Extracting Drug-Drug Interaction from the Biomedical Literature Using a Stacked Generalization-Based Approach

Drug-drug interaction (DDI) detection is particularly important for patient safety. However, the amount of biomedical literature regarding drug interactions is increasing rapidly. Therefore, there is a need to develop an effective approach for the automatic extraction of DDI information from the biomedical literature. In this paper, we present a Stacked Generalization-based approach for automatic DDI extraction. The approach combines the feature-based, graph and tree kernels and, therefore, reduces the risk of missing important features. In addition, it introduces some domain knowledge based features (the keyword, semantic type, and DrugBank features) into the feature-based kernel, which contribute to the performance improvement. More specifically, the approach applies Stacked generalization to automatically learn the weights from the training data and assign them to three individual kernels to achieve a much better performance than each individual kernel. The experimental results show that our approach can achieve a better performance of 69.24% in F-score compared with other systems in the DDI Extraction 2011 challenge task.     

Hash subgraph pairwise kernel for protein-protein interaction extraction

Extracting protein-protein interaction (PPI) from biomedical literature is an important task in biomedical text mining (BioTM). In this paper, we propose a hash subgraph pairwise (HSP) kernel-based approach for this task. The key to the novel kernel is to use the hierarchical hash labels to express the structural information of subgraphs in a linear time. We apply the graph kernel to compute dependency graphs representing the sentence structure for protein-protein interaction extraction task, which can efficiently make use of full graph structural information, and particularly capture the contiguous topological and label information ignored before. We evaluate the proposed approach on five publicly available PPI corpora. The experimental results show that our approach significantly outperforms all-path kernel approach on all five corpora and achieves state-of-the-art performance.     

Predicting Drug-Target Interactions Using Drug-Drug Interactions

Computational methods for predicting drug-target interactions have become important in drug research because they can help to reduce the time, cost, and failure rates for developing new drugs. Recently, with the accumulation of drug-related data sets related to drug side effects and pharmacological data, it has became possible to predict potential drug-target interactions. In this study, we focus on drug-drug interactions (DDI), their adverse effects () and pharmacological information (), and investigate the relationship among chemical structures, side effects, and DDIs from several data sources. In this study, data from the STITCH database, from drugs.com, and drug-target pairs from ChEMBL and SIDER were first collected. Then, by applying two machine learning approaches, a support vector machine (SVM) and a kernel-based L1-norm regularized logistic regression (KL1LR), we showed that DDI is a promising feature in predicting drug-target interactions. Next, the accuracies of predicting drug-target interactions using DDI were compared to those obtained using the chemical structure and side effects based on the SVM and KL1LR approaches, showing that DDI was the data source contributing the most for predicting drug-target interactions.     

Literature based drug interaction prediction with clinical assessment using electronic medical records: novel myopathy associated drug interactions

Drug-drug interactions (DDIs) are a common cause of adverse drug events. In this paper, we combined a literature discovery approach with analysis of a large electronic medical record database method to predict and evaluate novel DDIs. We predicted an initial set of 13197 potential DDIs based on substrates and inhibitors of cytochrome P450 (CYP) metabolism enzymes identified from published in vitro pharmacology experiments. Using a clinical repository of over 800,000 patients, we narrowed this theoretical set of DDIs to 3670 drug pairs actually taken by patients. Finally, we sought to identify novel combinations that synergistically increased the risk of myopathy. Five pairs were identified with their p-values less than 1E-06: loratadine and simvastatin (relative risk or RR = 1.69); loratadine and alprazolam (RR = 1.86); loratadine and duloxetine (RR = 1.94); loratadine and ropinirole (RR = 3.21); and promethazine and tegaserod (RR = 3.00). When taken together, each drug pair showed a significantly increased risk of myopathy when compared to the expected additive myopathy risk from taking either of the drugs alone. Based on additional literature data on in vitro drug metabolism and inhibition potency, loratadine and simvastatin and tegaserod and promethazine were predicted to have a strong DDI through the CYP3A4 and CYP2D6 enzymes, respectively. This new translational biomedical informatics approach supports not only detection of new clinically significant DDI signals, but also evaluation of their potential molecular mechanisms.     

Detection of Drug-Drug Interactions by Modeling Interaction Profile Fingerprints

Drug-drug interactions (DDIs) constitute an important problem in postmarketing pharmacovigilance and in the development of new drugs. The effectiveness or toxicity of a medication could be affected by the co-administration of other drugs that share pharmacokinetic or pharmacodynamic pathways. For this reason, a great effort is being made to develop new methodologies to detect and assess DDIs. In this article, we present a novel method based on drug interaction profile fingerprints (IPFs) with successful application to DDI detection. IPFs were generated based on the DrugBank database, which provided 9,454 well-established DDIs as a primary source of interaction data. The model uses IPFs to measure the similarity of pairs of drugs and generates new putative DDIs from the non-intersecting interactions of a pair. We described as part of our analysis the pharmacological and biological effects associated with the putative interactions; for example, the interaction between haloperidol and dicyclomine can cause increased risk of psychosis and tardive dyskinesia. First, we evaluated the method through hold-out validation and then by using four independent test sets that did not overlap with DrugBank. Precision for the test sets ranged from 0.4–0.5 with more than two fold enrichment factor enhancement. In conclusion, we demonstrated the usefulness of the method in pharmacovigilance as a DDI predictor, and created a dataset of potential DDIs, highlighting the etiology or pharmacological effect of the DDI, and providing an exploratory tool to facilitate decision support in DDI detection and patient safety.     

A discriminative approach for identifying domain–domain interactions from protein–protein interactions

Protein domains are functional and structural units of proteins. Therefore, identification of domain–domain interactions (DDIs) can provide insight into the biological functions of proteins. In this article, we propose a novel discriminative approach for predicting DDIs based on both protein–protein interactions (PPIs) and the derived information of non‐PPIs. We make a threefold contribution to the work in this area. First, we take into account non‐PPIs explicitly and treat the domain combinations that can discriminate PPIs from non‐PPIs as putative DDIs. Second, DDI identification is formalized as a feature selection problem, in which it tries to find out a minimum set of informative features (i.e., putative DDIs) that discriminate PPIs from non‐PPIs, which is plausible in biology and is able to predict DDIs in a systematic and accurate manner. Third, multidomain combinations including two‐domain combinations are taken into account in the proposed method, where multidomain cooperations may help proteins to interact with each other. Numerical results on several DDI prediction benchmark data sets show that the proposed discriminative method performs comparably well with other top algorithms with respect to overall performance, and outperforms other methods in terms of precision. The PPI data sets used for prediction of DDIs and prediction results can be found at http://csb.shu.edu.cn/dipd . Proteins 2010. © 2009 Wiley‐Liss, Inc.     

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.     

Improving Detection of Arrhythmia Drug-Drug Interactions in Pharmacovigilance Data through the Implementation of Similarity-Based Modeling

Identification of Drug-Drug Interactions (DDIs) is a significant challenge during drug development and clinical practice. DDIs are responsible for many adverse drug effects (ADEs), decreasing patient quality of life and causing higher care expenses. DDIs are not systematically evaluated in pre-clinical or clinical trials and so the FDA U. S. Food and Drug Administration relies on post-marketing surveillance to monitor patient safety. However, existing pharmacovigilance algorithms show poor performance for detecting DDIs exhibiting prohibitively high false positive rates. Alternatively, methods based on chemical structure and pharmacological similarity have shown promise in adverse drug event detection. We hypothesize that the use of chemical biology data in a post hoc analysis of pharmacovigilance results will significantly improve the detection of dangerous interactions. Our model integrates a reference standard of DDIs known to cause arrhythmias with drug similarity data. To compare similarity between drugs we used chemical structure (both 2D and 3D molecular structure), adverse drug side effects, chemogenomic targets, drug indication classes, and known drug-drug interactions. We evaluated the method on external reference standards. Our results showed an enhancement of sensitivity, specificity and precision in different top positions with the use of similarity measures to rank the candidates extracted from pharmacovigilance data. For the top 100 DDI candidates, similarity-based modeling yielded close to twofold precision enhancement compared to the proportional reporting ratio (PRR). Moreover, the method helps in the DDI decision making through the identification of the DDI in the reference standard that generated the candidate.     

Systematic Prediction of Pharmacodynamic Drug-Drug Interactions through Protein-Protein-Interaction Network

Identifying drug-drug interactions (DDIs) is a major challenge in drug development. Previous attempts have established formal approaches for pharmacokinetic (PK) DDIs, but there is not a feasible solution for pharmacodynamic (PD) DDIs because the endpoint is often a serious adverse event rather than a measurable change in drug concentration. Here, we developed a metric “S-score” that measures the strength of network connection between drug targets to predict PD DDIs. Utilizing known PD DDIs as golden standard positives (GSPs), we observed a significant correlation between S-score and the likelihood a PD DDI occurs. Our prediction was robust and surpassed existing methods as validated by two independent GSPs. Analysis of clinical side effect data suggested that the drugs having predicted DDIs have similar side effects. We further incorporated this clinical side effects evidence with S-score to increase the prediction specificity and sensitivity through a Bayesian probabilistic model. We have predicted 9,626 potential PD DDIs at the accuracy of 82% and the recall of 62%. Importantly, our algorithm provided opportunities for better understanding the potential molecular mechanisms or physiological effects underlying DDIs, as illustrated by the case studies.     

Unravelling the complex drug–drug interactions of the cardiovascular drugs,verapamil and digoxin,with P-glycoprotein

Drug–drug interactions (DDIs) and associated toxicity from cardiovascular drugs represents a major problem for effective co-administration of cardiovascular therapeutics. A significant amount of drug toxicity from DDIs occurs because of drug interactions and multiple cardiovascular drug binding to the efflux transporter P-glycoprotein (Pgp), which is particularly problematic for cardiovascular drugs because of their relatively low therapeutic indexes. The calcium channel antagonist, verapamil and the cardiac glycoside, digoxin, exhibit DDIs with Pgp through non-competitive inhibition of digoxin transport, which leads to elevated digoxin plasma concentrations and digoxin toxicity. In the present study, verapamil-induced ATPase activation kinetics were biphasic implying at least two verapamil-binding sites on Pgp, whereas monophasic digoxin activation of Pgp-coupled ATPase kinetics suggested a single digoxin-binding site. Using intrinsic protein fluorescence and the saturation transfer double difference (STDD) NMR techniques to probe drug–Pgp interactions, verapamil was found to have little effect on digoxin–Pgp interactions at low concentrations of verapamil, which is consistent with simultaneous binding of the drugs and non-competitive inhibition. Higher concentrations of verapamil caused significant disruption of digoxin–Pgp interactions that suggested overlapping and competing drug-binding sites. These interactions correlated to drug-induced conformational changes deduced from acrylamide quenching of Pgp tryptophan fluorescence. Also, Pgp-coupled ATPase activity kinetics measured with a range of verapamil and digoxin concentrations fit well to a DDI model encompassing non-competitive and competitive inhibition of digoxin by verapamil. The results and previous transport studies were combined into a comprehensive model of verapamil–digoxin DDIs encompassing drug binding, ATP hydrolysis, transport and conformational changes.     

Analysis and prediction of drug–drug interaction by minimum redundancy maximum relevance and incremental feature selection

Drug–drug interaction (DDI) defines a situation in which one drug affects the activity of another when both are administered together. DDI is a common cause of adverse drug reactions and sometimes also leads to improved therapeutic effects. Therefore, it is of great interest to discover novel DDIs according to their molecular properties and mechanisms in a robust and rigorous way. This paper attempts to predict effective DDIs using the following properties: (1) chemical interaction between drugs; (2) protein interactions between the targets of drugs; and (3) target enrichment of KEGG pathways. The data consisted of 7323 pairs of DDIs collected from the DrugBank and 36,615 pairs of drugs constructed by randomly combining two drugs. Each drug pair was represented by 465 features derived from the aforementioned three categories of properties. The random forest algorithm was adopted to train the prediction model. Some feature selection techniques, including minimum redundancy maximum relevance and incremental feature selection, were used to extract key features as the optimal input for the prediction model. The extracted key features may help to gain insights into the mechanisms of DDIs and provide some guidelines for the relevant clinical medication developments, and the prediction model can give new clues for identification of novel DDIs.     

Functional coherence in domain interaction networks

MOTIVATION: Extracting functional information from protein-protein interactions (PPI) poses significant challenges arising from the noisy, incomplete, generic and static nature of data obtained from high-throughput screening. Typical proteins are composed of multiple domains, often regarded as their primary functional and structural units. Motivated by these considerations, domain-domain interactions (DDI) for network-based analyses have received significant recent attention. This article performs a formal comparative investigation of the relationship between functional coherence and topological proximity in PPI and DDI networks. Our investigation provides the necessary basis for continued and focused investigation of DDIs as abstractions for functional characterization and modularization of networks. RESULTS: We investigate the problem of assessing the functional coherence of two biomolecules (or segments thereof) in a formal framework. We establish essential attributes of admissible measures of functional coherence, and demonstrate that existing, well-accepted measures are ill-suited to comparative analyses involving different entities (i.e. domains versus proteins). We propose a statistically motivated functional similarity measure that takes into account functional specificity as well as the distribution of functional attributes across entity groups to assess functional similarity in a statistically meaningful and biologically interpretable manner. Results on diverse data, including high-throughput and computationally predicted PPIs, as well as structural and computationally inferred DDIs for different organisms show that: (i) the relationship between functional similarity and network proximity is captured in a much more (biologically) intuitive manner by our measure, compared to existing measures and (ii) network proximity and functional similarity are significantly more correlated in DDI networks than in PPI networks, and that structurally determined DDIs provide better functional relevance as compared to computationally inferred DDIs.     

Protein complex prediction based on maximum matching with domain-domain interaction

With the development of high-throughput methods for identifying protein-protein interactions, large scale interaction networks are available. Computational methods to analyze the networks to detect functional modules as protein complexes are becoming more important. However, most of the existing methods only make use of the protein-protein interaction networks without considering the structural limitations of proteins to bind together. In this paper, we design a new protein complex prediction method by extending the idea of using domain-domain interaction information. Here we formulate the problem into a maximum matching problem (which can be solved in polynomial time) instead of the binary integer linear programming approach (which can be NP-hard in the worst case). We also add a step to predict domain-domain interactions which first searches the database Pfam using the hidden Markov model and then predicts the domain-domain interactions based on the database DOMINE and InterDom which contain confirmed DDIs. By adding the domain-domain interaction prediction step, we have more edges in the DDI graph and the recall value is increased significantly (at least doubled) comparing with the method of Ozawa et al. (2010) [1] while the average precision value is slightly better. We also combine our method with three other existing methods, such as COACH, MCL and MCODE. Experiments show that the precision of the combined method is improved. This article is part of a Special Issue entitled: Computational Methods for Protein Interaction and Structural Prediction.     

Protein complex prediction based on maximum matching with domain–domain interaction

With the development of high-throughput methods for identifying protein–protein interactions, large scale interaction networks are available. Computational methods to analyze the networks to detect functional modules as protein complexes are becoming more important. However, most of the existing methods only make use of the protein–protein interaction networks without considering the structural limitations of proteins to bind together. In this paper, we design a new protein complex prediction method by extending the idea of using domain–domain interaction information. Here we formulate the problem into a maximum matching problem (which can be solved in polynomial time) instead of the binary integer linear programming approach (which can be NP-hard in the worst case). We also add a step to predict domain–domain interactions which first searches the database Pfam using the hidden Markov model and then predicts the domain–domain interactions based on the database DOMINE and InterDom which contain confirmed DDIs. By adding the domain–domain interaction prediction step, we have more edges in the DDI graph and the recall value is increased significantly (at least doubled) comparing with the method of Ozawa et al. (2010) [1] while the average precision value is slightly better. We also combine our method with three other existing methods, such as COACH, MCL and MCODE. Experiments show that the precision of the combined method is improved. This article is part of a Special Issue entitled: Computational Methods for Protein Interaction and Structural Prediction.     

Data mining and predictive modeling of biomolecular network from biomedical literature databases

In this paper, we present a novel approach Bio-IEDM (biomedical information extraction and data mining) to integrate text mining and predictive modeling to analyze biomolecular network from biomedical literature databases. Our method consists of two phases. In phase 1, we discuss a semisupervised efficient learning approach to automatically extract biological relationships such as protein-protein interaction, protein-gene interaction from the biomedical literature databases to construct the biomolecular network. Our method automatically learns the patterns based on a few user seed tuples and then extracts new tuples from the biomedical literature based on the discovered patterns. The derived biomolecular network forms a large scale-free network graph. In phase 2, we present a novel clustering algorithm to analyze the biomolecular network graph to identify biologically meaningful subnetworks (communities). The clustering algorithm considers the characteristics of the scale-free network graphs and is based on the local density of the vertex and its neighborhood functions that can be used to find more meaningful clusters with different density level. The experimental results indicate our approach is very effective in extracting biological knowledge from a huge collection of biomedical literature. The integration of data mining and information extraction provides a promising direction for analyzing the biomolecular network     

INDI: a computational framework for inferring drug interactions and their associated recommendations

Inferring drug–drug interactions (DDIs) is an essential step in drug development and drug administration. Most computational inference methods focus on modeling drug pharmacokinetics, aiming at interactions that result from a common metabolizing enzyme (CYP). Here, we introduce a novel prediction method, INDI (INferring Drug Interactions), allowing the inference of both pharmacokinetic, CYP‐related DDIs (along with their associated CYPs) and pharmacodynamic, non‐CYP associated ones. On cross validation, it obtains high specificity and sensitivity levels (AUC (area under the receiver‐operating characteristic curve)?0.93). In application to the FDA adverse event reporting system, 53% of the drug events could potentially be connected to known (41%) or predicted (12%) DDIs. Additionally, INDI predicts the severity level of each DDI upon co‐administration of the involved drugs, suggesting that severe interactions are abundant in the clinical practice. Examining regularly taken medications by hospitalized patients, 18% of the patients receive known or predicted severely interacting drugs and are hospitalized more frequently. Access to INDI and its predictions is provided via a web tool at http://www.cs.tau.ac.il/～bnet/software/INDI , facilitating the inference and exploration of drug interactions and providing important leads for physicians and pharmaceutical companies alike.     

PPIDomainMiner: Inferring domain-domain interactions from multiple sources of protein-protein interactions

Many biological processes are mediated by protein-protein interactions (PPIs). Because protein domains are the building blocks of proteins, PPIs likely rely on domain-domain interactions (DDIs). Several attempts exist to infer DDIs from PPI networks but the produced datasets are heterogeneous and sometimes not accessible, while the PPI interactome data keeps growing.We describe a new computational approach called “PPIDM” (Protein-Protein Interactions Domain Miner) for inferring DDIs using multiple sources of PPIs. The approach is an extension of our previously described “CODAC” (Computational Discovery of Direct Associations using Common neighbors) method for inferring new edges in a tripartite graph. The PPIDM method has been applied to seven widely used PPI resources, using as “Gold-Standard” a set of DDIs extracted from 3D structural databases. Overall, PPIDM has produced a dataset of 84,552 non-redundant DDIs. Statistical significance (p-value) is calculated for each source of PPI and used to classify the PPIDM DDIs in Gold (9,175 DDIs), Silver (24,934 DDIs) and Bronze (50,443 DDIs) categories. Dataset comparison reveals that PPIDM has inferred from the 2017 releases of PPI sources about 46% of the DDIs present in the 2020 release of the 3did database, not counting the DDIs present in the Gold-Standard. The PPIDM dataset contains 10,229 DDIs that are consistent with more than 13,300 PPIs extracted from the IMEx database, and nearly 23,300 DDIs (27.5%) that are consistent with more than 214,000 human PPIs extracted from the STRING database. Examples of newly inferred DDIs covering more than 10 PPIs in the IMEx database are provided.Further exploitation of the PPIDM DDI reservoir includes the inventory of possible partners of a protein of interest and characterization of protein interactions at the domain level in combination with other methods. The result is publicly available at http://ppidm.loria.fr/.     

IDDI: integrated domain-domain interaction and protein interaction analysis system

Background

Deciphering protein-protein interaction (PPI) in domain level enriches valuable information about binding mechanism and functional role of interacting proteins. The 3D structures of complex proteins are reliable source of domain-domain interaction (DDI) but the number of proven structures is very limited. Several resources for the computationally predicted DDI have been generated but they are scattered in various places and their prediction show erratic performances. A well-organized PPI and DDI analysis system integrating these data with fair scoring system is necessary.

Method

We integrated three structure-based DDI datasets and twenty computationally predicted DDI datasets and constructed an interaction analysis system, named IDDI, which enables to browse protein and domain interactions with their relationships. To integrate heterogeneous DDI information, a novel scoring scheme is introduced to determine the reliability of DDI by considering the prediction scores of each DDI and the confidence levels of each prediction method in the datasets, and independencies between predicted datasets. In addition, we connected this DDI information to the comprehensive PPI information and developed a unified interface for the interaction analysis exploring interaction networks at both protein and domain level.

Result

IDDI provides 204,705 DDIs among total 7,351 Pfam domains in the current version. The result presents that total number of DDIs is increased eight times more than that of previous studies. Due to the increment of data, 50.4% of PPIs could be correlated with DDIs which is more than twice of previous resources. Newly designed scoring scheme outperformed the previous system in its accuracy too. User interface of IDDI system provides interactive investigation of proteins and domains in interactions with interconnected way. A specific example is presented to show the efficiency of the systems to acquire the comprehensive information of target protein with PPI and DDI relationships. IDDI is freely available at http://pcode.kaist.ac.kr/iddi/.