Drug-drug Interaction Network Research Articles

A Physiologically-Based Pharmacokinetic (PBPK) Model Network for the Prediction of CYP1A2 and CYP2C19 Drug-Drug-Gene Interactions with Fluvoxamine, Omeprazole, S-mephenytoin, Moclobemide, Tizanidine, Mexiletine, Ethinylestradiol, and Caffeine.

Physiologically-based pharmacokinetic (PBPK) modeling is a well-recognized method for quantitatively predicting the effect of intrinsic/extrinsic factors on drug exposure. However, there are only few verified, freely accessible, modifiable, and comprehensive drug–drug interaction (DDI) PBPK models. We developed a qualified whole-body PBPK DDI network for cytochrome P450 (CYP) CYP2C19 and CYP1A2 interactions. Template PBPK models were developed for interactions between fluvoxamine, S-mephenytoin, moclobemide, omeprazole, mexiletine, tizanidine, and ethinylestradiol as the perpetrators or victims. Predicted concentration–time profiles accurately described a validation dataset, including data from patients with genetic polymorphisms, demonstrating that the models characterized the CYP2C19 and CYP1A2 network over the whole range of DDI studies investigated. The models are provided on GitHub (GitHub Inc., San Francisco, CA, USA), expanding the library of publicly available qualified whole-body PBPK models for DDI predictions, and they are thereby available to support potential recommendations for dose adaptations, support labeling, inform the design of clinical DDI trials, and potentially waive those.

DPDDI: a deep predictor for drug-drug interactions

BackgroundThe treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases.ResultsIn this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs.ConclusionWe proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

Ollivier-Ricci Curvature-Based Method to Community Detection in Complex Networks

Identification of community structures in complex network is of crucial importance for understanding the system’s function, organization, robustness and security. Here, we present a novel Ollivier-Ricci curvature (ORC) inspired approach to community identification in complex networks. We demonstrate that the intrinsic geometric underpinning of the ORC offers a natural approach to discover inherent community structures within a network based on interaction among entities. We develop an ORC-based community identification algorithm based on the idea of sequential removal of negatively curved edges symptomatic of high interactions (e.g., traffic, attraction). To illustrate and compare the performance with other community identification methods, we examine the ORC-based algorithm with stochastic block model artificial networks and real-world examples ranging from social to drug-drug interaction networks. The ORC-based algorithm is able to identify communities with either better or comparable performance accuracy and to discover finer hierarchical structures of the network. This opens new geometric avenues for analysis of complex networks dynamics.

Detecting drug communities and predicting comprehensive drug\u2013drug interactions via balance regularized semi-nonnegative matrix factorization

BackgroundBecause drug–drug interactions (DDIs) may cause adverse drug reactions or contribute to complex-disease treatments, it is important to identify DDIs before multiple-drug medications are prescribed. As the alternative of high-cost experimental identifications, computational approaches provide a much cheaper screening for potential DDIs on a large scale manner. Nevertheless, most of them only predict whether or not one drug interacts with another, but neglect their enhancive (positive) and depressive (negative) changes of pharmacological effects. Moreover, these comprehensive DDIs do not occur at random, but exhibit a weakly balanced relationship (a structural property when considering the DDI network), which would help understand how high-order DDIs work.ResultsThis work exploits the intrinsically structural relationship to solve two tasks, including drug community detection as well as comprehensive DDI prediction in the cold-start scenario. Accordingly, we first design a balance regularized semi-nonnegative matrix factorization (BRSNMF) to partition the drugs into communities. Then, to predict enhancive and degressive DDIs in the cold-start scenario, we develop a BRSNMF-based predictive approach, which technically leverages drug-binding proteins (DBP) as features to associate new drugs (having no known DDI) with other drugs (having known DDIs). Our experiments demonstrate that BRSNMF can generate the drug communities, which exhibit more reasonable sizes, the property of weak balance as well as pharmacological significances. Moreover, they demonstrate the superiority of DBP features and the inspiring ability of the BRSNMF-based predictive approach on comprehensive DDI prediction with 94% accuracy among top-50 predicted enhancive and 86% accuracy among bottom-50 predicted degressive DDIs.ConclusionsOwing to the regularization of the weak balance property of the comprehensive DDI network into semi-nonnegative matrix factorization, our proposed BRSNMF is able to not only generate better drug communities but also provide an inspiring comprehensive DDI prediction in the cold-start scenario.

In silico drug repositioning based on drug-miRNA associations.

Drug repositioning has become a prevailing tactic as this strategy is efficient, economical and low risk for drug discovery. Meanwhile, recent studies have confirmed that small-molecule drugs can modulate the expression of disease-related miRNAs, which indicates that miRNAs are promising therapeutic targets for complex diseases. In this study, we put forward and verified the hypothesis that drugs with similar miRNA profiles may share similar therapeutic properties. Furthermore, a comprehensive drug-drug interaction network was constructed based on curated drug-miRNA associations. Through random network comparison, topological structure analysis and network module extraction, we found that the closely linked drugs in the network tend to treat the same diseases. Additionally, the curated drug-disease relationships (from the CTD) and random walk with restarts algorithm were utilized on the drug-drug interaction network to identify the potential drugs for a given disease. Both internal validation (leave-one-out cross-validation) and external validation (independent drug-disease data set from the ChEMBL) demonstrated the effectiveness of the proposed approach. Finally, by integrating drug-miRNA and miRNA-disease information, we also explain the modes of action of drugs in the view of miRNA regulation. In summary, our work could determine novel and credible drug indications and offer novel insights and valuable perspectives for drug repositioning.

A Drug Repurposing Method Based on Drug-Drug Interaction Networks and Using Energy Model Layouts.

Complex network representations of reported drug-drug interactions foster computational strategies that can infer pharmacological functions which, in turn, create incentives for drug repositioning. Here, we use Gephi (a platform for complex network visualization and analysis) to represent a drug-drug interaction network with drug interaction information from DrugBank 4.1. Both modularity class- and force-directed layout ForceAtlas2 are employed to generate drug clusters which correspond to nine specific drug properties. Most drugs comply with their cluster's dominant property; however, some of them seem not to be in a proper position (i.e., in accordance with their already known functions). Such cases, along with cases of drugs that are topologically placed in the overlapping or bordering zones between clusters, may indicate previously unaccounted pharmacologic functions, thus leading to potential repositionings. Out of the 1141 drugs with relevant information on their interactions in DrugBank 4.1, we confirm the predicted properties for 85% of the drugs. The high prediction rate of our methodology suggests that, at least for some of the 15% drugs that seem to be inconsistent with the predicted property, we can get very good repositioning hints. As such, we present illustrative examples of recovered well-known repositionings, as well as recently confirmed pharmacological properties.

An Integrated Local Classification Model of Predicting Drug-Drug Interactions via Dempster-Shafer Theory of Evidence

Drug-drug interactions (DDIs) may trigger adverse drug reactions, which endanger the patients. DDI identification before making clinical medications is critical but bears a high cost in clinics. Computational approaches, including global model-based and local model based, are able to screen DDI candidates among a large number of drug pairs by utilizing preliminary characteristics of drugs (e.g. drug chemical structure). However, global model-based approaches are usually slow and don’t consider the topological structure of DDI network, while local model-based approaches have the degree-induced bias that a new drug tends to link to the drug having many DDI. All of them lack an effective ensemble method to combine results from multiple predictors. To address the first two issues, we propose a local classification-based model (LCM), which considers the topology of DDI network and has the relaxation of the degree-induced bias. Furthermore, we design a novel supervised fusion rule based on the Dempster-Shafer theory of evidence (LCM-DS), which aggregates the results from multiple LCMs. To make the final prediction, LCM-DS integrates three aspects from multiple classifiers, including the posterior probabilities output by individual classifiers, the proximity between their instance decision profiles and their reference profiles, as well as the quality of their reference profiles. Last, the substantial comparison with three state-of-the-art approaches demonstrates the effectiveness of our LCM, and the comparison with both individual LCM implementations and classical fusion algorithms exhibits the superiority of our LCM-DS.

Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning.

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 consideration 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 predicting unknown interactions between drugs in five arbitrary chosen large-scale DDI databases, namely DrugBank, KEGG, NDF-RT, SemMedDB, and Twosides. We estimated the performance of link prediction using a series of experiments on DDI networks. We performed 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 methodology 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 identification of potential DDIs in clinical research.

Clustering based drug-drug interaction networks for possible repositioning of drugs against EGFR mutations: Clustering based DDI networks for EGFR mutations

EGFRs are a vast group of receptor tyrosine kinases playing an important role in a number of tumors, including lungs, head and neck, breast, and esophageal cancers. A couple of techniques are being used in the process of drug design. Drug repositioning or repurposing is a rising idea that consists of distinguishing modern remedial indications for officially existing dynamic pharmaceutical compounds. Here, a novel approach of analyzing drug–drug interaction networks, based on clustering methodology is used to reposition effective compounds against mutant EGFR having G719X, exon 19 deletions/insertions, L858R, and L861Q mutations. Data about 2062 drugs are obtained, and mining is performed to filter only those drugs which fulfill Lipinski rule of five. Clustering is performed, and DDIs are built on the clusters to identify effective drug compounds. Only 1052 compounds fulfill Lipinski rule. 12 clusters are formed for 1052 drugs compounds. DDIs are developed for each cluster. Only 15 drugs are suggested to be more effective assuming strong interactions in a DDI.

Clustering drug-drug interaction networks with energy model layouts: community analysis and drug repurposing.

Analyzing drug-drug interactions may unravel previously unknown drug action patterns, leading to the development of new drug discovery tools. We present a new approach to analyzing drug-drug interaction networks, based on clustering and topological community detection techniques that are specific to complex network science. Our methodology uncovers functional drug categories along with the intricate relationships between them. Using modularity-based and energy-model layout community detection algorithms, we link the network clusters to 9 relevant pharmacological properties. Out of the 1141 drugs from the DrugBank 4.1 database, our extensive literature survey and cross-checking with other databases such as Drugs.com, RxList, and DrugBank 4.3 confirm the predicted properties for 85% of the drugs. As such, we argue that network analysis offers a high-level grasp on a wide area of pharmacological aspects, indicating possible unaccounted interactions and missing pharmacological properties that can lead to drug repositioning for the 15% drugs which seem to be inconsistent with the predicted property. Also, by using network centralities, we can rank drugs according to their interaction potential for both simple and complex multi-pathology therapies. Moreover, our clustering approach can be extended for applications such as analyzing drug-target interactions or phenotyping patients in personalized medicine applications.

Machine learning-based prediction of drug–drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties

Drug-drug interactions (DDIs) are an important consideration in both drug development and clinical application, especially for co-administered medications. While it is necessary to identify all possible DDIs during clinical trials, DDIs are frequently reported after the drugs are approved for clinical use, and they are a common cause of adverse drug reactions (ADR) and increasing healthcare costs. Computational prediction may assist in identifying potential DDIs during clinical trials. Here we propose a heterogeneous network-assisted inference (HNAI) framework to assist with the prediction of DDIs. First, we constructed a comprehensive DDI network that contained 6946 unique DDI pairs connecting 721 approved drugs based on DrugBank data. Next, we calculated drug-drug pair similarities using four features: phenotypic similarity based on a comprehensive drug-ADR network, therapeutic similarity based on the drug Anatomical Therapeutic Chemical classification system, chemical structural similarity from SMILES data, and genomic similarity based on a large drug-target interaction network built using the DrugBank and Therapeutic Target Database. Finally, we applied five predictive models in the HNAI framework: naive Bayes, decision tree, k-nearest neighbor, logistic regression, and support vector machine, respectively. The area under the receiver operating characteristic curve of the HNAI models is 0.67 as evaluated using fivefold cross-validation. Using antipsychotic drugs as an example, several HNAI-predicted DDIs that involve weight gain and cytochrome P450 inhibition were supported by literature resources. Through machine learning-based integration of drug phenotypic, therapeutic, structural, and genomic similarities, we demonstrated that HNAI is promising for uncovering DDIs in drug development and postmarketing surveillance.

Pharmacointeraction Network Models Predict Unknown Drug-Drug Interactions

Drug-drug interactions (DDIs) can lead to serious and potentially lethal adverse events. 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. Detection methods are further hindered by the extremely large combinatoric space of possible drug-drug-AE combinations. There is therefore a practical need for predictive tools that can identify potential DDIs years in advance, enabling drug safety professionals to better prioritize their limited investigative resources and take appropriate regulatory action. To meet this need, we describe Predictive Pharmacointeraction Networks (PPINs) – a novel approach that predicts unknown DDIs by exploiting the network structure of all known DDIs, together with other intrinsic and taxonomic properties of drugs and AEs. We constructed an 856-drug DDI network from a 2009 snapshot of a widely-used drug safety database, and used it to develop PPIN models for predicting future DDIs. We compared the DDIs predicted based solely on these 2009 data, with newly reported DDIs that appeared in a 2012 snapshot of the same database. Using a standard multivariate approach to combine predictors, the PPIN model achieved an AUROC (area under the receiver operating characteristic curve) of 0.81 with a sensitivity of 48% given a specificity of 90%. An analysis of DDIs by severity level revealed that the model was most effective for predicting “contraindicated” DDIs (AUROC = 0.92) and less effective for “minor” DDIs (AUROC = 0.63). These results indicate that network based methods can be useful for predicting unknown drug-drug interactions.

Network‐Assisted Investigation of Antipsychotic Drugs and Their Targets

Antipsychotic drugs are tranquilizing psychiatric medications primarily used in the treatment of schizophrenia and similar severe mental disorders. So far, most of these drugs have been discovered without knowing much on the molecular mechanisms of their actions. The available large amount of pharmacogenetics, pharmacometabolomics, and pharmacoproteomics data for many drugs makes it possible to systematically explore the molecular mechanisms underlying drug actions. In this study, we applied a unique network-based approach to investigate antipsychotic drugs and their targets. We first retrieved 43 antipsychotic drugs, 42 unique target genes, and 46 adverse drug interactions from the DrugBank database and then generated a drug-gene network and a drug-drug interaction network. Through drug-gene network analysis, we found that seven atypical antipsychotic drugs tended to form two clusters that could be defined by drugs with different target receptor profiles. In the drug-drug interaction network, we found that three drugs (zuclopenthixol, ziprasidone, and thiothixene) tended to have more adverse drug interactions than others, while clozapine had fewer adverse drug interactions. This investigation indicated that these antipsychotics might have different molecular mechanisms underlying the drug actions. This pilot network-assisted investigation of antipsychotics demonstrates that network-based analysis is useful for uncovering the molecular actions of antipsychotics.

Network analysis of adverse drug interactions.

Harmful effects associated with use of drugs are caused as a result of their side effects and combined use of different drugs. These drug interactions result in increased or decreased drug effects, or produce other new unwanted effects and are serious problems for medical institutions and pharmaceutical companies. In this study, we created a drug-drug interaction network from drug package inserts and characterized drug interactions. The known information about the potential risk of drug interactions is described in drug package inserts. Japanese drug package inserts are stored in the JAPIC (Japan Pharmaceutical Information Center) database and GenomeNet provides the GenomeNet pharmaceutical products database, which integrate the JAPIC and KEGG databases. We extracted drug interaction data from GenomeNet, where interactions are classified according to risks, contraindications or cautions for coadministration, and some entries include information about enzymes metabolizing the drugs. We defined drug target and drug-metabolizing enzymes as interaction factors using information on them in KEGG DRUG, and classified drugs into pharmacological/chemical subgroups. In the resulting drug-drug interaction network, the drugs that are associated with the same interaction factors are closely interconnected. Mechanisms of these interactions were then identified by each interaction factor. To characterize other interactions without interaction factors, we used the ATC classification system and found an association between interaction mechanisms and pharmacological/chemical subgroups.

Architecture of the drug-drug interaction network

Drug interaction information has been extensively compiled into large databases. The objective of the present study was to provide a systematic overview of the available drug interaction information, using a network approach. The drug-drug interaction information was retrieved from a comprehensive source reference that documents primary drug interaction information over an extended period of time. With careful examination of the information, we identified three continuously growing databases that consisted of 351, 636 and 966 drugs and 742, 1858 and 3351 pairs of interaction, respectively. We then constructed three drug-drug interaction networks in which the interacting drugs were treated as nodes and were connected with links that represent interactions. For each network, we determined the number of interactions that each drug in that network has, and prepared histograms to show the frequency distribution. The frequency distribution or the probability that a given drug has k interactions, P(k), followed a power-law distribution, where the power law exponent was close to -1·5 and was independent of the network size. The results suggested that while the majority of the drugs in the network had few interactions (small k), highly interacting drugs (large k) were rare but contributed most of the network interactions. The present study demonstrated that drug interaction information can be viewed and analysed as a connecting, growing network. As with many real-world networks, the drug interaction network was scale free, indicating that drug interaction information has been dominated by a relatively small number of highly interacting drugs.