Predicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization

BackgroundDrug-drug interactions (DDIs) always cause unexpected and even adverse drug reactions. It is important to identify DDIs before drugs are used in the market. However, preclinical identification of DDIs requires much money and time. Computational approaches have exhibited their abilities to predict potential DDIs on a large scale by utilizing pre-market drug properties (e.g. chemical structure). Nevertheless, none of them can predict two comprehensive types of DDIs, including enhancive and degressive DDIs, which increases and decreases the behaviors of the interacting drugs respectively. There is a lack of systematic analysis on the structural relationship among known DDIs. Revealing such a relationship is very important, because it is able to help understand how DDIs occur. Both the prediction of comprehensive DDIs and the discovery of structural relationship among them play an important guidance when making a co-prescription.ResultsIn this work, treating a set of comprehensive DDIs as a signed network, we design a novel model (DDINMF) for the prediction of enhancive and degressive DDIs based on semi-nonnegative matrix factorization. Inspiringly, DDINMF achieves the conventional DDI prediction (AUROC = 0.872 and AUPR = 0.605) and the comprehensive DDI prediction (AUROC = 0.796 and AUPR = 0.579). Compared with two state-of-the-art approaches, DDINMF shows it superiority. Finally, representing DDIs as a binary network and a signed network respectively, an analysis based on NMF reveals crucial knowledge hidden among DDIs.ConclusionsOur approach is able to predict not only conventional binary DDIs but also comprehensive DDIs. More importantly, it reveals several key points about the DDI network: (1) both binary and signed networks show fairly clear clusters, in which both drug degree and the difference between positive degree and negative degree show significant distribution; (2) the drugs having large degrees tend to have a larger difference between positive degree and negative degree; (3) though the binary DDI network contains no information about enhancive and degressive DDIs at all, it implies some of their relationship in the comprehensive DDI matrix; (4) the occurrence of signs indicating enhancive and degressive DDIs is not random because the comprehensive DDI network is equipped with a structural balance.

[1]  Yaoyun Zhang,et al.  Leveraging syntactic and semantic graph kernels to extract pharmacokinetic drug drug interactions from biomedical literature , 2016, BMC Systems Biology.

[2]  Xing-Ming Zhao,et al.  Prediction of Drug Combinations by Integrating Molecular and Pharmacological Data , 2011, PLoS Comput. Biol..

[3]  Ruili Huang,et al.  Comprehensive Characterization of Cytochrome P450 Isozyme Selectivity across Chemical Libraries , 2009, Nature Biotechnology.

[4]  L. Wienkers,et al.  Predicting in vivo drug interactions from in vitro drug discovery data , 2005, Nature Reviews Drug Discovery.

[5]  Jianyu Shi,et al.  Predicting existing targets for new drugs base on strategies for missing interactions , 2016, BMC Bioinformatics.

[6]  Xu Han,et al.  Literature Based Drug Interaction Prediction with Clinical Assessment Using Electronic Medical Records: Novel Myopathy Associated Drug Interactions , 2012, PLoS Comput. Biol..

[7]  J. Koch-weser,et al.  Serum drug concentrations in clinical perspective. , 1981, Therapeutic drug monitoring.

[8]  Chris H. Q. Ding,et al.  Convex and Semi-Nonnegative Matrix Factorizations , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Siu-Ming Yiu,et al.  Predicting Comprehensive Drug-Drug Interactions for New Drugs via Triple Matrix Factorization , 2017, IWBBIO.

[10]  Zhongming Zhao,et al.  Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties. , 2014, Journal of the American Medical Informatics Association : JAMIA.

[11]  Sebastian Polak,et al.  The Role of Interaction Model in Simulation of Drug Interactions and QT Prolongation , 2016, Current Pharmacology Reports.

[12]  Yasen Jiao,et al.  Performance measures in evaluating machine learning based bioinformatics predictors for classifications , 2016, Quantitative Biology.

[13]  Bernhard Schölkopf,et al.  Nonlinear Component Analysis as a Kernel Eigenvalue Problem , 1998, Neural Computation.

[14]  L J Lesko,et al.  Drug Interaction Studies: Study Design, Data Analysis, and Implications for Dosing and Labeling , 2007, Clinical pharmacology and therapeutics.

[15]  Mark A Harris,et al.  Estimating serum concentrations of dioxin-like compounds in the U.S. population effective 2005-2006 and 2007-2008: A multiple imputation and trending approach incorporating NHANES pooled sample data. , 2017, Environment international.

[16]  D. Bates,et al.  Systems analysis of adverse drug events. ADE Prevention Study Group. , 1995, JAMA.

[17]  David S. Wishart,et al.  DrugBank 4.0: shedding new light on drug metabolism , 2013, Nucleic Acids Res..

[18]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[19]  Chris H. Q. Ding,et al.  Symmetric Nonnegative Matrix Factorization for Graph Clustering , 2012, SDM.

[20]  N Al‐Huniti,et al.  Simulation and Prediction of the Drug‐Drug Interaction Potential of Naloxegol by Physiologically Based Pharmacokinetic Modeling , 2016, CPT: pharmacometrics & systems pharmacology.

[21]  Peter M. A. Sloot,et al.  A novel feature-based approach to extract drug-drug interactions from biomedical text , 2014, Bioinform..

[22]  S. D. Jong.  SIMPLS: an alternative approach to partial least squares regression , 1993 .

[23]  Jianying Hu,et al.  Label Propagation Prediction of Drug-Drug Interactions Based on Clinical Side Effects , 2015, Scientific Reports.

[24]  Anna Wolc,et al.  Pharmacokinetic drug‐drug interaction between erlotinib and paracetamol: A potential risk for clinical practice , 2017, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[25]  Jian-Yu Shi,et al.  Predicting drug-target interaction for new drugs using enhanced similarity measures and super-target clustering. , 2015, Methods.

[26]  John Highton,et al.  Giant cell arteritis treatment failure resulting from probable steroid/antiepileptic drug-drug interaction. , 2017, The New Zealand medical journal.

[27]  Tapio Pahikkala,et al.  Toward more realistic drug^target interaction predictions , 2014 .

[28]  George Hripcsak,et al.  Similarity-based modeling in large-scale prediction of drug-drug interactions , 2014, Nature Protocols.

[29]  Ping Zhang,et al.  DDI-CPI, a server that predicts drug–drug interactions through implementing the chemical–protein interactome , 2014, Nucleic Acids Res..

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

[31]  Rita Businaro,et al.  Why We Need an Efficient and Careful Pharmacovigilance , 2013 .

[32]  Siu-Ming Yiu,et al.  LCM-DS: A novel approach of predicting drug-drug interactions for new drugs via Dempster-Shafer theory of evidence , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).