Identifying potential adverse drug reactions (ADRs) is critically important for drug discovery and public health. Here we developed a multiple evidence fusion (MEF) method for the large-scale prediction of drug ADRs that can handle both approved drugs and novel molecules. MEF is based on the similarity reference by collaborative filtering, and integrates multiple similarity measures from various data types, taking advantage of the complementarity in the data. We used MEF to integrate drug-related and ADR-related data from multiple levels, including the network structural data formed by known drug-ADR relationships for predicting likely unknown ADRs. On cross-validation, it obtains high sensitivity and specificity, substantially outperforming existing methods that utilize single or a few data types. We validated our prediction by their overlap with drug-ADR associations that are known in databases. The proposed computational method could be used for complementary hypothesis generation and rapid analysis of potential drug-ADR interactions.

Predicting drug side effects is an important topic in the drug discovery. Although several machine learning methods have been proposed to predict side effects, there is still space for improvements. Firstly, the side effect prediction is a multi-label learning task, and we can adopt the multi-label learning techniques for it. Secondly, drug-related features are associated with side effects, and feature dimensions have specific biological meanings. Recognizing critical dimensions and reducing irrelevant dimensions may help to reveal the causes of side effects.

Underreporting is a major limitation of the voluntary reporting system of adverse drug reactions (ADRs). A 2009 systematic review showed the knowledge and attitudes of health professionals were strongly related with underreporting of ADRs.

Occurrence of adverse drug reactions is a major global health problem mostly affecting older adults. Identifying the magnitude and predictors of adverse drug reactions is crucial to developing strategies to mitigate the burden of adverse drug reactions. This study's objectives were to estimate and compare the prevalences of adverse drug reactions, to characterize them and to identify the predictors among hospitalized older adults.

Background: Adverse drug reactions (ADRs) are a major cause of hospital admissions, prolonged hospital stays, morbidity, and drug-related mortality. In this study, we sought to identify the most frequently reported medications and associated side effects in adolescent-aged patients in an effort to prioritize clinical pharmacology consultation efforts for hospitals seeking to improve patient safety.   Methods: Quarterly reported data were obtained from the United States Food and Drug Administration Adverse Events Reporting System (FAERS) from the third quarter of 2014 and ending in the third quarter of 2017. We then used the GeneCards database to map the pharmacogenomic biomarkers associated with the most reported FAERS drugs. Data homogenization and statistics analysis were all conducted in R for statistical programming. Results: We identified risperidone (10.64%) as the compound with the most reported ADRs from all reported cases. Males represented 90.1% of reported risperidone cases with gynecomastia being the most reported ADR. Ibuprofen OR=188 (95% CI, 105.00 - 335.00) and quetiapine fumarate OR=116 (95% CI, 48.40 - 278.00) were associated with the highest odds of completed suicide in teenagers. Ondansetron hydrochloride OR=7.12 (95% CI, 1.59 - 31.9) resulted in the highest odds of pneumothorax. Lastly, olanzapine (8.96%) represented the compound with the most reported drug-drug interactions cases, while valproic acid OR=221 (95% CI, 93.900 - 522.00) was associated with the highest odds of drug-drug interactions. Conclusion: Despite any data limitations, physicians prescribing risperidone in males should be aware of the high rates of adverse drug events and an alternative psychotropic should be considered in male patients. Further, patients with a history of pneumothorax or genetically predisposed to pneumothorax should be considered for an alternative antiemetic to ondansetron hydrochloride, due to increased odds associated with the drug and adverse event.

Since side-effects of drugs are one of the primary reasons for their failure in clinical trials, predicting their side-effects can help reduce drug development costs. We proposed a method based on heterogeneous graph transformer and capsule networks for side-effect-drug-association prediction (TCSD). The method encodes and integrates attributes from multiple types of neighbor nodes, connection semantics, and multi-view pairwise information. In each drug-side-effect heterogeneous graph, a target node has two types of neighbor nodes, the drug nodes and the side-effect ones. We proposed a new heterogeneous graph transformer-based context representation learning module. The module is able to encode specific topology and the contextual relations among multiple kinds of nodes. There are similarity and association connections between the target node and its various types of neighbor nodes, and these connections imply semantic diversity. Therefore, we designed a new strategy to measure the importance of a neighboring node to the target node and incorporate different semantics of the connections between the target node and its multi-type neighbors. Furthermore, we designed attentions at the neighbor node type level and at the graph level, respectively, to obtain enhanced informative neighbor node features and multi-graph features. Finally, a pairwise multi-view feature learning module based on capsule networks was built to learn the pairwise attributes from the heterogeneous graphs. Our prediction model was evaluated using a public dataset, and the cross-validation results showed it achieved superior performance to several state-of-the-art methods. Ablation experiments undertaken demonstrated the effectiveness of heterogeneous graph transformer-based context encoding, the position enhanced pairwise attribute learning, and the neighborhood node category-level attention. Case studies on five drugs further showed TCSD's ability in retrieving potential drug-related side-effect candidates, and TCSD inferred the candidate side-effects for 708 drugs.

Adverse drug events constitute a major challenge for the success of clinical trials. Several computational strategies have been suggested to estimate the risk of adverse drug events in preclinical drug development. While these approaches have demonstrated high utility in practice, they are at the same time limited to specific information sources. Thus, many current computational approaches neglect a wealth of information which results from the integration of different data sources, such as biological protein function, gene expression, chemical compound structure, cell-based imaging and others. In this work we propose an integrative and explainable multi-modal Graph Machine Learning approach (MultiGML), which fuses knowledge graphs with multiple further data modalities to predict drug related adverse events and general drug target-phenotype associations. MultiGML demonstrates excellent prediction performance compared to alternative algorithms, including various traditional knowledge graph embedding techniques. MultiGML distinguishes itself from alternative techniques by providing in-depth explanations of model predictions, which point towards biological mechanisms associated with predictions of an adverse drug event. Hence, MultiGML could be a versatile tool to support decision making in preclinical drug development.

Identification of various factors involved in adverse drug reactions in target proteins to develop therapeutic drugs with minimal/no side effect is very important. In this context, we have performed a comparative evolutionary rate analyses between the genes exhibiting drug side-effect(s) (SET) and genes showing no side effect (NSET) with an aim to increase the prediction accuracy of SET/NSET proteins using evolutionary rate determinants. We found that SET proteins are more conserved than the NSET proteins. The rates of evolution between SET and NSET protein primarily depend upon their noncomplex (protein complex association number = 0) forming nature, phylogenetic age, multifunctionality, membrane localization, and transmembrane helix content irrespective of their essentiality, total druggability (total number of drugs/target), m-RNA expression level, and tissue expression breadth. We also introduced two novel terms-killer druggability (number of drugs with killing side effect(s)/target), essential druggability (number of drugs targeting essential proteins/target) to explain the evolutionary rate variation between SET and NSET proteins. Interestingly, we noticed that SET proteins are younger than NSET proteins and multifunctional younger SET proteins are candidates of acquiring killing side effects. We provide evidence that higher killer druggability, multifunctionality, and transmembrane helices support the conservation of SET proteins over NSET proteins in spite of their recent origin. By employing all these entities, our Support Vector Machine model predicts human SET/NSET proteins to a high degree of accuracy (∼86%).

In silico network-based methods have shown promising results in the field of drug development. Yet, most of networks used in the previous research have not included context information even though biological associations actually do appear in the specific contexts. Here, we reconstruct an anatomical context-specific network by assigning contexts to biological associations using protein expression data and scientific literature. Furthermore, we employ the context-specific network for the analysis of drug effects with a proximity measure between drug targets and diseases. Distinct from previous context-specific networks, intercellular associations and phenomic level entities such as biological processes are included in our network to represent the human body. It is observed that performances in inferring drug-disease associations are increased by adding context information and phenomic level entities. In particular, hypertension, a disease related to multiple organs and associated with several phenomic level entities, is analyzed in detail to investigate how our network facilitates the inference of drug-disease associations. Our results indicate that the inclusion of context information, intercellular associations, and phenomic level entities can contribute towards a better prediction of drug-disease associations and provide detailed insight into understanding of how drugs affect diseases in the human body.

Efficient representations of drugs provide important support for healthcare analytics, such as drug-drug interaction (DDI) prediction and drug-drug similarity (DDS) computation. However, incomplete annotated data and drug feature sparseness create substantial barriers for drug representation learning, making it difficult to accurately identify new drug properties prior to public release. To alleviate these deficiencies, we propose KMR, a knowledge-oriented feature-driven method which can learn drug related knowledge with an accurate representation. We conduct series of experiments on real-world medical datasets to demonstrate that KMR is capable of drug representation learning. KMR can support to discover meaningful DDI with an accuracy rate of 92.19%, demonstrating that techniques developed in KMR significantly improve the prediction quality for new drugs not seen at training. Experimental results also indicate that KMR can identify DDS with an accuracy rate of 88.7% by facilitating drug knowledge, outperforming existing state-of-the-art drug similarity measures.

The emergence of large-scale genomic, chemical and pharmacological data provides new opportunities for drug discovery and repositioning. In this work, we develop a computational pipeline, called DTINet, to predict novel drug-target interactions from a constructed heterogeneous network, which integrates diverse drug-related information. DTINet focuses on learning a low-dimensional vector representation of features, which accurately explains the topological properties of individual nodes in the heterogeneous network, and then makes prediction based on these representations via a vector space projection scheme. DTINet achieves substantial performance improvement over other state-of-the-art methods for drug-target interaction prediction. Moreover, we experimentally validate the novel interactions between three drugs and the cyclooxygenase proteins predicted by DTINet, and demonstrate the new potential applications of these identified cyclooxygenase inhibitors in preventing inflammatory diseases. These results indicate that DTINet can provide a practically useful tool for integrating heterogeneous information to predict new drug-target interactions and repurpose existing drugs.Network-based data integration for drug-target prediction is a promising avenue for drug repositioning, but performance is wanting. Here, the authors introduce DTINet, whose performance is enhanced in the face of noisy, incomplete and high-dimensional biological data by learning low-dimensional vector representations.

A wide variety of drugs can cause myoclonus. To illustrate this, we first discuss two personally observed cases, one presenting with generalized, but facial-predominant, myoclonus that was induced by amantadine; and the other presenting with propriospinal myoclonus triggered by an antibiotic. We then review the literature on drugs that may cause myoclonus, extracting the corresponding clinical phenotype and suggested underlying pathophysiology. The most frequently reported classes of drugs causing myoclonus include opiates, antidepressants, antipsychotics, and antibiotics. The distribution of myoclonus ranges from focal to generalized, even amongst patients using the same drug, which suggests various neuro-anatomical generators. Possible underlying pathophysiological alterations involve serotonin, dopamine, GABA, and glutamate-related processes at various levels of the neuraxis. The high number of cases of drug-induced myoclonus, together with their reported heterogeneous clinical characteristics, underscores the importance of considering drugs as a possible cause of myoclonus, regardless of its clinical characteristics.

Drug development involves a deep understanding of the mechanisms of action and possible side effects of each drug, and sometimes results in the identification of new and unexpected uses for drugs, termed as drug repurposing. Both in case of serendipitous observations and systematic mechanistic explorations, confirmation of new indications for a drug requires hypothesis building around relevant drug-related data, such as molecular targets involved, and patient and cellular responses. These datasets are available in public repositories, but apart from sifting through the sheer amount of data imposing computational bottleneck, a major challenge is the difficulty in selecting which databases to use from an increasingly large number of available databases. The database selection is made harder by the lack of an overview of the types of data offered in each database. In order to alleviate these problems and to guide the end user through the drug repurposing efforts, we provide here a survey of 102 of the most promising and drug-relevant databases reported to date. We summarize the target coverage and types of data available in each database and provide several examples of how multi-database exploration can facilitate drug repurposing.

Failure to demonstrate efficacy and safety issues are important reasons that drugs do not reach the market. An incomplete understanding of how drugs exert their effects hinders regulatory and pharmaceutical industry projections of a drug's benefits and risks. Signaling pathways mediate drug response and while many signaling molecules have been characterized for their contribution to disease or their role in drug side effects, our knowledge of these pathways is incomplete. To better understand all signaling molecules involved in drug response and the phenotype associations of these molecules, we created a novel method, PathFX, a non-commercial entity, to identify these pathways and drug-related phenotypes. We benchmarked PathFX by identifying drugs' marketed disease indications and reported a sensitivity of 41%, a 2.7-fold improvement over similar approaches. We then used PathFX to strengthen signals for drug-adverse event pairs occurring in the FDA Adverse Event Reporting System (FAERS) and also identified opportunities for drug repurposing for new diseases based on interaction paths that associated a marketed drug to that disease. By discovering molecular interaction pathways, PathFX improved our understanding of drug associations to safety and efficacy phenotypes. The algorithm may provide a new means to improve regulatory and therapeutic development decisions.

The bipartite network representation of the drug-target interactions (DTIs) in a biosystem enhances understanding of the drugs' multifaceted action modes, suggests therapeutic switching for approved drugs and unveils possible side effects. As experimental testing of DTIs is costly and time-consuming, computational predictors are of great aid. Here, for the first time, state-of-the-art DTI supervised predictors custom-made in network biology were compared-using standard and innovative validation frameworks-with unsupervised pure topological-based models designed for general-purpose link prediction in bipartite networks. Surprisingly, our results show that the bipartite topology alone, if adequately exploited by means of the recently proposed local-community-paradigm (LCP) theory-initially detected in brain-network topological self-organization and afterwards generalized to any complex network-is able to suggest highly reliable predictions, with comparable performance with the state-of-the-art-supervised methods that exploit additional (non-topological, for instance biochemical) DTI knowledge. Furthermore, a detailed analysis of the novel predictions revealed that each class of methods prioritizes distinct true interactions; hence, combining methodologies based on diverse principles represents a promising strategy to improve drug-target discovery. To conclude, this study promotes the power of bio-inspired computing, demonstrating that simple unsupervised rules inspired by principles of topological self-organization and adaptiveness arising during learning in living intelligent systems (like the brain) can efficiently equal perform complicated algorithms based on advanced, supervised and knowledge-based engineering.

PRN is the acronym for 'pro re nata,' written against prescriptions whose administration should be based on patients' needs, rather than at set times. The aim of this systematic review was to explore safety issues and adverse events arising from PRN prescription and administration. Electronic databases including Scopus, PubMed [including Medline], Embase, Cinahl, Web of Science and ProQuest were systematically searched to retrieve articles published from 2005 to 2017.

Some 14% of global prevalence, based on high-income country populations, suffers from migraine. Chronic migraine is very disabling, being characterized by at least 15 headache days per month of which at least 8 days present the features of migraine. Onabotulinumtoxin A, targeting the machinery for exocytosis of neurotransmitters and neuropeptides, has been approved for use in chronic migraine since 2010. This systematic review and meta-analysis appraises the safety of onabotulinumtoxin A treatment for chronic migraine and the occurrence of treatment-related adverse events (TRAEs) in randomized, clinical studies in comparison with placebo or other comparators and preventative treatments according to the most updated Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) 2020 recommendations. The search retrieved 888 total records. Nine studies are included and seven were eligible for meta-analysis. The present study demonstrates that toxin produces more TRAEs than placebo, but less than oral topiramate, supporting the safety of onabotulinumtoxin A, and highlights the heterogeneity of the studies present in the literature (I2 = 96%; p < 0.00001). This points to the need for further, adequately powered, randomized clinical trials assessing the safety of onabotulinumtoxin A in combination with the newest treatment options.

Colchicine has been used historically as an anti-inflammatory agent for a wide range of diseases. Little is known regarding the relationship between colchicine use and infectious disease outcomes. The objective of this study was to systematically examine infectious adverse events associated with colchicine usage and the clinical use of colchicine for infectious diseases.

Polypharmacy is common among older adults and is associated with adverse outcomes. Polypharmacy increases the likelihood of receiving a potentially inappropriate medication (PIM). PIMs have traditionally been defined as medications that have either no benefit (e.g. therapeutic duplication) or increased risk (e.g. altered pharmacodynamics/kinetics with aging). A growing literature supports the notion that these represent only a subset of the potential risks of medications prescribed to older adults. Different authors have proposed new sets of criteria for evaluating medication appropriateness. This narrative review had two objectives: 1) to summarize the contents of these criteria in order to obtain preliminary information about where clinical consensus exists regarding appropriateness; 2) The second was to describe studies examining the risks and benefits of medications identified by the criteria to determine the strength of the evidence supporting the derivation of these criteria. We identified 13 articles sharing overlapping criteria for evaluating appropriateness including: (1) delayed time to benefit; (2) altered benefit-harm ratios in the face of competing risks; (3) effects that do not match patients' goals; and (4) nonadherence. The similarities across the articles suggested strong clinical consensus; however, the articles presented little data directly supporting these criteria. Additional studies provide evidence for the proof of concept that average estimates of benefit and harm derived from randomized controlled trials may differ from the benefits and harms experienced by older persons. However, more data are required to characterize the benefits and harms of medications in the context of the regimen as a whole and the individual's health status.

Adverse anticholinergic drug reactions are common, yet evidence on how to reduce exposure to anticholinergic activity and reliably measure successful deprescribing is still scant. This study proposes an algorithm-based approach to evaluate and reduce anticholinergic load, and reports the results of its pilot testing.