DeepDrug: A general graph-based deep learning framework for drug-drug interactions and drug-target interactions prediction

Computational approaches for accurate predictions of drug-related interactions such as drug-drug interactions (DDIs) and drug-target interactions (DTIs) are highly demanding for biochemical researchers due to their efficiency and cost-effectiveness. Despite the fact that many methods have been proposed and developed to predict DDIs and DTIs respectively, their success is still limited due to a lack of systematic evaluation of the intrinsic properties embedded in their structure. In this paper, we develop a deep learning framework, named DeepDrug, to overcome these shortcomings by using graph convolutional networks to learn the graphical representations of drugs and proteins such as molecular fingerprints and residual structures in order to boost the prediction accuracy. We benchmark our methods in binary-class DDIs, multi-class DDIs and binary-class DTIs classification tasks using several datasets. We then demonstrate that DeepDrug outperforms other state-of-the-art published methods both in terms of accuracy and robustness in predicting DDIs and DTIs with varying ratios of positive to negative training data. Ultimately, we visualize the structural features learned by DeepDrug, which display compatible and accordant patterns in chemical properties, providing additional evidence to support the strong predictive power of DeepDrug. We believe that DeepDrug is an efficient tool in accurate prediction of DDIs and DTIs and provides a promising path in understanding the underlying mechanism of these biochemical relations. The source code of the DeepDrug can be downloaded from https://github.com/wanwenzeng/deepdrug.

[1]  Makoto Miwa,et al.  Enhancing Drug-Drug Interaction Extraction from Texts by Molecular Structure Information , 2018, ACL.

[2]  Jian Peng,et al.  A Network Integration Approach for Drug-Target Interaction Prediction and Computational Drug Repositioning from Heterogeneous Information , 2017, RECOMB 2017.

[3]  Jure Leskovec,et al.  Modeling polypharmacy side effects with graph convolutional networks , 2018, bioRxiv.

[4]  Jae Yong Ryu,et al.  Deep learning improves prediction of drug–drug and drug–food interactions , 2018, Proceedings of the National Academy of Sciences.

[5]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[6]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[7]  Artem Cherkasov,et al.  PADME: A Deep Learning-based Framework for Drug-Target Interaction Prediction , 2018, ArXiv.

[8]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[9]  Silvia Crivelli,et al.  Structural Learning of Proteins Using Graph Convolutional Neural Networks , 2019, bioRxiv.

[10]  Zhiwei Cao,et al.  Combining genomic and network characteristics for extended capability in predicting synergistic drugs for cancer , 2015, Nature Communications.

[11]  Jennie Chang,et al.  Cerivastatin and reports of fatal rhabdomyolysis. , 2002, The New England journal of medicine.

[12]  Alex Fout,et al.  Protein Interface Prediction using Graph Convolutional Networks , 2017, NIPS.

[13]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[14]  Ali Masoudi-Nejad,et al.  Drug–target interaction prediction via chemogenomic space: learning-based methods , 2014, Expert opinion on drug metabolism & toxicology.

[15]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[16]  Károly Héberger,et al.  Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? , 2015, Journal of Cheminformatics.

[17]  Evan Bolton,et al.  PubChem 2019 update: improved access to chemical data , 2018, Nucleic Acids Res..

[18]  Paloma Martínez,et al.  SemEval-2013 Task 9 : Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013) , 2013, *SEMEVAL.

[19]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[20]  Dexter Hadley,et al.  Systematic integration of biomedical knowledge prioritizes drugs for repurposing , 2017, bioRxiv.

[21]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[22]  Ying Liu,et al.  Deep learning for drug-drug interaction extraction from the literature: a review , 2020, Briefings Bioinform..

[23]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[24]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[25]  Xiaohua Ma,et al.  Mechanisms of drug combinations: interaction and network perspectives , 2009, Nature Reviews Drug Discovery.

[26]  Bo Wang,et al.  Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities , 2018, Inf. Fusion.

[27]  David S. Goodsell,et al.  RCSB Protein Data Bank: biological macromolecular structures enabling research and education in fundamental biology, biomedicine, biotechnology and energy , 2018, Nucleic Acids Res..

[28]  P. Corey,et al.  Incidence of Adverse Drug Reactions in Hospitalized Patients , 2012 .

[29]  T. Meinertz.  Mibefradil : a drug which may enhance the propensity for the development of abnormal QT prolongation , 2001 .

[30]  Hui Yang,et al.  A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories , 2020, Nat. Mach. Intell..

[31]  Lukasz Kurgan,et al.  Survey of Similarity-based Prediction of Drug-protein Interactions. , 2018, Current medicinal chemistry.

[32]  David S. Wishart,et al.  DrugBank: a comprehensive resource for in silico drug discovery and exploration , 2005, Nucleic Acids Res..

[33]  Yoshihiro Yamanishi,et al.  Prediction of drug–target interaction networks from the integration of chemical and genomic spaces , 2008, ISMB.

[34]  T. Ohshima,et al.  Stimulated emission from nitrogen-vacancy centres in diamond , 2016, Nature Communications.

[35]  Yang Xie,et al.  A community computational challenge to predict the activity of pairs of compounds Citation , 2015 .

[36]  Yoshihiro Yamanishi,et al.  Supervised prediction of drug–target interactions using bipartite local models , 2009, Bioinform..

[37]  Kayvan Najarian,et al.  Machine learning approaches and databases for prediction of drug–target interaction: a survey paper , 2020, Briefings Bioinform..

[38]  P. Barry,et al.  Inappropriate prescribing in an acutely ill population of elderly patients as determined by Beers' Criteria. , 2008, Age and ageing.

[39]  D. Gudbjartsson,et al.  Variants in ELL2 influencing immunoglobulin levels associate with multiple myeloma , 2015, Nature Communications.

[40]  Paloma Martínez,et al.  The DDI corpus: An annotated corpus with pharmacological substances and drug-drug interactions , 2013, J. Biomed. Informatics.

[41]  G. Muirhead,et al.  Sildenafil: an orally active type 5 cyclic GMP-specific phosphodiesterase inhibitor for the treatment of penile erectile dysfunction. , 1996, International journal of impotence research.

[42]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[43]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[44]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[45]  Arzucan Özgür,et al.  DeepDTA: deep drug–target binding affinity prediction , 2018, Bioinform..

[46]  Herrero-ZazoMaría,et al.  The DDI corpus , 2013 .

[47]  Gaelen T. Hess,et al.  Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions , 2017, Nature Biotechnology.

[48]  R. Altman,et al.  Data-Driven Prediction of Drug Effects and Interactions , 2012, Science Translational Medicine.