Network Based Prediction of Drug-Drug Interactions

Abstract

Drug-drug interactions (DDIs) are responsible for many serious adverse events; their detection is crucial for patient safety but also very challenging. In recent years, several drugs have been withdrawn from the market due to interaction-related adverse events (AEs). Current methods for detecting DDIs rely on the accumulation of sufficient clinical evidence in the post-market stage, a lengthy process that often takes years, during which time numerous patients may suffer from the adverse effects of the DDI. Thus, there is a practical need for a predictive model that can identify potential DDIs years in advance, enabling drug safety professionals to better prioritize their limited investigative resources and take appropriate remedial action. To meet this need, we describe a predictive model applicable on a large scale to predict novel DDIs based on similarity of drug interaction candidates to drugs involved in established DDIs. The underlying assumption is that if drug A and drug B interact to produce a specific biological effect, then drugs similar to drug A (or drug B) are likely to interact with drug B (or drug A) to produce the same effect. We constructed a 352-drug DDI network from a 2011 snapshot of a widely-used drug safety database, which contains 3 700 established DDIs, and used it to develop the proposed model for predicting future DDIs. The target similarity of all selected pairs of drugs in DrugBank was computed to identify DDI candidates. The proposed model mainly follows two distinct approaches: the first which forces the preservation of existing (known) DDIs and the other without forced to preserve existing DDIs. Under each of these approaches prediction was performed using three different techniques: target similarity score, side effect similarity (P-score) and resulting score (which is generated by integrating the results of target similarity score and P-score). The methodology was evaluated by using Drugbank 2014 snapshot as a gold standard for the same set of drugs. The proposed model generates novel DDIs with an average accuracy of 95% and 92% for forces the preservation of existing (known) DDIs and the other without forced to preserve existing DDIs approaches respectively. These two approaches also give average AUC (Area Under the Curve) of 0.9834 and 0.8651 respectively. These results indicate that network based methods can be useful for predicting unknown drug-drug interactions.