Mapping Adverse Drug Reactions in Chemical Space

Role of text mining in early identification of potential drug safety issues

Drugs are an important part of today's medicine, designed to treat, control, and prevent diseases; however, besides their therapeutic effects, drugs may also cause adverse effects that range from cosmetic to severe morbidity and mortality. To identify these potential drug safety issues early, surveillance must be conducted for each drug throughout its life cycle, from drug development to different phases of clinical trials, and continued after market approval. A major aim of pharmacovigilance is to identify the potential drug-event associations that may be novel in nature, severity, and/or frequency. Currently, the state-of-the-art approach for signal detection is through automated procedures by analyzing vast quantities of data for clinical knowledge. There exists a variety of resources for the task, and many of them are textual data that require text analytics and natural language processing to derive high-quality information. This chapter focuses on the utilization of text mining techniques in identifying potential safety issues of drugs from textual sources such as biomedical literature, consumer posts in social media, and narrative electronic medical records.

3D pharmacophoric similarity improves multi adverse drug event identification in pharmacovigilance

Adverse drugs events (ADEs) detection constitutes a considerable concern in patient safety and public health care. For this reason, it is important to develop methods that improve ADE signal detection in pharmacovigilance databases. Our objective is to apply 3D pharmacophoric similarity models to enhance ADE recognition in Offsides, a pharmacovigilance resource with drug-ADE associations extracted from the FDA Adverse Event Reporting System (FAERS). We developed a multi-ADE predictor implementing 3D drug similarity based on a pharmacophoric approach, with an ADE reference standard extracted from the SIDER database. The results showed that the application of our 3D multi-type ADE predictor to the pharmacovigilance data in Offsides improved ADE identification and generated enriched sets of drug-ADE signals. The global ROC curve for the Offsides ADE candidates ranked with the 3D similarity score showed an area of 0.7. The 3D predictor also allows the identification of the most similar drug that causes the ADE under study, which could provide hypotheses about mechanisms of action and ADE etiology. Our method is useful in drug development, screening potential adverse effects in experimental drugs, and in drug safety, applicable to the evaluation of ADE signals selected through pharmacovigilance data mining.

Multivariate Analysis of Side Effects of Drug Molecules Based on Knowledge of Protein Bindings and ProteinProtein Interactions

Here, we examined the relationships between 969 side effects associated with 658 drugs and their 1368 human protein targets using our hybrid approaches. Firstly, L-shaped PLS (LPLS) was used to construct a multivariate model of side effects and protein bindings of drug molecules. LPLS is an extension of standard PLS regression, where, in addition to the response matrix Y and the regressor matrix X, an extra data matrix Z is constructed that summarizes the background information of X. X and Y are matrices comprising drugs-target proteins, and drugs-side effects, respectively. The Z matrix is the proteinprotein interaction data. From the loading plot of Y, we could identify two remarkable side effects (urinary incontinence and increased salivation) From the corresponding loading plot of X, the responsible protein targets causing each side effect could be estimated (sodium channels and gamma-aminobutyric acid (GABA) receptors). The loading plot of the Z matrix indicated that the GABA receptors interact with each other and they heavily influence the side effect of increased salivation. Secondly, Bayesian classifier methods were separately applied to the cases of the two side effects. That is, the Bayesian classifier method was used to classify drug molecules as binding or not binding to the responsible protein targets associated with each side effect. Using atom-coloring techniques, it was possible to estimate which fragments on the drug molecule might cause the specific side effects. This information is valuable for drug design to avoid specific side effects.

Systems pharmacology of adverse event mitigation by drug combinations

Drugs are designed for therapy, but medication-related adverse events are common, and risk/benefit analysis is critical for determining clinical use. Rosiglitazone, an efficacious antidiabetic drug, is associated with increased myocardial infarctions (MIs), thus limiting its usage. Because diabetic patients are often prescribed multiple drugs, we searched for usage of a second drug ("drug B") in the Food and Drug Administration's Adverse Event Reporting System (FAERS) that could mitigate the risk of rosiglitazone ("drug A")-associated MI. In FAERS, rosiglitazone usage is associated with increased occurrence of MI, but its combination with exenatide significantly reduces rosiglitazone-associated MI. Clinical data from the Mount Sinai Data Warehouse support the observations from FAERS. Analysis for confounding factors using logistic regression showed that they were not responsible for the observed effect. Using cell biological networks, we predicted that the mitigating effect of exenatide on rosiglitazone-associated MI could occur through clotting regulation. Data we obtained from the db/db mouse model agreed with the network prediction. To determine whether polypharmacology could generally be a basis for adverse event mitigation, we analyzed the FAERS database for other drug combinations wherein drug B reduced serious adverse events reported with drug A usage such as anaphylactic shock and suicidality. This analysis revealed 19,133 combinations that could be further studied. We conclude that this type of crowdsourced approach of using databases like FAERS can help to identify drugs that could potentially be repurposed for mitigation of serious adverse events.

Exploring the associations between drug side-effects and therapeutic indications

Drug therapeutic indications and side-effects are both measurable patient phenotype changes in response to the treatment. Inferring potential drug therapeutic indications and identifying clinically interesting drug side-effects are both important and challenging tasks. Previous studies have utilized either chemical structures or protein targets to predict indications and side-effects. In this study, we compared drug therapeutic indication prediction using various information including chemical structures, protein targets and side-effects. We also compared drug side-effect prediction with various information sources including chemical structures, protein targets and therapeutic indication. Prediction performance based on 10-fold cross-validation demonstrates that drug side-effects and therapeutic indications are the most predictive information source for each other. In addition, we extracted 6706 statistically significant indication-side-effect associations from all known drug-disease and drug-side-effect relationships. We further developed a novel user interface that allows the user to interactively explore these associations in the form of a dynamic bipartitie graph. Many relationship pairs provide explicit repositioning hypotheses (e.g., drugs causing postural hypotension are potential candidates for hypertension) and clear adverse-reaction watch lists (e.g., drugs for heart failure possibly cause impotence). All data sets and highly correlated disease-side-effect relationships are available at http://astro.temple.edu/∼tua87106/druganalysis.html.

Predictive in silico studies of human 5-hydroxytryptamine receptor subtype 2B (5-HT2B) and valvular heart disease

Serotonin (5-hydroxytryptamine, 5-HT) receptors are neuromodulator neurotransmitter receptors which when activated trigger a signal transduction cascade within cells resulting in cell-cell communication. 5-hydroxytryptamine receptor 2B (5-HT2B) is a subtype of the seven members of 5-hydroxytrytamine receptors family which is the largest member of the super family of 7-transmembrane G-protein coupled receptors (GPCRs). Not only do 5-HT receptors play physiological roles in the cardiovascular system, gastrointestinal and endocrine function as well as the central nervous system, but they also play a role in behavioral functions. In particular 5-HT2B receptor is widely spread with regards to its distribution throughout bodily tissues and is expressed at high levels in the lungs, peripheral tissues, liver, kidneys and prostate, just to name a few. Hence 5-HT2B participates in multiple biological functions including CNS regulation, regulation of gastrointestinal motality, cardiovascular regulation and 5-HT transport system regulation. While 5-HT2B is a viable drug target and has therapeutic indications for treating obesity, psychosis, Parkinson's disease etc. there is a growing concern regarding adverse drug reactions, specifically valvulopathy associated with 5-HT2B agonists. Due to the sequence homology experienced by 5-HT2 subtypes there is also a concern regarding the off-target effects of 5-HT2A and 5-HT2C agonists. The concepts of sensitivity and subtype selectivity are of paramount importance and now can be tackled with the aid of in silico studies, especially cheminformatics, to develop models to predict valvulopathy associated toxicity of drug candidates prior to clinical trials. This review has highlighted three in silico approaches thus far that have been successful in either predicting 5-HT2B toxicity of molecules or identifying important interactions between 5-HT2B and drug molecules that bring about valvulopathy related toxicities.

Determining molecular predictors of adverse drug reactions with causality analysis based on structure learning

OBJECTIVE

Adverse drug reaction (ADR) can have dire consequences. However, our current understanding of the causes of drug-induced toxicity is still limited. Hence it is of paramount importance to determine molecular factors of adverse drug responses so that safer therapies can be designed.

METHODS

We propose a causality analysis model based on structure learning (CASTLE) for identifying factors that contribute significantly to ADRs from an integration of chemical and biological properties of drugs. This study aims to address two major limitations of the existing ADR prediction studies. First, ADR prediction is mostly performed by assessing the correlations between the input features and ADRs, and the identified associations may not indicate causal relations. Second, most predictive models lack biological interpretability.

RESULTS

CASTLE was evaluated in terms of prediction accuracy on 12 organ-specific ADRs using 830 approved drugs. The prediction was carried out by first extracting causal features with structure learning and then applying them to a support vector machine (SVM) for classification. Through rigorous experimental analyses, we observed significant increases in both macro and micro F1 scores compared with the traditional SVM classifier, from 0.88 to 0.89 and 0.74 to 0.81, respectively. Most importantly, identified links between the biological factors and organ-specific drug toxicities were partially supported by evidence in Online Mendelian Inheritance in Man.

CONCLUSIONS

The proposed CASTLE model not only performed better in prediction than the baseline SVM but also produced more interpretable results (ie, biological factors responsible for ADRs), which is critical to discovering molecular activators of ADRs.

An Ensemble Approach for Drug Side Effect Prediction

In silico prediction of drug side-effects in early stage of drug development is becoming more popular now days, which not only reduces the time for drug design but also reduces the drug development costs. In this article we propose an ensemble approach to predict drug side-effects of drug molecules based on their chemical structure. Our idea originates from the observation that similar drugs have similar side-effects. Based on this observation we design an ensemble approach that combine the results from different classification models where each model is generated by a different set of similar drugs. We applied our approach to 1385 side-effects in the SIDER database for 888 drugs. Results show that our approach outperformed previously published approaches and standard classifiers. Furthermore, we applied our method to a number of uncharacterized drug molecules in DrugBank database and predict their side-effect profiles for future usage. Results from various sources confirm that our method is able to predict the side-effects for uncharacterized drugs and more importantly able to predict rare side-effects which are often ignored by other approaches. The method described in this article can be useful to predict side-effects in drug design in an early stage to reduce experimental cost and time.

Analysis of chemical and biological features yields mechanistic insights into drug side effects

Side effects (SEs) are the unintended consequence of therapeutic treatments, but they can also be seen as valuable readouts of drug effects, resulting from the perturbation of biological systems by chemical compounds. Unfortunately, biology and chemistry are often considered separately, leading to incomplete models unable to provide a unified view of SEs. Here, we investigate the molecular bases of over 1,600 SEs by navigating both chemical and biological spaces. We identified characteristic molecular traits for 1,162 SEs, 38% of which can be explained using solely biological arguments, and only 6% are exclusively associated with the chemistry of the compounds, implying that the drug action is somewhat unspecific. Overall, we provide mechanistic insights for most SEs and emphasize the need to blend biology and chemistry to surpass intricate phenomena not captured in the molecular biology view.

Predicting drugs side effects based on chemical-chemical interactions and protein-chemical interactions

A drug side effect is an undesirable effect which occurs in addition to the intended therapeutic effect of the drug. The unexpected side effects that many patients suffer from are the major causes of large-scale drug withdrawal. To address the problem, it is highly demanded by pharmaceutical industries to develop computational methods for predicting the side effects of drugs. In this study, a novel computational method was developed to predict the side effects of drug compounds by hybridizing the chemical-chemical and protein-chemical interactions. Compared to most of the previous works, our method can rank the potential side effects for any query drug according to their predicted level of risk. A training dataset and test datasets were constructed from the benchmark dataset that contains 835 drug compounds to evaluate the method. By a jackknife test on the training dataset, the 1st order prediction accuracy was 86.30%, while it was 89.16% on the test dataset. It is expected that the new method may become a useful tool for drug design, and that the findings obtained by hybridizing various interactions in a network system may provide useful insights for conducting in-depth pharmacological research as well, particularly at the level of systems biomedicine.

Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs

Objective

Adverse drug reaction (ADR) is one of the major causes of failure in drug development. Severe ADRs that go undetected until the post-marketing phase of a drug often lead to patient morbidity. Accurate prediction of potential ADRs is required in the entire life cycle of a drug, including early stages of drug design, different phases of clinical trials, and post-marketing surveillance.

Methods

Many studies have utilized either chemical structures or molecular pathways of the drugs to predict ADRs. Here, the authors propose a machine-learning-based approach for ADR prediction by integrating the phenotypic characteristics of a drug, including indications and other known ADRs, with the drug's chemical structures and biological properties, including protein targets and pathway information. A large-scale study was conducted to predict 1385 known ADRs of 832 approved drugs, and five machine-learning algorithms for this task were compared.

Results

This evaluation, based on a fivefold cross-validation, showed that the support vector machine algorithm outperformed the others. Of the three types of information, phenotypic data were the most informative for ADR prediction. When biological and phenotypic features were added to the baseline chemical information, the ADR prediction model achieved significant improvements in area under the curve (from 0.9054 to 0.9524), precision (from 43.37% to 66.17%), and recall (from 49.25% to 63.06%). Most importantly, the proposed model successfully predicted the ADRs associated with withdrawal of rofecoxib and cerivastatin.

Conclusion

The results suggest that phenotypic information on drugs is valuable for ADR prediction. Moreover, they demonstrate that different models that combine chemical, biological, or phenotypic information can be built from approved drugs, and they have the potential to detect clinically important ADRs in both preclinical and post-marketing phases.

Integrative relational machine-learning for understanding drug side-effect profiles

Background

Drug side effects represent a common reason for stopping drug development during clinical trials. Improving our ability to understand drug side effects is necessary to reduce attrition rates during drug development as well as the risk of discovering novel side effects in available drugs. Today, most investigations deal with isolated side effects and overlook possible redundancy and their frequent co-occurrence.

Results

In this work, drug annotations are collected from SIDER and DrugBank databases. Terms describing individual side effects reported in SIDER are clustered with a semantic similarity measure into term clusters (TCs). Maximal frequent itemsets are extracted from the resulting drug x TC binary table, leading to the identification of what we call side-effect profiles (SEPs). A SEP is defined as the longest combination of TCs which are shared by a significant number of drugs. Frequent SEPs are explored on the basis of integrated drug and target descriptors using two machine learning methods: decision-trees and inductive-logic programming. Although both methods yield explicit models, inductive-logic programming method performs relational learning and is able to exploit not only drug properties but also background knowledge. Learning efficiency is evaluated by cross-validation and direct testing with new molecules. Comparison of the two machine-learning methods shows that the inductive-logic-programming method displays a greater sensitivity than decision trees and successfully exploit background knowledge such as functional annotations and pathways of drug targets, thereby producing rich and expressive rules. All models and theories are available on a dedicated web site.

Conclusions

Side effect profiles covering significant number of drugs have been extracted from a drug ×side-effect association table. Integration of background knowledge concerning both chemical and biological spaces has been combined with a relational learning method for discovering rules which explicitly characterize drug-SEP associations. These rules are successfully used for predicting SEPs associated with new drugs.

Predicting adverse drug reaction profiles by integrating protein interaction networks with drug structures

The prediction of adverse drug reactions (ADRs) has become increasingly important, due to the rising concern on serious ADRs that can cause drugs to fail to reach or stay in the market. We proposed a framework for predicting ADR profiles by integrating protein-protein interaction (PPI) networks with drug structures. We compared ADR prediction performances over 18 ADR categories through four feature groups-only drug targets, drug targets with PPI networks, drug structures, and drug targets with PPI networks plus drug structures. The results showed that the integration of PPI networks and drug structures can significantly improve the ADR prediction performance. The median AUC values for the four groups were 0.59, 0.61, 0.65, and 0.70. We used the protein features in the best two models, "Cardiac disorders" (median-AUC: 0.82) and "Psychiatric disorders" (median-AUC: 0.76), to build ADR-specific PPI networks with literature supports. For validation, we examined 30 drugs withdrawn from the U.S. market to see if our approach can predict their ADR profiles and explain why they were withdrawn. Except for three drugs having ADRs in the categories we did not predict, 25 out of 27 withdrawn drugs (92.6%) having severe ADRs were successfully predicted by our approach.

Relating drug-protein interaction network with drug side effects

Motivation: Identifying the emergence and underlying mechanisms of drug side effects is a challenging task in the drug development process. This underscores the importance of system–wide approaches for linking different scales of drug actions; namely drug-protein interactions (molecular scale) and side effects (phenotypic scale) toward side effect prediction for uncharacterized drugs.

Results: We performed a large-scale analysis to extract correlated sets of targeted proteins and side effects, based on the co-occurrence of drugs in protein-binding profiles and side effect profiles, using sparse canonical correlation analysis. The analysis of 658 drugs with the two profiles for 1368 proteins and 1339 side effects led to the extraction of 80 correlated sets. Enrichment analyses using KEGG and Gene Ontology showed that most of the correlated sets were significantly enriched with proteins that are involved in the same biological pathways, even if their molecular functions are different. This allowed for a biologically relevant interpretation regarding the relationship between drug–targeted proteins and side effects. The extracted side effects can be regarded as possible phenotypic outcomes by drugs targeting the proteins that appear in the same correlated set. The proposed method is expected to be useful for predicting potential side effects of new drug candidate compounds based on their protein-binding profiles.

Supplementary information: Datasets and all results are available at http://web.kuicr.kyoto-u.ac.jp/supp/smizutan/target-effect/.

Availability: Software is available at the above supplementary website.

Contact:yamanishi@bioreg.kyushu-u.ac.jp, or goto@kuicr.kyoto-u.ac.jp

Automated detection of structural alerts (chemical fragments) in (eco)toxicology

This mini-review describes the evolution of different algorithms dedicated to the automated discovery of chemical fragments associated to (eco)toxicological endpoints. These structural alerts correspond to one of the most interesting approach of in silico toxicology due to their direct link with specific toxicological mechanisms. A number of expert systems are already available but, since the first work in this field which considered a binomial distribution of chemical fragments between two datasets, new data miners were developed and applied with success in chemoinformatics. The frequency of a chemical fragment in a dataset is often at the core of the process for the definition of its toxicological relevance. However, recent progresses in data mining provide new insights into the automated discovery of new rules. Particularly, this review highlights the notion of Emerging Patterns that can capture contrasts between classes of data.

Data mining methodologies for pharmacovigilance

Medicines are designed to cure, treat, or prevent diseases; however, there are also risks in taking any medicine - particularly short term or long term adverse drug reactions (ADRs) can cause serious harm to patients. Adverse drug events have been estimated to cause over 700,000 emergency department visits each year in the United States. Thus, for medication safety, ADR monitoring is required for each drug throughout its life cycle, including early stages of drug design, different phases of clinical trials, and postmarketing surveillance. Pharmacovigilance (PhV) is the science that concerns with the detection, assessment, understanding and prevention of ADRs. In the pre-marketing stages of a drug, PhV primarily focuses on predicting potential ADRs using preclinical characteristics of the compounds (e.g., drug targets, chemical structure) or screening data (e.g., bioassay data). In the postmarketing stage, PhV has traditionally involved in mining spontaneous reports submitted to national surveillance systems. The research focus is currently shifting toward the use of data generated from platforms outside the conventional framework such as electronic medical records (EMRs), biomedical literature, and patient-reported data in online health forums. The emerging trend of PhV is to link preclinical data from the experimental platform with human safety information observed in the postmarketing phase. This article provides a general overview of the current computational methodologies applied for PhV at different stages of drug development and concludes with future directions and challenges.

Drug side-effect prediction based on the integration of chemical and biological spaces

Drug side-effects, or adverse drug reactions, have become a major public health concern and remain one of the main causes of drug failure and of drug withdrawal once they have reached the market. Therefore, the identification of potential severe side-effects is a challenging issue. In this paper, we develop a new method to predict potential side-effect profiles of drug candidate molecules based on their chemical structures and target protein information on a large scale. We propose several extensions of kernel regression model for multiple responses to deal with heterogeneous data sources. The originality lies in the integration of the chemical space of drug chemical structures and the biological space of drug target proteins in a unified framework. As a result, we demonstrate the usefulness of the proposed method on the simultaneous prediction of 969 side-effects for approved drugs from their chemical substructure and target protein profiles and show that the prediction accuracy consistently improves owing to the proposed regression model and integration of chemical and biological information. We also conduct a comprehensive side-effect prediction for uncharacterized drug molecules stored in DrugBank and confirm interesting predictions using independent information sources. The proposed method is expected to be useful at many stages of the drug development process.

The promiscuous binding of pharmaceutical drugs and their transporter-mediated uptake into cells: what we (need to) know and how we can do so

A recent paper in this journal sought to counter evidence for the role of transport proteins in effecting drug uptake into cells, and questions that transporters can recognize drug molecules in addition to their endogenous substrates. However, there is abundant evidence that both drugs and proteins are highly promiscuous. Most proteins bind to many drugs and most drugs bind to multiple proteins (on average more than six), including transporters (mutations in these can determine resistance); most drugs are known to recognise at least one transporter. In this response, we alert readers to the relevant evidence that exists or is required. This needs to be acquired in cells that contain the relevant proteins, and we highlight an experimental system for simultaneous genome-wide assessment of carrier-mediated uptake in a eukaryotic cell (yeast).

Investigating drug repositioning opportunities in FDA drug labels through topic modeling

Background

Drug repositioning offers an opportunity to revitalize the slowing drug discovery pipeline by finding new uses for currently existing drugs. Our hypothesis is that drugs sharing similar side effect profiles are likely to be effective for the same disease, and thus repositioning opportunities can be identified by finding drug pairs with similar side effects documented in U.S. Food and Drug Administration (FDA) approved drug labels. The safety information in the drug labels is usually obtained in the clinical trial and augmented with the observations in the post-market use of the drug. Therefore, our drug repositioning approach can take the advantage of more comprehensive safety information comparing with conventional de novo approach.

Method

A probabilistic topic model was constructed based on the terms in the Medical Dictionary for Regulatory Activities (MedDRA) that appeared in the Boxed Warning, Warnings and Precautions, and Adverse Reactions sections of the labels of 870 drugs. Fifty-two unique topics, each containing a set of terms, were identified by using topic modeling. The resulting probabilistic topic associations were used to measure the distance (similarity) between drugs. The success of the proposed model was evaluated by comparing a drug and its nearest neighbor (i.e., a drug pair) for common indications found in the Indications and Usage Section of the drug labels.

Results

Given a drug with more than three indications, the model yielded a 75% recall, meaning 75% of drug pairs shared one or more common indications. This is significantly higher than the 22% recall rate achieved by random selection. Additionally, the recall rate grows rapidly as the number of drug indications increases and reaches 84% for drugs with 11 indications. The analysis also demonstrated that 65 drugs with a Boxed Warning, which indicates significant risk of serious and possibly life-threatening adverse effects, might be replaced with safer alternatives that do not have a Boxed Warning. In addition, we identified two therapeutic groups of drugs (Musculo-skeletal system and Anti-infective for systemic use) where over 80% of the drugs have a potential replacement with high significance.

Conclusion

Topic modeling can be a powerful tool for the identification of repositioning opportunities by examining the adverse event terms in FDA approved drug labels. The proposed framework not only suggests drugs that can be repurposed, but also provides insight into the safety of repositioned drugs.

A strategy based on protein-protein interface motifs may help in identifying drug off-targets

Networks are increasingly used to study the impact of drugs at the systems level. From the algorithmic standpoint, a drug can "attack" nodes or edges of a protein-protein interaction network. In this work, we propose a new network strategy, "The Interface Attack", based on protein-protein interfaces. Similar interface architectures can occur between unrelated proteins. Consequently, in principle, a drug that binds to one has a certain probability of binding to others. The interface attack strategy simultaneously removes from the network all interactions that consist of similar interface motifs. This strategy is inspired by network pharmacology and allows inferring potential off-targets. We introduce a network model that we call "Protein Interface and Interaction Network (P2IN)", which is the integration of protein-protein interface structures and protein interaction networks. This interface-based network organization clarifies which protein pairs have structurally similar interfaces and which proteins may compete to bind the same surface region. We built the P2IN with the p53 signaling network and performed network robustness analysis. We show that (1) "hitting" frequent interfaces (a set of edges distributed around the network) might be as destructive as eleminating high degree proteins (hub nodes), (2) frequent interfaces are not always topologically critical elements in the network, and (3) interface attack may reveal functional changes in the system better than the attack of single proteins. In the off-target detection case study, we found that drugs blocking the interface between CDK6 and CDKN2D may also affect the interaction between CDK4 and CDKN2D.

Virtual target screening: validation using kinase inhibitors

Computational methods involving virtual screening could potentially be employed to discover new biomolecular targets for an individual molecule of interest (MOI). However, existing scoring functions may not accurately differentiate proteins to which the MOI binds from a larger set of macromolecules in a protein structural database. An MOI will most likely have varying degrees of predicted binding affinities to many protein targets. However, correctly interpreting a docking score as a hit for the MOI docked to any individual protein can be problematic. In our method, which we term "Virtual Target Screening (VTS)", a set of small drug-like molecules are docked against each structure in the protein library to produce benchmark statistics. This calibration provides a reference for each protein so that hits can be identified for an MOI. VTS can then be used as tool for: drug repositioning (repurposing), specificity and toxicity testing, identifying potential metabolites, probing protein structures for allosteric sites, and testing focused libraries (collection of MOIs with similar chemotypes) for selectivity. To validate our VTS method, twenty kinase inhibitors were docked to a collection of calibrated protein structures. Here, we report our results where VTS predicted protein kinases as hits in preference to other proteins in our database. Concurrently, a graphical interface for VTS was developed.

Personalized medicine: the impact on chemistry

An effective strategy for personalized medicine requires a major conceptual change in the development and application of therapeutics. In this article, we argue that further advances in this field should be made with reference to another conceptual shift, that of network pharmacology. We examine the intersection of personalized medicine and network pharmacology to identify strategies for the development of personalized therapies that are fully informed by network pharmacology concepts. This provides a framework for discussion of the impact personalized medicine will have on chemistry in terms of drug discovery, formulation and delivery, the adaptations and changes in ideology required and the contribution chemistry is already making. New ways of conceptualizing chemistry's relationship with medicine will lead to new approaches to drug discovery and hold promise of delivering safer and more effective therapies.

Large-Scale QSAR in Target Prediction and Phenotypic HTS Assessment

The advent of in silico compound target prediction offers a potential paradigm shift in how large compound collections are understood and used strategically in high-throughput screens (HTS). Specifically, phenotypic HTS hits may be annotated both with known targets and predicted targets using large-scale QSAR models, enabling a more sophisticated hit assessment. Efforts in massive bioactivity data integration and standardization is empowering such compound-target annotations. These approaches differ fundamentally from the traditional role of QSAR in lead optimization and binding affinity predictions to global, probabilistic target predictions for thousands of human proteins.

Data-driven prediction of drug effects and interactions

Adverse drug events remain a leading cause of morbidity and mortality around the world. Many adverse events are not detected during clinical trials before a drug receives approval for use in the clinic. Fortunately, as part of postmarketing surveillance, regulatory agencies and other institutions maintain large collections of adverse event reports, and these databases present an opportunity to study drug effects from patient population data. However, confounding factors such as concomitant medications, patient demographics, patient medical histories, and reasons for prescribing a drug often are uncharacterized in spontaneous reporting systems, and these omissions can limit the use of quantitative signal detection methods used in the analysis of such data. Here, we present an adaptive data-driven approach for correcting these factors in cases for which the covariates are unknown or unmeasured and combine this approach with existing methods to improve analyses of drug effects using three test data sets. We also present a comprehensive database of drug effects (Offsides) and a database of drug-drug interaction side effects (Twosides). To demonstrate the biological use of these new resources, we used them to identify drug targets, predict drug indications, and discover drug class interactions. We then corroborated 47 (P < 0.0001) of the drug class interactions using an independent analysis of electronic medical records. Our analysis suggests that combined treatment with selective serotonin reuptake inhibitors and thiazides is associated with significantly increased incidence of prolonged QT intervals. We conclude that confounding effects from covariates in observational clinical data can be controlled in data analyses and thus improve the detection and prediction of adverse drug effects and interactions.

Large-scale prediction and testing of drug activity on side-effect targets

Discovering the unintended 'off-targets' that predict adverse drug reactions is daunting by empirical methods alone. Drugs can act on several protein targets, some of which can be unrelated by conventional molecular metrics, and hundreds of proteins have been implicated in side effects. Here we use a computational strategy to predict the activity of 656 marketed drugs on 73 unintended 'side-effect' targets. Approximately half of the predictions were confirmed, either from proprietary databases unknown to the method or by new experimental assays. Affinities for these new off-targets ranged from 1 nM to 30 μM. To explore relevance, we developed an association metric to prioritize those new off-targets that explained side effects better than any known target of a given drug, creating a drug-target-adverse drug reaction network. Among these new associations was the prediction that the abdominal pain side effect of the synthetic oestrogen chlorotrianisene was mediated through its newly discovered inhibition of the enzyme cyclooxygenase-1. The clinical relevance of this inhibition was borne out in whole human blood platelet aggregation assays. This approach may have wide application to de-risking toxicological liabilities in drug discovery.

Predicting adverse drug events using pharmacological network models

Early and accurate identification of adverse drug events (ADEs) is critically important for public health. We have developed a novel approach for predicting ADEs, called predictive pharmacosafety networks (PPNs). PPNs integrate the network structure formed by known drug-ADE relationships with information on specific drugs and adverse events to predict likely unknown ADEs. Rather than waiting for sufficient post-market evidence to accumulate for a given ADE, this predictive approach relies on leveraging existing, contextual drug safety information, thereby having the potential to identify certain ADEs earlier. We constructed a network representation of drug-ADE associations for 809 drugs and 852 ADEs on the basis of a snapshot of a widely used drug safety database from 2005 and supplemented these data with additional pharmacological information. We trained a logistic regression model to predict unknown drug-ADE associations that were not listed in the 2005 snapshot. We evaluated the model's performance by comparing these predictions with the new drug-ADE associations that appeared in a 2010 snapshot of the same drug safety database. The proposed model achieved an AUROC (area under the receiver operating characteristic curve) statistic of 0.87, with a sensitivity of 0.42 given a specificity of 0.95. These findings suggest that predictive network methods can be useful for predicting unknown ADEs.

Personalized medicine: changing the paradigm of drug development

Despite an increased investment in research and development, there has been a steady decline in the number of drugs brought to market over the past 40 years. The tools of personalized medicine are refining diseases into molecular categories, and future therapeutics may be dictated by a patient's molecular profile relative to these categories. The adoption of a personalized medicine approach to drug development may improve the success rate by minimizing variability during each phase of the drug development process. This chapter describes the current paradigm of drug development and then discusses how molecular profiling/personalized medicine might be used to improve upon this paradigm.

Methicillin-resistant Staphylococcus aureus (MRSA) pyruvate kinase as a target for bis-indole alkaloids with antibacterial activities

Novel classes of antimicrobials are needed to address the emergence of multidrug-resistant bacteria such as methicillin-resistant Staphylococcus aureus (MRSA). We have recently identified pyruvate kinase (PK) as a potential novel drug target based upon it being an essential hub in the MRSA interactome (Cherkasov, A., Hsing, M., Zoraghi, R., Foster, L. J., See, R. H., Stoynov, N., Jiang, J., Kaur, S., Lian, T., Jackson, L., Gong, H., Swayze, R., Amandoron, E., Hormozdiari, F., Dao, P., Sahinalp, C., Santos-Filho, O., Axerio-Cilies, P., Byler, K., McMaster, W. R., Brunham, R. C., Finlay, B. B., and Reiner, N. E. (2011) J. Proteome Res. 10, 1139-1150; Zoraghi, R., See, R. H., Axerio-Cilies, P., Kumar, N. S., Gong, H., Moreau, A., Hsing, M., Kaur, S., Swayze, R. D., Worrall, L., Amandoron, E., Lian, T., Jackson, L., Jiang, J., Thorson, L., Labriere, C., Foster, L., Brunham, R. C., McMaster, W. R., Finlay, B. B., Strynadka, N. C., Cherkasov, A., Young, R. N., and Reiner, N. E. (2011) Antimicrob. Agents Chemother. 55, 2042-2053). Screening of an extract library of marine invertebrates against MRSA PK resulted in the identification of bis-indole alkaloids of the spongotine (A), topsentin (B, D), and hamacanthin (C) classes isolated from the Topsentia pachastrelloides as novel bacterial PK inhibitors. These compounds potently and selectively inhibited both MRSA PK enzymatic activity and S. aureus growth in vitro. The most active compounds, cis-3,4-dihyrohyrohamacanthin B (C) and bromodeoxytopsentin (D), were identified as highly potent MRSA PK inhibitors (IC(50) values of 16-60 nM) with at least 166-fold selectivity over human PK isoforms. These novel anti-PK natural compounds exhibited significant antibacterial activities against S. aureus, including MRSA (minimal inhibitory concentrations (MIC) of 12.5 and 6.25 μg/ml, respectively) with selectivity indices (CC(50)/MIC) >4. We also report the discrete structural features of the MRSA PK tetramer as determined by x-ray crystallography, which is suitable for selective targeting of the bacterial enzyme. The co-crystal structure of compound C with MRSA PK confirms that the latter is a target for bis-indole alkaloids. It elucidates the essential structural requirements for PK inhibitors in "small" interfaces that provide for tetramer rigidity and efficient catalytic activity. Our results identified a series of natural products as novel MRSA PK inhibitors, providing the basis for further development of potential novel antimicrobials.

Predicting adverse side effects of drugs

Background

Studies of toxicity and unintended side effects can lead to improved drug safety and efficacy. One promising form of study comes from molecular systems biology in the form of "systems pharmacology". Systems pharmacology combines data from clinical observation and molecular biology. This approach is new, however, and there are few examples of how it can practically predict adverse reactions (ADRs) from an experimental drug with acceptable accuracy.

Results

We have developed a new and practical computational framework to accurately predict ADRs of trial drugs. We combine clinical observation data with drug target data, protein-protein interaction (PPI) networks, and gene ontology (GO) annotations. We use cardiotoxicity, one of the major causes for drug withdrawals, as a case study to demonstrate the power of the framework. Our results show that an in silico model built on this framework can achieve a satisfactory cardiotoxicity ADR prediction performance (median AUC = 0.771, Accuracy = 0.675, Sensitivity = 0.632, and Specificity = 0.789). Our results also demonstrate the significance of incorporating prior knowledge, including gene networks and gene annotations, to improve future ADR assessments.

Conclusions

Biomolecular network and gene annotation information can significantly improve the predictive accuracy of ADR of drugs under development. The use of PPI networks can increase prediction specificity and the use of GO annotations can increase prediction sensitivity. Using cardiotoxicity as an example, we are able to further identify cardiotoxicity-related proteins among drug target expanding PPI networks. The systems pharmacology approach that we developed in this study can be generally applicable to all future developmental drug ADR assessments and predictions.

Mining FDA drug labels using an unsupervised learning technique--topic modeling

BACKGROUND

The Food and Drug Administration (FDA) approved drug labels contain a broad array of information, ranging from adverse drug reactions (ADRs) to drug efficacy, risk-benefit consideration, and more. However, the labeling language used to describe these information is free text often containing ambiguous semantic descriptions, which poses a great challenge in retrieving useful information from the labeling text in a consistent and accurate fashion for comparative analysis across drugs. Consequently, this task has largely relied on the manual reading of the full text by experts, which is time consuming and labor intensive.

METHOD

In this study, a novel text mining method with unsupervised learning in nature, called topic modeling, was applied to the drug labeling with a goal of discovering "topics" that group drugs with similar safety concerns and/or therapeutic uses together. A total of 794 FDA-approved drug labels were used in this study. First, the three labeling sections (i.e., Boxed Warning, Warnings and Precautions, Adverse Reactions) of each drug label were processed by the Medical Dictionary for Regulatory Activities (MedDRA) to convert the free text of each label to the standard ADR terms. Next, the topic modeling approach with latent Dirichlet allocation (LDA) was applied to generate 100 topics, each associated with a set of drugs grouped together based on the probability analysis. Lastly, the efficacy of the topic modeling was evaluated based on known information about the therapeutic uses and safety data of drugs.

RESULTS

The results demonstrate that drugs grouped by topics are associated with the same safety concerns and/or therapeutic uses with statistical significance (P<0.05). The identified topics have distinct context that can be directly linked to specific adverse events (e.g., liver injury or kidney injury) or therapeutic application (e.g., antiinfectives for systemic use). We were also able to identify potential adverse events that might arise from specific medications via topics.

CONCLUSIONS

The successful application of topic modeling on the FDA drug labeling demonstrates its potential utility as a hypothesis generation means to infer hidden relationships of concepts such as, in this study, drug safety and therapeutic use in the study of biomedical documents.

Computational tools for polypharmacology and repurposing

Most drugs act on a multitude of targets rather than on one single target. Polypharmacology, an upcoming branch of pharmaceutical science, deals with the recognition of these off-target activities of small chemical compounds. Due to the high amount of data to be processed, application of computational methods is indispensable in this area. This review summarizes the most important in silico approaches for polypharmacology. The described methods comprise network pharmacology, machine learning techniques and chemogenomic approaches. The use of these methods for drug repurposing as a branch of drug discovery and development is discussed. Furthermore, a broad range of prospective applications is summarized to give the reader an overview of possibilities and limitations of the described techniques.

Drug repositioning using in silico compound profiling

BACKGROUND

Drug repositioning is a current strategy to find new uses for existing drugs, patented or not, and for late-stage candidates that failed for lack of efficacy.

RESULTS

In silico profiling of several marketed drugs (methadone, rapamycin, saquinavir and telmisartan) was performed, exploiting a vast amount of published information. Similar compounds were assessed in terms of target-activity profiles for major drug-target families. In silico profiles were visualized within an interactive heat map and detailed analysis was performed associated with the accessible current knowledge.

CONCLUSION

Based on a basic principle assuming that similar molecules share similar target activity, new potential targets and, therefore, opportunities of potential new indications have been identified and discussed.

Predicting drug side-effect profiles: a chemical fragment-based approach

Background

Drug side-effects, or adverse drug reactions, have become a major public health concern. It is one of the main causes of failure in the process of drug development, and of drug withdrawal once they have reached the market. Therefore, in silico prediction of potential side-effects early in the drug discovery process, before reaching the clinical stages, is of great interest to improve this long and expensive process and to provide new efficient and safe therapies for patients.

Results

In the present work, we propose a new method to predict potential side-effects of drug candidate molecules based on their chemical structures, applicable on large molecular databanks. A unique feature of the proposed method is its ability to extract correlated sets of chemical substructures (or chemical fragments) and side-effects. This is made possible using sparse canonical correlation analysis (SCCA). In the results, we show the usefulness of the proposed method by predicting 1385 side-effects in the SIDER database from the chemical structures of 888 approved drugs. These predictions are performed with simultaneous extraction of correlated ensembles formed by a set of chemical substructures shared by drugs that are likely to have a set of side-effects. We also conduct a comprehensive side-effect prediction for many uncharacterized drug molecules stored in DrugBank, and were able to confirm interesting predictions using independent source of information.

Conclusions

The proposed method is expected to be useful in various stages of the drug development process.

Recent trends and observations in the design of high-quality screening collections

The design of a high-quality screening collection is of utmost importance for the early drug-discovery process and provides, in combination with high-quality assay systems, the foundation of future discoveries. Herein, we review recent trends and observations to successfully expand the access to bioactive chemical space, including the feedback from hit assessment interviews of high-throughput screening campaigns; recent successes with chemogenomics target family approaches, the identification of new relevant target/domain families, diversity-oriented synthesis and new emerging compound classes, and non-classical approaches, such as fragment-based screening and DNA-encoded chemical libraries. The role of in silico library design approaches are emphasized.

In silico repositioning of approved drugs for rare and neglected diseases

One approach to speed up drug discovery is to examine new uses for existing approved drugs, so-called 'drug repositioning' or 'drug repurposing', which has become increasingly popular in recent years. Analysis of the literature reveals many examples of US Food and Drug Administration-approved drugs that are active against multiple targets (also termed promiscuity) that can also be used to therapeutic advantage for repositioning for other neglected and rare diseases. Using proof-of-principle examples, we suggest here that with current in silico technologies and databases of the structures and biological activities of chemical compounds (drugs) and related data, as well as close integration with in vitro screening data, improved opportunities for drug repurposing will emerge for neglected or rare/orphan diseases.

The Interweaving of Cheminformatics and HTS

The aim of this chapter is to describe the stages of early drug discovery that can be assisted by techniques commonly used in the field of cheminformatics. In fact, cheminformatics tools can be applied all the way from the design of compound libraries and the analysis of HTS results, to the discovery of functional relationships between compounds and their targets.

The chemical basis of pharmacology

Molecular biology now dominates pharmacology so thoroughly that it is difficult to recall that only a generation ago the field was very different. To understand drug action today, we characterize the targets through which they act and new drug leads are discovered on the basis of target structure and function. Until the mid-1980s the information often flowed in reverse: investigators began with organic molecules and sought targets, relating receptors not by sequence or structure but by their ligands. Recently, investigators have returned to this chemical view of biology, bringing to it systematic and quantitative methods of relating targets by their ligands. This has allowed the discovery of new targets for established drugs, suggested the bases for their side effects, and predicted the molecular targets underlying phenotypic screens. The bases for these new methods, some of their successes and liabilities, and new opportunities for their use are described.

Drug-target interaction prediction from chemical, genomic and pharmacological data in an integrated framework

MOTIVATION

In silico prediction of drug-target interactions from heterogeneous biological data is critical in the search for drugs and therapeutic targets for known diseases such as cancers. There is therefore a strong incentive to develop new methods capable of detecting these potential drug-target interactions efficiently.

RESULTS

In this article, we investigate the relationship between the chemical space, the pharmacological space and the topology of drug-target interaction networks, and show that drug-target interactions are more correlated with pharmacological effect similarity than with chemical structure similarity. We then develop a new method to predict unknown drug-target interactions from chemical, genomic and pharmacological data on a large scale. The proposed method consists of two steps: (i) prediction of pharmacological effects from chemical structures of given compounds and (ii) inference of unknown drug-target interactions based on the pharmacological effect similarity in the framework of supervised bipartite graph inference. The originality of the proposed method lies in the prediction of potential pharmacological similarity for any drug candidate compounds and in the integration of chemical, genomic and pharmacological data in a unified framework. In the results, we make predictions for four classes of important drug-target interactions involving enzymes, ion channels, GPCRs and nuclear receptors. Our comprehensively predicted drug-target interaction networks enable us to suggest many potential drug-target interactions and to increase research productivity toward genomic drug discovery.

SUPPLEMENTARY INFORMATION

Datasets and all prediction results are available at http://cbio.ensmp.fr/~yyamanishi/pharmaco/.

AVAILABILITY

Softwares are available upon request.

Missing Value Estimation for Compound-Target Activity Data

Relationships between drug targets and associated diseases have traditionally been investigated by means of sequence similarity, comparative protein modeling, and pathway analysis. Recently, a complementary paradigm has emerged to link targets and drugs via biological responses within activity data and visualize findings in networks. It has been indicated that one of the obstacles towards the identification of novel interactions is the sparsity of available data. In this article, we provide a survey of estimation methods that address the challenge of data sparsity. Each method is described in terms of its advantages and limitations, and an exemplary application on compound-target activity data is demonstrated. With such imputation methods in-hand, the opportunity to combine efforts in molecular informatics can be realized, yielding novel insights into ligand-target space.