Positive-Unlabeled Learning for inferring drug interactions based on heterogeneous attributes

BackgroundInvestigating and understanding drug-drug interactions (DDIs) is important in improving the effectiveness of clinical care. DDIs can occur when two or more drugs are administered together. Experimentally based DDI detection methods require a large cost and time. Hence, there is a great interest in developing efficient and useful computational methods for inferring potential DDIs. Standard binary classifiers require both positives and negatives for training. In a DDI context, drug pairs that are known to interact can serve as positives for predictive methods. But, the negatives or drug pairs that have been confirmed to have no interaction are scarce. To address this lack of negatives, we introduce a Positive-Unlabeled Learning method for inferring potential DDIs.ResultsThe proposed method consists of three steps: i) application of Growing Self Organizing Maps to infer negatives from the unlabeled dataset; ii) using a pairwise similarity function to quantify the overlap between individual features of drugs and iii) using support vector machine classifier for inferring DDIs. We obtained 6036 DDIs from DrugBank database. Using the proposed approach, we inferred 589 drug pairs that are likely to not interact with each other; these drug pairs are used as representative data for the negative class in binary classification for DDI prediction. Moreover, we classify the predicted DDIs as Cytochrome P450 (CYP) enzyme-Dependent and CYP-Independent interactions invoking their locations on the Growing Self Organizing Map, due to the particular importance of these enzymes in clinically significant interaction effects. Further, we provide a case study on three predicted CYP-Dependent DDIs to evaluate the clinical relevance of this study.ConclusionOur proposed approach showed an absolute improvement in F1-score of 14 and 38% in comparison to the method that randomly selects unlabeled data points as likely negatives, depending on the choice of similarity function. We inferred 5300 possible CYP-Dependent DDIs and 592 CYP-Independent DDIs with the highest posterior probabilities. Our discoveries can be used to improve clinical care as well as the research outcomes of drug development.

[1]  Marc C. Nicklaus,et al.  QSAR Modeling and Prediction of Drug-Drug Interactions. , 2016, Molecular pharmaceutics.

[2]  H P Rang,et al.  Comprar Rang & Dale's Pharmacology, 7th Edition with STUDENT CONSULT Online Access | Graeme Henderson | 9780702034718 | Churchill Livingstone , 2011 .

[3]  Young-Seuk Park,et al.  Self-Organizing Map , 2008 .

[4]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[5]  Artem Sokolov,et al.  One-Class Detection of Cell States in Tumor Subtypes , 2016, PSB.

[6]  Ping Zhang,et al.  Exploring the associations between drug side-effects and therapeutic indications , 2014, J. Biomed. Informatics.

[7]  Jinyan Li,et al.  Positive-unlabeled learning for the prediction of conformational B-cell epitopes , 2015, BMC Bioinformatics.

[8]  Bala Srinivasan,et al.  Dynamic self-organizing maps with controlled growth for knowledge discovery , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9]  Michael J. Sorich,et al.  Cytochrome P450 Part 1: Multiplicity and Function , 2008 .

[10]  Philip S. Yu,et al.  Positive and Unlabeled Learning for Graph Classification , 2011, 2011 IEEE 11th International Conference on Data Mining.

[11]  Marinka Zitnik,et al.  Collective Pairwise Classification for Multi-Way Analysis of Disease and Drug Data , 2016, PSB.

[12]  Julie B Wahlang,et al.  DRUG INTERACTIONS AND ADVERSE DRUG REACTIONS – A BRIEF CLINICAL GUIDE , 2018 .

[13]  Chitta Baral,et al.  Discovering drug–drug interactions: a text-mining and reasoning approach based on properties of drug metabolism , 2010, Bioinform..

[14]  George Hripcsak,et al.  Improving Detection of Arrhythmia Drug-Drug Interactions in Pharmacovigilance Data through the Implementation of Similarity-Based Modeling , 2015, PloS one.

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

[16]  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.

[17]  Xiaoli Li,et al.  Learning to Classify Texts Using Positive and Unlabeled Data , 2003, IJCAI.

[18]  H P Rang,et al.  Rang and Dale's pharmacology , 2012 .

[19]  Russ B. Altman,et al.  A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports , 2012, J. Am. Medical Informatics Assoc..

[20]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[21]  R. Sharan,et al.  INDI: a computational framework for inferring drug interactions and their associated recommendations , 2012, Molecular systems biology.

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

[23]  Lai Wei,et al.  Analysis and prediction of drug–drug interaction by minimum redundancy maximum relevance and incremental feature selection , 2017, Journal of biomolecular structure & dynamics.

[24]  David S. Wishart,et al.  DrugBank: a knowledgebase for drugs, drug actions and drug targets , 2007, Nucleic Acids Res..

[25]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[26]  Lei Yang,et al.  Classification of Cytochrome P450 Inhibitors and Noninhibitors Using Combined Classifiers , 2011, J. Chem. Inf. Model..

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

[28]  Thomas M. Polasek,et al.  Drug interactions: principles and practice , 2012 .

[29]  P. Bork,et al.  A side effect resource to capture phenotypic effects of drugs , 2010, Molecular systems biology.

[30]  Simone Rossi,et al.  Australian Medicines Handbook , 2012 .

[31]  Edward H. Lee.  American society of health-system pharmacists. , 2011, P & T : a peer-reviewed journal for formulary management.

[32]  Zhiyong Lu,et al.  A new method for computational drug repositioning using drug pairwise similarity , 2012, 2012 IEEE International Conference on Bioinformatics and Biomedicine.

[33]  Carol Friedman,et al.  Drug-drug interaction through molecular structure similarity analysis , 2012, J. Am. Medical Informatics Assoc..

[34]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

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

[36]  Saman K. Halgamuge,et al.  BMC Bioinformatics BioMed Central Methodology article Binning sequences using very sparse labels within a metagenome , 2008 .

[37]  P. Bork,et al.  Drug Target Identification Using Side-Effect Similarity , 2008, Science.

[38]  Xing-Ming Zhao,et al.  Gene function prediction using labeled and unlabeled data , 2008, BMC Bioinformatics.

[39]  Hongkang Mei,et al.  Systematic Prediction of Pharmacodynamic Drug-Drug Interactions through Protein-Protein-Interaction Network , 2013, PLoS Comput. Biol..

[40]  Joel Dudley,et al.  Exploiting drug-disease relationships for computational drug repositioning , 2011, Briefings Bioinform..

[41]  Ping Zhang,et al.  Predicting Drug-Drug Interactions Through Large-Scale Similarity-Based Link Prediction , 2016, ESWC.

[42]  Sean Ekins,et al.  In silico methods for predicting drug-drug interactions with cytochrome P-450s, transporters and beyond. , 2015, Advanced drug delivery reviews.

[43]  Shehroz S. Khan,et al.  A Survey of Recent Trends in One Class Classification , 2009, AICS.