Discovering Links Between Side Effects and Drugs Using a Diffusion Based Method

Identifying the unintended effects of drugs (side effects) is a very important issue in pharmacological studies. The laboratory verification of associations between drugs and side effects requires costly, time-intensive research. Thus, an approach to predicting drug side effects based on known side effects, using a computational model, is highly desirable. To provide such a model, we used openly available data resources to model drugs and side effects as a bipartite graph. The drug-drug network is constructed using the word2vec model where the edges between drugs represent the semantic similarity between them. We integrated the bipartite graph and the semantic similarity graph using a matrix factorization method and a diffusion based model. Our results show the effectiveness of this integration by computing weighted (i.e., ranked) predictions of initially unknown links between side effects and drugs.

[1]  Bart De Moor,et al.  Candidate gene prioritization by network analysis of differential expression using machine learning approaches , 2010, BMC Bioinformatics.

[2]  Jon M. Kleinberg,et al.  The link-prediction problem for social networks , 2007, J. Assoc. Inf. Sci. Technol..

[3]  Eduard Ayguadé,et al.  Limitations and Alternatives for the Evaluation of Large-scale Link Prediction , 2016, ArXiv.

[4]  S. R. Fine,et al.  ADVERSE DRUG REACTIONS , 2009, BMJ : British Medical Journal.

[5]  Michael R. Lyu,et al.  Mining social networks using heat diffusion processes for marketing candidates selection , 2008, CIKM '08.

[6]  Fillia Makedon,et al.  Learning from Incomplete Ratings Using Non-negative Matrix Factorization , 2006, SDM.

[7]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[8]  Sebastian Schneeweiss,et al.  Admissions caused by adverse drug events to internal medicine and emergency departments in hospitals: a longitudinal population-based study , 2002, European Journal of Clinical Pharmacology.

[9]  Pushpraj Shukla,et al.  Early identification of adverse drug reactions from search log data , 2016, J. Biomed. Informatics.

[10]  Fan Chung,et al.  The heat kernel as the pagerank of a graph , 2007, Proceedings of the National Academy of Sciences.

[11]  A. Fliri,et al.  Analysis of drug-induced effect patterns to link structure and side effects of medicines , 2005, Nature chemical biology.

[12]  Inderjit S. Dhillon,et al.  Generalized Nonnegative Matrix Approximations with Bregman Divergences , 2005, NIPS.

[13]  Ted Pedersen,et al.  Measures of semantic similarity and relatedness in the biomedical domain , 2007, J. Biomed. Informatics.

[14]  Munir Pirmohamed,et al.  Fortnightly review: Adverse drug reactions , 1998 .

[15]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[16]  Xiaojun Wu,et al.  Graph Regularized Nonnegative Matrix Factorization for Data Representation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Michael R. Lyu,et al.  DiffusionRank: a possible penicillin for web spamming , 2007, SIGIR.

[18]  Yi-Cheng Zhang,et al.  Heat conduction process on community networks as a recommendation model. , 2007, Physical review letters.

[19]  J. Delvenne,et al.  Random walks on graphs , 2004 .

[20]  Yang Xie,et al.  A community computational challenge to predict the activity of pairs of compounds , 2014, Nature Biotechnology.

[21]  Bin Chen,et al.  Gaining Insight into Off-Target Mediated Effects of Drug Candidates with a Comprehensive Systems Chemical Biology Analysis , 2009, J. Chem. Inf. Model..

[22]  Xing Chen,et al.  NLLSS: Predicting Synergistic Drug Combinations Based on Semi-supervised Learning , 2016, PLoS Comput. Biol..

[23]  Zhu-Hong You,et al.  A heterogeneous label propagation approach to explore the potential associations between miRNA and disease , 2018, Journal of Translational Medicine.

[24]  F. Göbel,et al.  Random walks on graphs , 1974 .

[25]  Zhiyong Lu,et al.  A survey of current trends in computational drug repositioning , 2016, Briefings Bioinform..

[26]  Benjamin J. Raphael,et al.  Network propagation: a universal amplifier of genetic associations , 2017, Nature Reviews Genetics.

[27]  A. Butte,et al.  Predicting Adverse Drug Reactions Using Publicly Available PubChem BioAssay Data , 2011, Clinical pharmacology and therapeutics.

[28]  M. Weiss,et al.  Trends in emergency hospital admissions in England due to adverse drug reactions: 2008–2015 , 2017 .

[29]  Xing Chen,et al.  Drug-target interaction prediction by random walk on the heterogeneous network. , 2012, Molecular bioSystems.

[30]  Jung-Hsien Chiang,et al.  Detecting Potential Adverse Drug Reactions Using a Deep Neural Network Model , 2019, Journal of medical Internet research.

[31]  Alexander E. Ivliev,et al.  Drug Target Prediction and Repositioning Using an Integrated Network-Based Approach , 2013, PloS one.

[32]  Wenjun Wang,et al.  A unified framework for link prediction based on non-negative matrix factorization with coupling multivariate information , 2018, PloS one.

[33]  Nitesh V. Chawla,et al.  Evaluating link prediction methods , 2014, Knowledge and Information Systems.

[34]  Vít Novácek,et al.  Using Drug Similarities for Discovery of Possible Adverse Reactions , 2016, AMIA.

[35]  Jia Qu,et al.  RFSMMA: A New Computational Model to Identify and Prioritize Potential Small Molecule-MiRNA Associations , 2019, J. Chem. Inf. Model..

[36]  Jure Leskovec,et al.  Predicting multicellular function through multi-layer tissue networks , 2017, Bioinform..

[37]  Xing Chen,et al.  Inferring potential small molecule–miRNA association based on triple layer heterogeneous network , 2018, Journal of Cheminformatics.

[38]  Yoshihiro Yamanishi,et al.  Drug Side-Effect Prediction Based on the Integration of Chemical and Biological Spaces , 2012, J. Chem. Inf. Model..

[39]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[40]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[41]  Ling Chen,et al.  Link prediction based on non-negative matrix factorization , 2017, PloS one.

[42]  George Hripcsak,et al.  Detection of drug‐drug interactions through data mining studies using clinical sources, scientific literature and social media , 2018, Briefings Bioinform..

[43]  Charles Elkan,et al.  Link Prediction via Matrix Factorization , 2011, ECML/PKDD.

[44]  Yifan Jia,et al.  Predicting links based on knowledge dissemination in complex network , 2017 .

[45]  Philip E. Bourne,et al.  Drug Discovery Using Chemical Systems Biology: Identification of the Protein-Ligand Binding Network To Explain the Side Effects of CETP Inhibitors , 2009, PLoS Comput. Biol..

[46]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

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

[48]  Guido Zuccon,et al.  Medical Semantic Similarity with a Neural Language Model , 2014, CIKM.

[49]  Pascal Frossard,et al.  Learning Heat Diffusion Graphs , 2016, IEEE Transactions on Signal and Information Processing over Networks.

[50]  D. Bojanic,et al.  Keynote review: in vitro safety pharmacology profiling: an essential tool for successful drug development. , 2005, Drug discovery today.

[51]  Xing Chen,et al.  MicroRNA-small molecule association identification: from experimental results to computational models , 2018, Briefings Bioinform..