Translating clinical findings into knowledge in drug safety evaluation--drug induced liver injury prediction system (DILIps)

Drug-induced liver injury (DILI) is a significant concern in drug development due to the poor concordance between preclinical and clinical findings of liver toxicity. We hypothesized that the DILI types (hepatotoxic side effects) seen in the clinic can be translated into the development of predictive in silico models for use in the drug discovery phase. We identified 13 hepatotoxic side effects with high accuracy for classifying marketed drugs for their DILI potential. We then developed in silico predictive models for each of these 13 side effects, which were further combined to construct a DILI prediction system (DILIps). The DILIps yielded 60-70% prediction accuracy for three independent validation sets. To enhance the confidence for identification of drugs that cause severe DILI in humans, the "Rule of Three" was developed in DILIps by using a consensus strategy based on 13 models. This gave high positive predictive value (91%) when applied to an external dataset containing 206 drugs from three independent literature datasets. Using the DILIps, we screened all the drugs in DrugBank and investigated their DILI potential in terms of protein targets and therapeutic categories through network modeling. We demonstrated that two therapeutic categories, anti-infectives for systemic use and musculoskeletal system drugs, were enriched for DILI, which is consistent with current knowledge. We also identified protein targets and pathways that are related to drugs that cause DILI by using pathway analysis and co-occurrence text mining. While marketed drugs were the focus of this study, the DILIps has a potential as an evaluation tool to screen and prioritize new drug candidates or chemicals, such as environmental chemicals, to avoid those that might cause liver toxicity. We expect that the methodology can be also applied to other drug safety endpoints, such as renal or cardiovascular toxicity.     

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.     

Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9

Cytochrome P450 2C9 (CYP2C9) is a major drug-metabolizing enzyme that represents 20% of the hepatic CYPs and is responsible for the metabolism of 15% of drugs. A general concern in drug discovery is to avoid the inhibition of CYP leading to toxic drug accumulation and adverse drug–drug interactions. However, the prediction of CYP inhibition remains challenging due to its complexity. We developed an original machine learning approach for the prediction of drug-like molecules inhibiting CYP2C9. We created new predictive models by integrating CYP2C9 protein structure and dynamics knowledge, an original selection of physicochemical properties of CYP2C9 inhibitors, and machine learning modeling. We tested the machine learning models on publicly available data and demonstrated that our models successfully predicted CYP2C9 inhibitors with an accuracy, sensitivity and specificity of approximately 80%. We experimentally validated the developed approach and provided the first identification of the drugs vatalanib, piriqualone, ticagrelor and cloperidone as strong inhibitors of CYP2C9 with IC values <18 μM and sertindole, asapiprant, duvelisib and dasatinib as moderate inhibitors with IC50 values between 40 and 85 μM. Vatalanib was identified as the strongest inhibitor with an IC50 value of 0.067 μM. Metabolism assays allowed the characterization of specific metabolites of abemaciclib, cloperidone, vatalanib and tarafenacin produced by CYP2C9. The obtained results demonstrate that such a strategy could improve the prediction of drug-drug interactions in clinical practice and could be utilized to prioritize drug candidates in drug discovery pipelines.     

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.     

A Network Inference Method for Large-Scale Unsupervised Identification of Novel Drug-Drug Interactions

Characterizing interactions between drugs is important to avoid potentially harmful combinations, to reduce off-target effects of treatments and to fight antibiotic resistant pathogens, among others. Here we present a network inference algorithm to predict uncharacterized drug-drug interactions. Our algorithm takes, as its only input, sets of previously reported interactions, and does not require any pharmacological or biochemical information about the drugs, their targets or their mechanisms of action. Because the models we use are abstract, our approach can deal with adverse interactions, synergistic/antagonistic/suppressing interactions, or any other type of drug interaction. We show that our method is able to accurately predict interactions, both in exhaustive pairwise interaction data between small sets of drugs, and in large-scale databases. We also demonstrate that our algorithm can be used efficiently to discover interactions of new drugs as part of the drug discovery process.     

Gap junction inhibition prevents drug-induced liver toxicity and fulminant hepatic failure

Drug-induced liver injury (DILI) limits the development and application of many therapeutic compounds and presents major challenges to the pharmaceutical industry and clinical medicine. Acetaminophen-containing compounds are among the most frequently prescribed drugs and are also the most common cause of DILI. Here we describe a pharmacological strategy that targets gap junction communication to prevent amplification of fulminant hepatic failure and acetaminophen-induced hepatotoxicity. We demonstrate that connexin 32 (Cx32), a key hepatic gap junction protein, is an essential mediator of DILI by showing that mice deficient in Cx32 are protected against liver damage, acute inflammation and death caused by liver-toxic drugs. We identify a small-molecule inhibitor of Cx32 that protects against liver failure and death in wild-type mice when co-administered with known hepatotoxic drugs. These findings indicate that gap junction inhibition could provide a pharmaceutical strategy to limit DILI and improve drug safety.     

Transfer learning for cytochrome P450 isozyme selectivity prediction

In the drug discovery process, the metabolic fate of drugs is crucially important to prevent drug-drug interactions. Therefore, P450 isozyme selectivity prediction is an important task for screening drugs of appropriate metabolism profiles. Recently, large-scale activity data of five P450 isozymes (CYP1A2 CYP2C9, CYP3A4, CYP2D6, and CYP2C19) have been obtained using quantitative high-throughput screening with a bioluminescence assay. Although some isozymes share similar selectivities, conventional supervised learning algorithms independently learn a prediction model from each P450 isozyme. They are unable to exploit the other P450 isozyme activity data to improve the predictive performance of each P450 isozyme's selectivity. To address this issue, we apply transfer learning that uses activity data of the other isozymes to learn a prediction model from multiple P450 isozymes. After using the large-scale P450 isozyme selectivity dataset for five P450 isozymes, we evaluate the model's predictive performance. Experimental results show that, overall, our algorithm outperforms conventional supervised learning algorithms such as support vector machine (SVM), Weighted k-nearest neighbor classifier, Bagging, Adaboost, and latent semantic indexing (LSI). Moreover, our results show that the predictive performance of our algorithm is improved by exploiting the multiple P450 isozyme activity data in the learning process. Our algorithm can be an effective tool for P450 selectivity prediction for new chemical entities using multiple P450 isozyme activity data.     

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.     

A Network-Based Classification Model for Deriving Novel Drug-Disease Associations and Assessing Their Molecular Actions

The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level. Properly selected features of the network representations of existing drug-disease associations can be used to infer novel indications of existing drugs. To find new drug-disease associations, we generated an integrative genetic network using combinations of interactions, including protein-protein interactions and gene regulatory network datasets. Within this network, network adjacencies of drug-drug and disease-disease were quantified using a scored path between target sets of them. Furthermore, the common topological module of drugs or diseases was extracted, and thereby the distance between topological drug-module and disease (or disease-module and drug) was quantified. These quantified scores were used as features for the prediction of novel drug-disease associations. Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties. Our predictions and current clinical trials overlap significantly across the different phases of drug development. We also identified and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer’s disease. Within the network, those modules show potential pathways that illustrate the mechanisms of new drug indications, including propranolol as a potential anticancer agent and telmisartan as treatment for Alzheimer’s disease.     

Drug Repositioning by Kernel-Based Integration of Molecular Structure,Molecular Activity,and Phenotype Data

Computational inference of novel therapeutic values for existing drugs, i.e., drug repositioning, offers the great prospect for faster and low-risk drug development. Previous researches have indicated that chemical structures, target proteins, and side-effects could provide rich information in drug similarity assessment and further disease similarity. However, each single data source is important in its own way and data integration holds the great promise to reposition drug more accurately. Here, we propose a new method for drug repositioning, PreDR (Predict Drug Repositioning), to integrate molecular structure, molecular activity, and phenotype data. Specifically, we characterize drug by profiling in chemical structure, target protein, and side-effects space, and define a kernel function to correlate drugs with diseases. Then we train a support vector machine (SVM) to computationally predict novel drug-disease interactions. PreDR is validated on a well-established drug-disease network with 1,933 interactions among 593 drugs and 313 diseases. By cross-validation, we find that chemical structure, drug target, and side-effects information are all predictive for drug-disease relationships. More experimentally observed drug-disease interactions can be revealed by integrating these three data sources. Comparison with existing methods demonstrates that PreDR is competitive both in accuracy and coverage. Follow-up database search and pathway analysis indicate that our new predictions are worthy of further experimental validation. Particularly several novel predictions are supported by clinical trials databases and this shows the significant prospects of PreDR in future drug treatment. In conclusion, our new method, PreDR, can serve as a useful tool in drug discovery to efficiently identify novel drug-disease interactions. In addition, our heterogeneous data integration framework can be applied to other problems.     

Pharmacogenetics and pharmacogenomics of cholesterol-lowering therapy

PURPOSE OF REVIEW: To summarize recent findings on pharmacokinetics, pharmacodynamics, drug-drug interactions and influence of lifestyle heterogeneity on adverse events in cholesterol-lowering therapy RECENT FINDINGS: The prevention of cardiovascular disease is critically dependent on lipid-lowery therapy, including statins, cholesterol absorption inhibitors, fibrates and nicotinic acid. Statins are the most prescribed drugs in lipid lowering therapy with variability in response and almost one third of the patients do not meet their treatment goals. The severe adverse effects of treatment with cerivastatin stimulated the search for new genes and gene variations affecting pharmacokinetics, drug-drug interactions and pharmacodynamics. Moreover, instead of monotherapy, combined therapy of statins with ezetemibe and niacin was considered. This led to the identification of CD13, NPC1L1 and HM74A as new targets and CYP2C8 and glucuronidation enzymes as potential targets for drug-drug interactions. Moreover multiple polymorphic sites and pleiotrophic gene targets were reinvestigated in larger cohorts and the relevant pathogenetic factors start to evolve. SUMMARY: Statin therapy is widely used and well tolerated by the majority of patients. To further reduce potential adverse effects and to increase efficacy, combined therapy concepts with ezetimibe or niacin are underway.     

Classifying Drugs by their Arrhythmogenic Risk Using Machine Learning

All medications have adverse effects. Among the most serious of these are cardiac arrhythmias. Current paradigms for drug safety evaluation are costly, lengthy, conservative, and impede efficient drug development. Here, we combine multiscale experiment and simulation, high-performance computing, and machine learning to create a risk estimator to stratify new and existing drugs according to their proarrhythmic potential. We capitalize on recent developments in machine learning and integrate information across 10 orders of magnitude in space and time to provide a holistic picture of the effects of drugs, either individually or in combination with other drugs. We show, both experimentally and computationally, that drug-induced arrhythmias are dominated by the interplay between two currents with opposing effects: the rapid delayed rectifier potassium current and the L-type calcium current. Using Gaussian process classification, we create a classifier that stratifies drugs into safe and arrhythmic domains for any combinations of these two currents. We demonstrate that our classifier correctly identifies the risk categories of 22 common drugs exclusively on the basis of their concentrations at 50% current block. Our new risk assessment tool explains under which conditions blocking the L-type calcium current can delay or even entirely suppress arrhythmogenic events. Using machine learning in drug safety evaluation can provide a more accurate and comprehensive mechanistic assessment of the proarrhythmic potential of new drugs. Our study paves the way toward establishing science-based criteria to accelerate drug development, design safer drugs, and reduce heart rhythm disorders.     

DLGCN:基于图卷积网络的药物-lncRNA[]关联预测

为实现高通量识别新的药物-长链非编码RNA(Long non-coding RNA, lncRNA)关联,本文提出了一种基于图卷积网络模型来识别潜在药物-lncRNA关联的方法DLGCN(Drug-LncRNA graph convolution network)。首先,基于药物的结构信息和lncRNA的序列信息分别构建了药物-药物和lncRNA-lncRNA相似性网络,并整合实验证实的药物-lncRNA关联构建了药物-lncRNA异质性网络。然后,将注意力机制和图卷积运算应用于该网络中,学习药物和lncRNA的低维特征,基于整合的低维特征预测新的药物-lncRNA关联。通过效能评估,DLGCN的受试者工作特性曲线下面积(Area under receiver operating characteristic, AUROC)达到0.843 1,优于经典的机器学习方法和常见的深度学习方法。此外,DLGCN预测到姜黄素能够调控lncRNA MALAT1的表达,已被最近的研究证实。DLGCN能够有效预测药物-lncRNA关联,为肿瘤治疗新靶点的识别和抗癌药物的筛选提供了重要参考。     

Direct costs and hospital morbimortality impact from preventable adverse drug events

Introduction. Implementing pharmacovigilance activities consists of monitoring and assessment of activities related to medical attention. However, additional data are necessary to identify conditions where care quality can be improved. Therefore, a focus on adverse drug events analysis from a prevention and economic perspective is needed, with emphasis on its local impact. Objective. Preventable adverse drug events were summarized to establishing their impact on morbidity and mortality, as well as to estimate the ensuing economic burden. Materials and methods. The data were gathered from a level 3 hospital (high complexity), located in Bogotá, Colombia, where specific pharmacovigilance activities were recorded in 2007. Patient charts were reviewed to characterize adverse drug events according to their causality, severity and preventability. Direct costs were estimated by grouping diagnostic tests, length of hospitalization, procedures and additional drugs required. Results. The charts of 283 patients and 448 reports were analyzed. These data indicated that 24.8% of adverse drug events were preventable and that an associated mortality of 1.1% had occurred. The associated direct costs were between USD $16,687 and $18,739. Factors more commonly associated with preventability were drug-drug interactions, as well as inappropriate doses and unsuitable frequencies at which the drugs were administrated. Conclusions. The data recommended that actions be taken to decrease preventable adverse drug events, because of negative impact on patient′s health, and unnecessary consumption of healthcare resources.     

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.     

Ligand-Target Prediction by Structural Network Biology Using nAnnoLyze

Target identification is essential for drug design, drug-drug interaction prediction, dosage adjustment and side effect anticipation. Specifically, the knowledge of structural details is essential for understanding the mode of action of a compound on a target protein. Here, we present nAnnoLyze, a method for target identification that relies on the hypothesis that structurally similar binding sites bind similar ligands. nAnnoLyze integrates structural information into a bipartite network of interactions and similarities to predict structurally detailed compound-protein interactions at proteome scale. The method was benchmarked on a dataset of 6,282 pairs of known interacting ligand-target pairs reaching a 0.96 of area under the Receiver Operating Characteristic curve (AUC) when using the drug names as an input feature for the classifier, and a 0.70 of AUC for “anonymous” compounds or compounds not present in the training set. nAnnoLyze resulted in higher accuracies than its predecessor, AnnoLyze. We applied the method to predict interactions for all the compounds in the DrugBank database with each human protein structure and provide examples of target identification for known drugs against human diseases. The accuracy and applicability of our method to any compound indicate that a comparative docking approach such as nAnnoLyze enables large-scale annotation and analysis of compound–protein interactions and thus may benefit drug development.     

An approach for classification of highly imbalanced data using weighting and undersampling

Real-world datasets commonly have issues with data imbalance. There are several approaches such as weighting, sub-sampling, and data modeling for handling these data. Learning in the presence of data imbalances presents a great challenge to machine learning. Techniques such as support-vector machines have excellent performance for balanced data, but may fail when applied to imbalanced datasets. In this paper, we propose a new undersampling technique for selecting instances from the majority class. The performance of this approach was evaluated in the context of several real biological imbalanced data. The ratios of negative to positive samples vary from ~9:1 to ~100:1. Useful classifiers have high sensitivity and specificity. Our results demonstrate that the proposed selection technique improves the sensitivity compared to weighted support-vector machine and available results in the literature for the same datasets.     

Machine learning modeling of family wide enzyme-substrate specificity screens

Biocatalysis is a promising approach to sustainably synthesize pharmaceuticals, complex natural products, and commodity chemicals at scale. However, the adoption of biocatalysis is limited by our ability to select enzymes that will catalyze their natural chemical transformation on non-natural substrates. While machine learning and in silico directed evolution are well-posed for this predictive modeling challenge, efforts to date have primarily aimed to increase activity against a single known substrate, rather than to identify enzymes capable of acting on new substrates of interest. To address this need, we curate 6 different high-quality enzyme family screens from the literature that each measure multiple enzymes against multiple substrates. We compare machine learning-based compound-protein interaction (CPI) modeling approaches from the literature used for predicting drug-target interactions. Surprisingly, comparing these interaction-based models against collections of independent (single task) enzyme-only or substrate-only models reveals that current CPI approaches are incapable of learning interactions between compounds and proteins in the current family level data regime. We further validate this observation by demonstrating that our no-interaction baseline can outperform CPI-based models from the literature used to guide the discovery of kinase inhibitors. Given the high performance of non-interaction based models, we introduce a new structure-based strategy for pooling residue representations across a protein sequence. Altogether, this work motivates a principled path forward in order to build and evaluate meaningful predictive models for biocatalysis and other drug discovery applications.