Document Type : Applied Article


1 School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.

2 School of Computer engineering, Iran University of Science and Technology, Tehran, Iran.


The search for effective treatments for complex diseases, while minimizing toxicity and side effects, has become crucial. However, identifying synergistic combinations of drugs is often a time-consuming and expensive process, relying on trial and error due to the vast search space involved. Addressing this issue, we present a deep learning framework in this study. Our framework utilizes a diverse set of features, including chemical structure, biomedical literature embedding, and biological network interaction data, to predict potential synergistic combinations. Additionally, we employ autoencoders and principal component analysis (PCA) for dimension reduction in sparse data. Through 10-fold cross-validation, we achieved an impressive 98 percent area under the curve (AUC), surpassing the performance of seven previous state-of-the-art approaches by an average of 8%.


Main Subjects

[1] D. Chen, X. Liu, Y. Yang, H. Yang, P. Lu, "Systematic synergy modeling: understanding drug synergy from a systems biology perspective," BMC systems biology, 2015.
[2] B. He, C. Lu, G. Zheng, X. He, M. Wang, G. Chen, G. Zhang, A. Lu, "Combination therapeutics in complex diseases," Journal of Cellular and Molecular Medicine, 2016.
[3] T. C. Chou, "Theoretical basis, experimental design, and computerized simulation of synergism and antagonism in drug combination studies," Pharmacological reviews, 2006.
[4] F. Cheng, I. A. Kovács, A. L. Barabási, "Network-based prediction of drug combinations," Nature communications, 2019.
[5] L. Wu, Y. Wen, D. Leng, Q. Zhang, C. Dai, Z. Wang, Z. Liu, B. Yan, Y. Zhang, J. Wang, S. He, "Machine learning methods, databases and tools for drug combination prediction," Briefings in bioinformatics, 2022.
[6] R. G. Zinner, B. L. Barrett, E. Popova, P. Damien, A. Y. Volgin, J. G. Gelovani, R. Lotan, H. T. Tran, C. Pisano, G. B. Mills, L. Mao, "Algorithmic guided screening of drug combinations of arbitrary size for activity against cancer cells," Molecular cancer therapeutics, 2009.
[7] J. Y. Shi, J. X. Li, K. T. Mao, J. B. Cao, P. Lei, H. M. Lu, S. M. Yiu, "Predicting combinative drug pairs via multiple classifier system with positive samples only," Computer methods and programs in biomedicine, 2019.
[8] L. Y. Bai, H. Dai, Q. Xu, M. Junaid, S. L. Peng, X. Zhu, Y. Xiong, D. Q. Wei, "Prediction of effective drug combinations by an improved naïve bayesian algorithm," International journal of molecular sciences, 2018.
[9] J. Li, X. Y. Tong, L. D. Zhu, H. Y. Zhang, "A machine learning method for drug combination prediction," Frontiers in Genetics, 2020.
[10] "PubMed," [Online]. Available:
[11] K. Traynor, FDA approves four-drug anti-HIV combination tablet, Oxford University Press, 2012.
[12] B. Al-Lazikani, U. Banerji, P. Workman, "Combinatorial drug therapy for cancer in the post-genomic era," Nature biotechnology, 2012
[13] E. Guney, J. Menche, M. Vidal, A. L. Barábasi, "Network-based in silico drug efficacy screening," Nature communications, 2016.
[14] H. Chen, S. K. Iyengar, J. Li, "Large-scale analysis of drug combinations by integrating multiple heterogeneous information networks," in InProceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2019.
[15] T. Hastie, R. Tibshirani, J. H. Friedman, J. H. Friedman, The elements of statistical learning: data mining, inference, and prediction, 2009, springer.
[16] V. Y. Tan, C. Févotte, "Tan VY, Févotte C. Automatic relevance determination in nonnegative matrix factorization with the/spl beta/-divergence," IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012.
[17] L. Huang, F. Li, J. Sheng, X. Xia, J. Ma, M. Zhan, S. T. Wong, "DrugComboRanker: drug combination discovery based on target network analysis," Bioinformatics, 2014.
[18] D. Chen, H. Zhang, P. Lu, X. Liu, H. Cao, "Synergy evaluation by a pathway--pathway interaction network: a new way to predict drug combination," Molecular BioSystems, 2016.
[19] Y. Sun, Z. Sheng, C. Ma, K. Tang, R. Zhu, Z. Wu, R. Shen, J. Feng, D. Wu, D. Huang, D. Huang, "Combining genomic and network characteristics for extended capability in predicting synergistic drugs for cancer," Nature communications, 2015.
[20] X. Chen, B. Ren, M. Chen, Q. Wang, L. Zhang, G. Yan, "NLLSS: predicting synergistic drug combinations based on semi-supervised learning," PLoS computational biology, 2016.
[21] H. Liu, W. Zhang, L. Nie, X. Ding, J. Luo, L. Zou, "Predicting effective drug combinations using gradient tree boosting based on features extracted from drug-protein heterogeneous network," BMC bioinformatics, 2019.
[22] P. Sidorov, S. Naulaerts, J. Ariey-Bonnet, E. Pasquier, P. J. Ballester, "Predicting synergism of cancer drug combinations using NCI-ALMANAC data," Frontiers in chemistry, 2019.
[23] C. Zhang, G. Yan, "Synergistic drug combinations prediction by integrating pharmacological data," Synthetic and systems biotechnology, 2019.
[24] Y. Juan, Y. Zhuang, W. S. Chin, C. J. Lin, "Field-aware factorization machines for CTR prediction," in InProceedings of the 10th ACM conference on recommender systems, 2016.
[25] H. Julkunen, A. Cichonska, P. Gautam, S. Szedmak, J. Douat, T. Pahikkala, T. Aittokallio, J. Rousu, "comboFM: leveraging multi-way interactions for systematic prediction of drug combination effects," bioRxiv, 2020.
[26] A. Ianevski, A. K. Giri, P. Gautam, A. Kononov, S. Potdar, J. Saarela, K. Wennerberg, T. Aittokallio, "Prediction of drug combination effects with a minimal set of experiments," Nature machine intelligence, 2019
[27] K. Preuer, R. P. Lewis, S. Hochreiter, A. Bender, K. C. Bulusu, G. Klambauer, "DeepSynergy: predicting anti-cancer drug synergy with Deep Learning," Bioinformatics, 2018.
[28] F. Xia, M. Shukla, T. Brettin, C. Garcia-Cardona, J. Cohn, .J. E. Allen, S. Maslov, S. L. Holbeck, J. H. Doroshow, Y. A. Evrard, E. A. Stahlberg, "Predicting tumor cell line response to drug pairs with deep learning," BMC bioinformatics, 2018.
[29] T. Zhang, L. Zhang, .P. R. Payne, F. Li, "Synergistic drug combination prediction by integrating multiomics data in deep learning models," in InTranslational bioinformatics for therapeutic development, 2021.
[30] H. I. Kuru, O. Tastan, A. E. Cicek, "MatchMaker: a deep learning framework for drug synergy prediction," IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2021.
[31] P. Jiang, S. Huang, Z. Fu, Z. Sun, T. M. Lakowski, P. Hu, "Deep graph embedding for prioritizing synergistic anticancer drug combinations," Computational and structural biotechnology journal, 2020.
[32] S. Forrest, "Genetic algorithms: principles of natural selection applied to computation," Science, 1993.
[33] N. Yin, W. Ma, J. Pei, Q. Ouyang, C. Tang, L. Lai, "Synergistic and antagonistic drug combinations depend on network topology," PloS one, 2014.
[34] A. C. Nascimento, R. B. Prudêncio, I. G. Costa, "A multiple kernel learning algorithm for drug-target interaction prediction," BMC bioinformatics, 2016.
[35] T. Chen, C. Guestrin, "Xgboost: A scalable tree boosting system," in InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016.
[36] Z. Wu, X. M. Zhao, L. Chen, "A systems biology approach to identify effective cocktail drugs," in InBMC systems biology, 2010.
[37] I. F. Tsigelny, "Artificial intelligence in drug combination therapy," Briefings in bioinformatics, 2019.
[38] Y. Liu, Q. Wei, G. Yu, W. Gai, Y. Li, X. Chen, "DCDB 2.0: a major update of the drug combination database," Database, 2014.
[39] M. Kuhn, I. Letunic, L. J. Jensen, P. Bork, "The SIDER database of drugs and side effects," Nucleic acids research, 2016.
[40] D. Weininger, "SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules," Journal of chemical information and computer sciences, 1988.
[41] M. Allahgholi, H. Rahmani, D. Javdani , G. Weiss, D. Módos, "ADDI: Recommending alternatives for drug--drug interactions with negative health effects," Computers in Biology and Medicine, 2020.
[42] T. Mikolov, K. Chen, G. Corrado, L. Dean, "Efficient estimation of word representations in vector space," arXiv preprint arXiv:1301.3781, 2013.
[43] M. A. Kramer, "Nonlinear principal component analysis using autoassociative neural networks," AIChE journal, 1991.
[44] M. Li, Y. Wang, R. Zheng, X. Shi, Y. Li, F. X. Wu, J. Wang, "DeepDSC: a deep learning method to predict drug sensitivity of cancer cell lines," IEEE/ACM transactions on computational biology and bioinformatics, 2019.
[45] L. Prechelt, "Automatic early stopping using cross validation: quantifying the criteria," Neural Networks, 1998.
[46] Q. Xu, Y. Xiong, H. Dai, K. M. Kumari, Q. Xu, H. Y. Ou, D. Q. Wei, "PDC-SGB: Prediction of effective drug combinations using a stochastic gradient boosting algorithm," Journal of theoretical biology, 2017.
[47] G. Su, A. Kuchinsky, J. H. Morris, D. J. States, F. Meng, "GLay: community structure analysis of biological networks," Bioinformatics, 2010.
[48] O. Oladimeji, O. Oladimeji, "Detecting Breast Cancer through Blood Analysis Data using Classification Algorithms," Journal of AI and Data Mining, 2021.