon model.
Similar content being viewed by others
References
A community computational challenge to predict the activity of pairs of compounds. Nature Biotechnology 32(12), 1213–1222
Cami A, Manzi S, Arnold A, Reis BY (2013) Pharmacointeraction network models predict unknown drug-drug interactions. PLOS ONE 8(4):1–9. https://doi.org/10.1371/journal.pone.0061468
Cartwright D, Harary F (1977) Structural balance: A generalization of heider’s theory 1. Soc Netw 63(5):9–25
Çelebi R, Mostafapour V, Yasar E, Gümüs O, Dikenelli O (2015) Prediction of drug-drug interactions using pharmacological similarities of drugs. In: 2015 26th International workshop on database and expert systems applications (DEXA), pp 14–17
Chen X, Liu X, Wu J (2019) Drug-drug interaction prediction with graph representation learning. In: 2019 IEEE International conference on bioinformatics and biomedicine (BIBM), pp 354–361
D’Informatique D, Ese N, Esent P, Au E, Gers F, Hersch P, Esident P, Frasconi P (2001) Long short-term memory in recurrent neural networks. Epfl 9(8):1735–1780
Giacomini KM, Krauss RM, Roden DM, Eichelbaum M, Hayden MR, Nakamura Y (2007) When good drugs go bad. Nature 446(7139):975–977
Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249–256
Han K, Jeng EE, Hess GT, Morgens DW, Li A, Bassik MC (2017) Synergistic drug combinations for cancer identified in a crispr screen for pairwise genetic interactions. Nature Biotechnology
Hu B, Wang H, Wang L, Yuan W (2018) Adverse Drug Reaction Predictions Using Stacking Deep Heterogeneous Information Network Embedding Approach. Molecules. 23(12):3193. https://doi.org/10.3390/molecules23123193. https://www.mdpi.com/1420-3049/23/12/3193
Hu B, Wang H, Yu X, Yuan W, He T (2017) Sparse network embedding for community detection and sign prediction in signed social networks. Journal of Ambient Intelligence & Humanized Computing 10 (1)1–12. https://doi.org/10.1007/s12652-017-0630-1
Huang LC, Wu X, Chen JY (2013) Predicting adverse drug reaction profiles by integrating protein interaction networks with drug structures. Proteomics 13(2):313–324
Jaccard P (1912) The distribution of flora in the alpine zone. N Phytol 11(2):37–50
Jia J, Zhu F, Ma X, Cao ZW, Li YX, Chen YZ (2009) Mechanisms of drug combinations: interaction and network perspectives. Nat Rev Drug Discov 8(6):516–516
Kastrin A, Ferk P, Leskošek B (2018) Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning. PLOS ONE 13(5):1–23. https://doi.org/10.1371/journal.pone.0196865
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. Computer Science
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks
Liu H, Liu B, Zhang H, Li L, Qin X, Zhang G (2018) Crowd evacuation simulation approach based on navigation knowledge and two-layer control mechanism. Inform Sci 436–437:247–267
Liu R, Wang H, Yu X (2018) Shared-nearest-neighbor-based clustering by fast search and find of density peaks. Inform Sci 450:200–226
Liu S, Huang Z, Qiu Y, Chen YP, Zhang W (2019) Structural network embedding using multi-modal deep auto-encoders for predicting drug-drug interactions. In: 2019 IEEE International conference on bioinformatics and biomedicine (BIBM), pp 445–450
Marinka Z, Monica A, Jure L (2018) Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics 34(13):i457–i466
Nickel M, Tresp V, Kriegel HP (2011) A three-way model for collective learning on multi-relational data. In: Proceedings of the 28th international conference on machine learning, ICML 2011, Bellevue, Washington, USA, June 28 - July 2, 2011
Papalexakis EE, Faloutsos C, Sidiropoulos ND (2016) Tensors for Data Mining and Data Fusion: Models, Applications, and Scalable Algorithms. Association for Computing Machinery, New York, NY, USA 8(2) 44. 2157–6904. https://doi.org/10.1145/2915921
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
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’14, 701–710, Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/2623330.2623732
Qin X, Liu H, Zhang H, Liu B (2018) A collective motion model based on two-layer relationship mechanism for bi-direction pedestrian flow simulation. Simul Modell PractTheory 84:268–285
Tang J, Chang Y, Aggarwal C, Liu H (2015) A survey of signed network mining in social media. ACM Computing Surveys
Wang XX, Li JB (2005) Method of computing accessibility matrix from adjacency matrix. Journal of Jilin Institute of Chemical Technology
Zhang W, Chen Y, Liu F, Luo F, Tian G, Li X (2017) Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data. Bmc Bioinformatics 18(1):18
Zheng Y, Peng H, Ghosh S, Lan C, Li J Inverse similarity and reliable negative samples for drug side-effect prediction. BMC Bioinformatics 19(13) 1471–2105. https://doi.org/10.1186/s12859-018-2563-x
Zong N, Hyeoneui K, Victoria N, Olivier H (2017) Deep mining heterogeneous networks of biomedical linked data to predict novel drugtarget associations (15)15. Bioinformatics 33(15):1367–4803. https://doi.org/10.1093/bioinformatics/btx160
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant 61672329 and 81273704, in part by the Project of the Shandong Provincial Project of Education Scientific Plan (No.SDYY18058).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, T., Cui, J., Zhuang, H. et al. Modeling polypharmacy effects with heterogeneous signed graph convolutional networks. Appl Intell 51, 8316–8333 (2021). https://doi.org/10.1007/s10489-021-02296-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02296-4