Predicting Drug-target Interactions via FM-DNN Learning

Author(s): Jihong Wang, Hao Wang, Xiaodan Wang, Huiyou Chang*.

Journal Name: Current Bioinformatics

Volume 15 , Issue 1 , 2020

Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: Identifying Drug-Target Interactions (DTIs) is a major challenge for current drug discovery and drug repositioning. Compared to traditional experimental approaches, in silico methods are fast and inexpensive. With the increase in open-access experimental data, numerous computational methods have been applied to predict DTIs.

Methods: In this study, we propose an end-to-end learning model of Factorization Machine and Deep Neural Network (FM-DNN), which emphasizes both low-order (first or second order) and high-order (higher than second order) feature interactions without any feature engineering other than raw features. This approach combines the power of FM and DNN learning for feature learning in a new neural network architecture.

Results: The experimental DTI basic features include drug characteristics (609), target characteristics (1819), plus drug ID, target ID, total 2430. We compare 8 models such as SVM, GBDT, WIDE-DEEP etc, the FM-DNN algorithm model obtains the best results of AUC(0.8866) and AUPR(0.8281).

Conclusion: Feature engineering is a job that requires expert knowledge, it is often difficult and time-consuming to achieve good results. FM-DNN can auto learn a lower-order expression by FM and a high-order expression by DNN.FM-DNN model has outstanding advantages over other commonly used models.

Keywords: Drug-target interactions, prediction, factorization machines, DNN learning, machine learning, drug bank.

[1]
Zhang J, Zhu M, Chen P, et al. DrugRPE: Random projection ensemble approach to drug-target interaction prediction. Neurocomputing 2017; 228: 256-62.
[http://dx.doi.org/10.1016/j.neucom.2016.10.039]
[2]
Cao DS, Zhang LX, Tan GS, et al. Computational prediction of drug target interactions using chemical, biological, and network features. Mol Inform 2014; 33(10): 669-81.
[http://dx.doi.org/10.1002/minf.201400009] [PMID: 27485302]
[3]
Wen M, Zhang Z, Niu S, et al. Deep-Learning-based drug-target interaction prediction. J Proteome Res 2017; 16(4): 1401-9.
[http://dx.doi.org/10.1021/acs.jproteome.6b00618] [PMID: 28264154]
[4]
Ashburn TT, Thor KB. Drug repositioning: identifying and developing new uses for existing drugs. Nat Rev Drug Discov 2004; 3(8): 673-83.
[http://dx.doi.org/10.1038/nrd1468] [PMID: 15286734]
[5]
Rayhan F, Ahmed S, Shatabda S, et al. Rahman MS. iDTIESBoost. Identification of drug target interaction using evolutionary and structural features with boosting 2017; 7: 17731.
[http://dx.doi.org/10.1038/s41598-017-18025-2] [PMID: 29255285]
[6]
Cheng T, Hao M, Takeda T, Bryant SH, Wang Y. Large-Scale prediction of drug-target interaction: a Data-centric review. AAPS J 2017; 19(5): 1264-75.
[http://dx.doi.org/10.1208/s12248-017-0092-6] [PMID: 28577120]
[7]
Mousavian Z, Masoudi-Nejad A. Drug-target interaction prediction via chemogenomic space: learning-based methods. Expert Opin Drug Metab Toxicol 2014; 10(9): 1273-87.
[http://dx.doi.org/10.1517/17425255.2014.950222] [PMID: 25112457]
[8]
Yamanishi Y, Kotera M, Kanehisa M, Goto S. Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework. Bioinformatics 2010; 26(12): i246-54.
[http://dx.doi.org/10.1093/bioinformatics/btq176] [PMID: 20529913]
[9]
Chen YZ, Zhi DG. Ligand-protein inverse docking and its potential use in the computer search of protein targets of a small molecule. Proteins 2001; 43(2): 217-26.
[http://dx.doi.org/10.1002/1097-0134(20010501)43:2<217:AID-PROT1032>3.0.CO;2-G] [PMID: 11276090]
[10]
Periole X, Knepp AM, Sakmar TP, Marrink SJ, Huber T. Structural determinants of the supramolecular organization of G protein-coupled receptors in bilayers. J Am Chem Soc 2012; 134(26): 10959-65.
[http://dx.doi.org/10.1021/ja303286e] [PMID: 22679925]
[11]
Li ZC, Zhong WQ, Liu ZQ, et al. Large-scale identification of potential drug targets based on the topological features of human protein-protein interaction network. Anal Chim Acta 2015; 871: 18-27.
[http://dx.doi.org/10.1016/j.aca.2015.02.032] [PMID: 25847157]
[12]
Ba-Alawi W, Soufan O, Essack M, Kalnis P, Bajic VB. DASPfind: new efficient method to predict drug-target interactions. J Cheminform 2016; 8(1): 15.
[http://dx.doi.org/10.1186/s13321-016-0128-4] [PMID: 26985240]
[13]
Chen X, Liu MX, Yan GY. Drug-target interaction prediction by random walk on the heterogeneous network. Mol Biosyst 2012; 8(7): 1970-8.
[http://dx.doi.org/10.1039/c2mb00002d] [PMID: 22538619]
[14]
Chen H, Zhang Z. A semi-supervised method for drug-target interaction prediction with consistency in networks. PLoS One 2013; 8(5) e62975
[http://dx.doi.org/10.1371/journal.pone.0062975] [PMID: 23667553]
[15]
Zhao S, Li S. Network-based relating pharmacological and genomic spaces for drug target identification. PLoS One 2010; 5(7) e117640
[http://dx.doi.org/10.1371/journal.pone.0011764] [PMID: 20668676]
[16]
Cheng F, Zhou Y, Li W, Liu G, Tang Y. Prediction of chemical-protein interactions network with weighted network-based inference method. PLoS One 2012; 7(7) e41064
[http://dx.doi.org/10.1371/journal.pone.0041064] [PMID: 22815915]
[17]
Niu YQ. Supervised prediction of drug-target interactions by ensemble learning. J Chem Pharm Res 2014; 6(7): 1991-9.
[18]
Zhao JIE, Cao ZHI. A Label Extended Semi-supervised Learning Method for Drug-target Interaction Prediction. International Conference on Automation, Mechanical Control and Computational Engineering. 1635-40.
[19]
Deng NY, Wang Y, Yang ZX, et al. Computationally probing drug-protein interactions via support vector machine. Lett Drug Des Discov 2010; 7(5): 370-8.
[http://dx.doi.org/10.2174/157018010791163433]
[20]
Guo H, Tang R, Ye Y, et al. DeepFM: A factorization-machine based neural network for CTR prediction. International Joint Conference on Artificial Intelligence. 1725-31.
[http://dx.doi.org/10.24963/ijcai.2017/239]
[21]
Cheng HT, Koc L, Harmsen J, et al. Wide & Deep Learning for Recommender Systems. The 1st Workshop on Deep Learning for Recommender Systems. ACM New York 2016.9:7-10.
[22]
Cao DS, Liang YZ, Yan J, Tan GS, Xu QS, Liu S. PyDPI: freely available python package for chemoinformatics, bioinformatics, and chemogenomics studies. J Chem Inf Model 2013; 53(11): 3086-96.
[http://dx.doi.org/10.1021/ci400127q] [PMID: 24047419]
[23]
Rendle S. Factorization machines. International Conference on Data Mining. 995-1000.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 15
ISSUE: 1
Year: 2020
Page: [68 - 76]
Pages: 9
DOI: 10.2174/1574893614666190227160538
Price: $65

Article Metrics

PDF: 22
HTML: 5
EPUB: 1
PRC: 1