Author/Editor		Kastrin, Andrej; Ferk, Polonca; Leskošek, Branimir
Title		Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning
Type		članek
Vol. and No.		Letnik 13, št. 5
Publication year		2018
Volume		str. 1-23
ISSN		1932-6203 - PloS one
Language		eng
Abstract		Drug-drug interaction (DDI) is a change in the effect of a drug when patient takes another drug. Characterizing DDIs is extremely important to avoid potential adverse drug reactions. We represent DDIs as a complex network in which nodes refer to drugs and links refer to their potential interactions. Recently, the problem of link prediction has attracted much con- sideration in scientific community. We represent the process of link prediction as a binary classification task on networks of potential DDIs. We use link prediction techniques for pre- dicting unknown interactions between drugs in five arbitrary chosen large-scale DDI data- bases, namely DrugBank, KEGG, NDF-RT, SemMedDB, and Twosides. We estimated the performance of link prediction using a series of experiments on DDI networks. We per- formed link prediction using unsupervised and supervised approach including classification tree, k -nearest neighbors, support vector machine, random forest, and gradient boosting machine classifiers based on topological and semantic similarity features. Supervised approach clearly outperforms unsupervised approach. The Twosides network gained the best prediction performance regarding the area under the precision-recall curve (0.93 for both random forests and gradient boosting machine). The applied methodolog y can be used as a tool to help researchers to identify potential DDIs. The supervised link prediction approach proved to be promising for potential DDIs prediction and may facilitate the identifi- cation of potential DDIs in clinical research.
Keywords		drug-drug interaction adverse drug reactions statistics medsebojno delovanje zdravil neželeni učinki statistika