Data-driven prediction of adverse drug reactions induced by drug-drug interactions

Abstract

BackgroundThe expanded use of multiple drugs has increased the occurrence of adverse drug reactions (ADRs) induced by drug-drug interactions (DDIs). However, such reactions are typically not observed in clinical drug-development studies because most of them focus on single-drug therapies. ADR reporting systems collect information on adverse health effects caused by both single drugs and DDIs. A major challenge is to unambiguously identify the effects caused by DDIs and to attribute them to specific drug interactions. A computational method that provides prospective predictions of potential DDI-induced ADRs will help to identify and mitigate these adverse health effects.MethodWe hypothesize that drug-protein interactions can be used as independent variables in predicting ADRs. We constructed drug pair-protein interaction profiles for ~800 drugs using drug-protein interaction information in the public domain. We then constructed statistical models to score drug pairs for their potential to induce ADRs based on drug pair-protein interaction profiles.ResultsWe used extensive clinical database information to construct categorical prediction models for drug pairs that are likely to induce ADRs via synergistic DDIs and showed that model performance deteriorated only slightly, with a moderate amount of false positives and false negatives in the training samples, as evaluated by our cross-validation analysis. The cross validation calculations showed an average prediction accuracy of 89% across 1,096 ADR models that captured the deleterious effects of synergistic DDIs. Because the models rely on drug-protein interactions, we made predictions for pairwise combinations of 764 drugs that are currently on the market and for which drug-protein interaction information is available. These predictions are publicly accessible at http://avoid-db.bhsai.org. We used the predictive models to analyze broader aspects of DDI-induced ADRs, showing that ~10% of all combinations have the potential to induce ADRs via DDIs. This allowed us to identify potential DDI-induced ADRs not yet clinically reported. The ability of the models to quantify adverse effects between drug classes also suggests that we may be able to select drug combinations that minimize the risk of ADRs.ConclusionAlmost all information on DDI-induced ADRs is generated after drug approval. This situation poses significant health risks for vulnerable patient populations with comorbidities. To help mitigate the risks, we developed a robust probabilistic approach to prospectively predict DDI-induced ADRs. Based on this approach, we developed prediction models for 1,096 ADRs and used them to predict the propensity of all pairwise combinations of nearly 800 drugs to be associated with these ADRs via DDIs. We made the predictions publicly available via internet access.Electronic supplementary materialThe online version of this article (doi:10.1186/s40360-017-0153-6) contains supplementary material, which is available to authorized users.

Predicting Adverse Drug Reactions of Two-drug Combinations using Structural and Transcriptomic Drug Representations to Train a Artificial Neural Network

“…Older studies implicate ADRs to be one of the top 10 causes of fatality in the US (Lazarou et al, 1998) , while more recent studies report that they account for anywhere for 2.7% to 15% of hospitalizations (Liu et al, 2017;Miguel et al, 2012) . Drug-drug interactions account for upto 30% of ADRs (Iyer et al, 2014) , and are known to affect clinical outcomes in 80% of those observed in cancer patients (Beijnen & Schellens, 2004) .…”

Similarity-based machine learning support vector machine predictor of drug-drug interactions with improved accuracies

“…Instead of employing drug structures in DDI prediction, Ferdousi et al constructed a method based on drug functional similarities consisting of carriers, transporters, enzymes and targets . Ruifeng et al built large‐scale drug‐protein interaction profiles with protein‐chemical linked data from the STITCH database to construct the prediction models for drug pairs that are likely to induce adverse drug reactions via synergistic DDI, and then evaluated the performance using the TWOSIDES database …”

“…12 Ruifeng et al built large-scale drug-protein interaction profiles with protein-chemical linked data from the STITCH database to construct the prediction models for drug pairs that are likely to induce adverse drug reactions via synergistic DDI, and then evaluated the performance using the TWOSIDES database. 13 Specifically, Vilar et al used the molecular structure similarity, 14 IPF similarity, 15 3D pharmacophoric similarity, 16 drug-target similarity and adverse drug effect similarity to construct a new protocol and the STATISTICA software for predicting DDI with 84% accuracy. 17 Cheng et al developed similarity-based machine learning support vector machine (SVM) models using phenotypic, therapeutic, chemical structure and genomic features for predicting DDI at the performance level of AUROC = 0.67.…”

Opportunities and Challenges in Data-Driven Healthcare Research

“…Data-driven healthcare research has been proposed to achieve this goal [28][29]. In recent decades, various types of data-driven healthcare researches have been proposed, for instance, Genome-Wide Association Study (GWAS) [30][31] and Phenome-Wide Association Study (PheWAS) [32][33] have been developed to find associations between genes, diseases and drugs; drug-drug interaction studies have been implemented to detect adverse drug interactions [34]; predictive models are used to predict diseases such as Alzheimer [35] and suicide [36] at an earlier time; computational algorithms and statistical models are leveraged to identify risk factors related to patient outcomes such as unplanned readmission rates [38], mortality rates [39] and prolonged length of stay [40][41];…”