Computational prediction of drug-drug interactions based on drugs functional similarities

Abstract

Therapeutic activities of drugs are often influenced by co-administration of drugs that may cause inevitable drug-drug interactions (DDIs) and inadvertent side effects. Prediction and identification of DDIs are extremely vital for the patient safety and success of treatment modalities. A number of computational methods have been employed for the prediction of DDIs based on drugs structures and/or functions. Here, we report on a computational method for DDIs prediction based on functional similarity of drugs. The model was set based on key biological elements including carriers, transporters, enzymes and targets (CTET). The model was applied for 2189 approved drugs. For each drug, all the associated CTETs were collected, and the corresponding binary vectors were constructed to determine the DDIs. Various similarity measures were conducted to detect DDIs. Of the examined similarity methods, the inner product-based similarity measures (IPSMs) were found to provide improved prediction values. Altogether, 2,394,766 potential drug pairs interactions were studied. The model was able to predict over 250,000 unknown potential DDIs. Upon our findings, we propose the current method as a robust, yet simple and fast, universal in silico approach for identification of DDIs. We envision that this proposed method can be used as a practical technique for the detection of possible DDIs based on the functional similarities of drugs.

Structured Penalized Regression for Drug Sensitivity Prediction

“…() and Garnett et al . () considered only separate univariate models for each drug and could thus not take the strong correlation structure between drugs due to similarities in drug function (Ferdousi et al ., ) into account. They also did not address heterogeneity between the various molecular data sources, e.g.…”

D4: Deep Drug-drug interaction Discovery and Demystification

“…, focusing mainly on the pharmacodynamic interactions (drugtarget, therapeutic and adverse drug effect) or pharmacokinetic interactions (drug-protein). For those interactions, measures of similarity among drugs and mechanistic information (Ferdousi et al, 2017), Semantic Web Technologies and Linked Data in the life sciences (Kamdar and Musen, 2017), web data (Fokoue et al, 2016), textual (Abdelaziz et al, 2017;Tari et al, 2010), and interaction networks (Bai and Abernethy, 2013;Park et al, 2015) have been developed and successfully applied to predict DDIs and ways in which drugs interact. Moreover, features that have been used to identify and better understand DDIs and mechanisms of interaction include molecular structure (Vilar et al, 2012), interaction profile fingerprints (Vilar et al, 2013), phenotypic, therapeutic, chemical, and genomic properties (Cheng and Zhao, 2014;Ferdousi et al, 2017), model organism phenotypes (Hoehndorf et al, 2013), multiple interaction mechanisms (Noor et al, 2016), and drug and protein properties (Kamdar and Musen, 2017).…”

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

“…For example, Devendra et al developed a novel kernel‐learning approach using the different similarities between molecules, structures, phenotype and genomics to mine DDI, which proved to be effective . 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 …”

“…4 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. 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.…”