A survey on adverse drug reaction studies: data, tasks and machine learning methods

Prediction of adverse drug reactions using demographic and non-clinical drug characteristics in FAERS data

The presence of adverse drug reactions (ADRs) is an ongoing public health concern. While traditional methods to discover ADRs are very costly and limited, it is prudent to predict ADRs through non-invasive methods such as machine learning based on existing data. Although various studies exist regarding ADR prediction using non-clinical data, a process that leverages both demographic and non-clinical data for ADR prediction is missing. In addition, the importance of individual features in ADR prediction has yet to be fully explored. This study aims to develop an ADR prediction model based on demographic and non-clinical data, where we identify the highest contributing factors. We focus our efforts on 30 common and severe ADRs reported to the Food and Drug Administration (FDA) between 2012 and 2023. We have developed a random forest (RF) and deep learning (DL) machine learning model that ingests demographic data (e.g., Age and Gender of patients) and non-clinical data, which includes chemical, molecular, and biological drug characteristics. We successfully unified both demographic and non-clinical data sources within a complete dataset regarding ADR prediction. Model performances were assessed via the area under the receiver operating characteristic curve (AUC) and the mean average precision (MAP). We demonstrated that our parsimonious models, which include only the top 20 most important features comprising 5 demographic features and 15 non-clinical features (13 molecular and 2 biological), achieve ADR prediction performance comparable to a less practical, feature-rich model consisting of all 2,315 features. Specifically, our models achieved an AUC of 0.611 and 0.674 for RF and DL algorithms, respectively. We hope our research provides researchers and clinicians with valuable insights and facilitates future research designs by identifying top ADR predictors (including demographic information) and practical parsimonious models.

Central-Smoothing Hypergraph Neural Networks for Predicting Drug-Drug Interactions

Predicting drug-drug interactions (DDIs) is the problem of predicting side effects (unwanted outcomes) of a pair of drugs using drug information and known side effects of many pairs. This problem can be formulated as predicting labels (i.e., side effects) for each pair of nodes in a DDI graph, of which nodes are drugs and edges are interacting drugs with known labels. State-of-the-art methods for this problem are graph neural networks (GNNs), which leverage neighborhood information in the graph to learn node representations. For DDI, however, there are many labels with complicated relationships due to the nature of side effects. Usual GNNs often fix labels as one-hot vectors that do not reflect label relationships and potentially do not obtain the highest performance in the difficult cases of infrequent labels. In this brief, we formulate DDI as a hypergraph where each hyperedge is a triple: two nodes for drugs and one node for a label. We then present CentSmoothie, a hypergraph neural network (HGNN) that learns representations of nodes and labels altogether with a novel " central-smoothing " formulation. We empirically demonstrate the performance advantages of CentSmoothie in simulations as well as real datasets.

In silico off-target profiling for enhanced drug safety assessment

Ensuring drug safety in the early stages of drug development is crucial to avoid costly failures in subsequent phases. However, the economic burden associated with detecting drug off-targets and potential side effects through in vitro safety screening and animal testing is substantial. Drug off-target interactions, along with the adverse drug reactions they induce, are significant factors affecting drug safety. To assess the liability of candidate drugs, we developed an artificial intelligence model for the precise prediction of compound off-target interactions, leveraging multi-task graph neural networks. The outcomes of off-target predictions can serve as representations for compounds, enabling the differentiation of drugs under various ATC codes and the classification of compound toxicity. Furthermore, the predicted off-target profiles are employed in adverse drug reaction (ADR) enrichment analysis, facilitating the inference of potential ADRs for a drug. Using the withdrawn drug Pergolide as an example, we elucidate the mechanisms underlying ADRs at the target level, contributing to the exploration of the potential clinical relevance of newly predicted off-target interactions. Overall, our work facilitates the early assessment of compound safety/toxicity based on off-target identification, deduces potential ADRs of drugs, and ultimately promotes the secure development of drugs.

Predicting Drugs Suspected of Causing Adverse Drug Reactions Using Graph Features and Attention Mechanisms

BACKGROUND

Adverse drug reactions (ADRs) refer to an unintended harmful reaction that occurs after the administration of a medication for therapeutic purposes, which is unrelated to the intended pharmacological action of the drug. In the United States, ADRs account for 6% of all hospital admissions annually. The cost of ADR-related illnesses in 2016 was estimated at USD 528.4 billion. Increasing the awareness of ADRs is an effective measure to prevent them. Assessing suspected drugs in adverse events helps to enhance the awareness of ADRs.

METHODS

In this study, a suspect drug assisted judgment model (SDAJM) is designed to identify suspected drugs in adverse events. This framework utilizes the graph isomorphism network (GIN) and an attention mechanism to extract features based on patients' demographic information, drug information, and ADR information.

RESULTS

By comparing it with other models, the results of various tests show that this model performs well in predicting the suspected drugs in adverse reaction events. ADR signal detection was conducted on a group of cardiovascular system drugs, and case analyses were performed on two classic drugs, Mexiletine and Captopril, as well as on two classic antithyroid drugs. The results indicate that the model can accomplish the task of predicting drug ADRs. Validation using benchmark datasets from ten drug discovery domains shows that the model is applicable to classification tasks on the Tox21 and SIDER datasets.

CONCLUSIONS

This study applies deep learning methods to construct the SDAJM model for three purposes: (1) identifying drugs suspected to cause adverse drug events (ADEs), (2) predicting the ADRs of drugs, and (3) other drug discovery tasks. The results indicate that this method can offer new directions for research in the field of ADRs.

Graph reasoning method enhanced by relational transformers and knowledge distillation for drug-related side effect prediction

Identifying the side effects related to drugs is beneficial for reducing the risk of drug development failure and saving the drug development cost. We proposed a graph reasoning method, RKDSP, to fuse the semantics of multiple connection relationships, the local knowledge within each meta-path, the global knowledge among multiple meta-paths, and the attributes of the drug and side effect node pairs. We constructed drug-side effect heterogeneous graphs consisting of the drugs, side effects, and their similarity and association connections. Multiple relational transformers were established to learn node features from diverse meta-path semantic perspectives. A knowledge distillation module was constructed to learn local and global knowledge of multiple meta-paths. Finally, an adaptive convolutional neural network-based strategy was presented to adaptively encode the attributes of each drug-side effect node pair. The experimental results demonstrated that RKDSP outperforms the compared state-of-the-art prediction approaches.

Withdrawn 2.0-update on withdrawn drugs with pharmacovigilance data

One challenge in the development of novel drugs is their interaction with potential off-targets, which can cause unintended side-effects, that can lead to the subsequent withdrawal of approved drugs. At the same time, these off-targets may also present a chance for the repositioning of withdrawn drugs for new indications, which are potentially rare or more severe than the original indication and where certain adverse reactions may be avoidable or tolerable. To enable further insights into this topic, we updated our database Withdrawn by adding pharmacovigilance data from the FDA Adverse Event Reporting System (FAERS), as well as mechanism of action and human disease pathway prediction features for drugs that are or were temporarily withdrawn or discontinued in at least one country. As withdrawal data are still spread over dozens of national websites, we are continuously updating our lists of discontinued or withdrawn drugs and related (off-)targets. Furthermore, new systematic entry points for browsing the data, such as an ATC tree, were added, increasing the accessibility of the database in a user-friendly way. Withdrawn 2.0 is publicly available without the need for registration or login at https://bioinformatics.charite.de/withdrawn_3/index.php.

Machine learning models to detect and predict patient safety events using electronic health records: A systematic review

INTRODUCTION

Identifying patient safety events using electronic health records (EHRs) and automated machine learning-based detection methods can help improve the efficiency and quality of healthcare service provision.

OBJECTIVE

This study aimed to systematically review machine learning-based methods and techniques, as well as their results for patient safety event management using EHRs.

METHODS

We reviewed the studies that focused on machine learning techniques, including automatic prediction and detection of patient safety events and medical errors through EHR analysis to manage patient safety events. The data were collected by searching Scopus, PubMed (Medline), Web of Science, EMBASE, and IEEE Xplore databases.

RESULTS

After screening, 41 papers were reviewed. Support vector machine (SVM), random forest, conditional random field (CRF), and bidirectional long short-term memory with conditional random field (BiLSTM-CRF) algorithms were mostly applied to predict, identify, and classify patient safety events using EHRs; however, they had different performances. BiLSTM-CRF was employed in most of the studies to extract and identify concepts, e.g., adverse drug events (ADEs) and adverse drug reactions (ADRs), as well as relationships between drug and severity, drug and ADEs, drug and ADRs. Recurrent neural networks (RNN) and BiLSTM-CRF had the best results in detecting ADEs compared to other patient safety events. Linear classifiers and Naive Bayes (NB) had the highest performance for ADR detection. Logistic regression had the best results in detecting surgical site infections. According to the findings, the quality of articles has non-significantly improved in recent years, but they had low average scores.

CONCLUSIONS

Machine learning can be useful in automatic detection and prediction of patient safety events. However, most of these algorithms have not yet been externally validated or prospectively tested. Therefore, further studies are required to improve the performance of these automated systems.

Interpretable Drug-to-Drug Network Features for Predicting Adverse Drug Reactions

Recent years have witnessed booming data on drugs and their associated adverse drug reactions (ADRs). It was reported that these ADRs have resulted in a high hospitalisation rate worldwide. Therefore, a tremendous amount of research has been carried out to predict ADRs in the early phases of drug development, with the goal of reducing possible future risks. The pre-clinical and clinical phases of drug research can be time-consuming and cost-ineffective, so academics are looking forward to more extensive data mining and machine learning methods to be applied in this field of study. In this paper, we try to construct a drug-to-drug network based on non-clinical data sources. The network presents underlying relationships between drug pairs according to their common ADRs. Then, multiple node-level and graph-level network features are extracted from this network, e.g., weighted degree centrality, weighted PageRanks, etc. After concatenating the network features to the original drug features, they were fed into seven machine learning models, e.g., logistic regression, random forest, support vector machine, etc., and were compared to the baseline, where there were no network-based features considered. These experiments indicate that all the tested machine-learning methods would benefit from adding these network features. Among all these models, logistic regression (LR) had the highest mean AUROC score (82.1%) across all ADRs tested. Weighted degree centrality and weighted PageRanks were identified to be the most critical network features in the LR classifier. These pieces of evidence strongly indicate that the network approach can be vital in future ADR prediction, and this network-based approach could also be applied to other health informatics datasets.

A comprehensive tool for tumor precision medicine with pharmaco-omics data analysis

Background: Cancer precision medicine is an effective strategy to fight cancers by bridging genomics and drug discovery to provide specific treatment for patients with different genetic characteristics. Although some public databases and modelling frameworks have been developed through studies on drug response, most of them only considered the ramifications of the drug on the cell line and the effects on the patient still require a huge amount of work to integrate data from various databases and calculations, especially concerning precision treatment. Furthermore, not only efficacy but also the adverse effects of drugs on patients should be taken into account during cancer treatment. However, the adverse effects as essential indicators of drug safety assessment are always neglected. Method: A holistic estimation explores various drugs' efficacy levels by calculating their potency both in reversing and enhancing cancer-associated gene expression change. And a method for bridging the gap between cell culture and living tissue estimates the effectiveness of a drug on individual patients through the mappings of various cell lines to each person according to their genetic mutation similarities. Result: We predicted the efficacy of FDA-recommended drugs, taking into account both efficacy and toxicity, and obtained consistent results. We also provided an intuitive and easy-to-use web server called DBPOM (http://www.dbpom.net/, a comprehensive database of pharmaco-omics for cancer precision medicine), which not only integrates the above methods but also provides calculation results on more than 10,000 small molecule compounds and drugs. As a one-stop web server, clinicians and drug researchers can also analyze the overall effect of a drug or a drug combination on cancer patients as well as the biological functions that they target. DBPOM is now public, free to use with no login requirement, and contains all the data and code. Conclusion: Both the positive and negative effects of drugs during precision treatment are essential for practical application of drugs. DBPOM based on the two effects will become a vital resource and analysis platform for drug development, drug mechanism studies and the discovery of new therapies.

Prediction of drug side effects with transductive matrix co-completion

MOTIVATION

Side effects of drugs could cause severe health problems and the failure of drug development. Drug-target interactions are the basis for side effect production and are important for side effect prediction. However, the information on the known targets of drugs is incomplete. Furthermore, there could be also some missing data in the existing side effect profile of drugs. As a result, new methods are needed to deal with the missing features and missing labels in the problem of side effect prediction.

RESULTS

We propose a novel computational method based on transductive matrix co-completion and leverage the low-rank structure in the side effects and drug-target data. Positive-unlabelled learning is incorporated into the model to handle the impact of unobserved data. We also introduce graph regularization to integrate the drug chemical information for side effect prediction. We collect the data on side effects, drug targets, drug-associated proteins and drug chemical structures to train our model and test its performance for side effect prediction. The experiment results show that our method outperforms several other state-of-the-art methods under different scenarios. The case study and additional analysis illustrate that the proposed method could not only predict the side effects of drugs but also could infer the missing targets of drugs.

AVAILABILITY AND IMPLEMENTATION

The data and the code for the proposed method are available at https://github.com/LiangXujun/GTMCC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Evaluating molecular fingerprint-based models of drug side effects against a statistical control

There are many machine learning models that use molecular fingerprints of drugs to predict side effects. Characterizing their skill is necessary for understanding their usefulness in pharmaceutical development. Here, we analyze a statistical control of side effect prediction skill, develop a pipeline for benchmarking models, and evaluate how well existing models predict side effects identified in pharmaceutical documentation. We demonstrate that molecular fingerprints are useful for ranking drugs by their likelihood to cause a given side effect. However, the predictions for one or more drugs overall benefit only marginally from molecular fingerprints when ranking the likelihoods of many possible side effects, and display at most modest overall skill at identifying the side effects that do and do not occur.

A machine learning model using SNPs obtained from a genome-wide association study predicts the onset of vincristine-induced peripheral neuropathy

Vincristine treatment may cause peripheral neuropathy. In this study, we identified the genes associated with the development of peripheral neuropathy due to vincristine therapy using a genome-wide association study (GWAS) and constructed a predictive model for the development of peripheral neuropathy using genetic information-based machine learning. The study included 72 patients admitted to the Department of Hematology, Tokushima University Hospital, who received vincristine. Of these, 56 were genotyped using the Illumina Asian Screening Array-24 Kit, and a GWAS for the onset of peripheral neuropathy caused by vincristine was conducted. Using Sanger sequencing for 16 validation samples, the top three single nucleotide polymorphisms (SNPs) associated with the onset of peripheral neuropathy were determined. Machine learning was performed using the statistical software R package "caret". The 56 GWAS and 16 validation samples were used as the training and test sets, respectively. Predictive models were constructed using random forest, support vector machine, naive Bayes, and neural network algorithms. According to the GWAS, rs2110179, rs7126100, and rs2076549 were associated with the development of peripheral neuropathy on vincristine administration. Machine learning was performed using these three SNPs to construct a prediction model. A high accuracy of 93.8% was obtained with the support vector machine and neural network using rs2110179 and rs2076549. Thus, peripheral neuropathy development due to vincristine therapy can be effectively predicted by a machine learning prediction model using SNPs associated with it.

Advancing drug safety science by integrating molecular knowledge with post-marketing adverse event reports

Promising drug development efforts may frequently fail due to unintended adverse reactions. Several methods have been developed to analyze such data, aiming to improve pharmacovigilance and drug safety. In this work, we provide a brief review of key directions to quantitatively analyzing adverse events and explore the potential of augmenting these methods using additional molecular data descriptors. We argue that molecular expansion of adverse event data may provide a path to improving the insights gained through more traditional pharmacovigilance approaches. Examples include the ability to assess statistical relevance with respect to underlying biomolecular mechanisms, the ability to generate plausible causative hypotheses and/or confirmation where possible, the ability to computationally study potential clinical trial designs and/or results, as well as the further provision of advanced features incorporated in innovative methods, such as machine learning. In summary, molecular data expansion provides an elegant way to extend mechanistic modeling, systems pharmacology, and patient‐centered approaches for the assessment of drug safety. We anticipate that such advances in real‐world data informatics and outcome analytics will help to better inform public health, via the improved ability to prospectively understand and predict various types of drug‐induced molecular perturbations and adverse events.

Recent Progress in Traditional Chinese Medicines and Their Mechanism in the Treatment of Allergic Rhinitis

Objective

To conduct a systematic review on the mechanism of action and use of traditional Chinese medicines (TCM) in allergic rhinitis treatment.

Background

Allergic rhinitis (AR) is a type I allergic disease of the immune system induced by immunoglobulin E mediated inflammation and is characterized by sneezing, nasal itching, paroxysmal nasal obstruction, mucosal edema, cough, and rhinorrhea. More than 500 million people have been affected by rhinitis worldwide in the past 20 years, leading to negative effects on health, quality of life, and social relationships. Currently, the trending medicines used in the case of AR include intranasal corticosteroids and oral H1 antihistamines, which are given as combinatorial medicines supplemented with immune therapy. These medications have been found to be very effective in either the short term or long term; however, they have been found to possess some serious side effects. Search Methodology. The information in this article on classical and traditional Chinese medications used to treat AR was derived from original papers and reviews published in Chinese and English language journals. Two Chinese databases (Wanfang and CNKI) and three English databases (Cochrane Library, PubMed, and Embase) were utilized for data gathering.

Results

Traditional Chinese remedies have been identified to influence the production of cytokines such as IL-5 and IL-6, which are key mediators of eosinophilic inflammation, TNF-α, which stimulates TH2 cells at the site of inflammation, and NF-кB, which is required for cytokine and IgE antibody production. TCM has also been shown to be successful in lowering histamine levels, preserving histological changes by decreasing the thickness of the lamina propria, and downregulating the expression of Orai1, STIM1, and TRYC1, showing low expression of Ca⁺² channel proteins.

Conclusion

In this review, we discussed a series of classical, traditional Chinese medications, including Centipeda minima, Scutellaria baicalensis, licorice root (Glycyrrhiza uralensis), and others, as potential antiallergic agents and investigate their in vivo effect upon the production of cytokines and release of histamines for allergic rhinitis treatment.

A Data-Driven Medical Decision Framework for Associating Adverse Drug Events with Drug-Drug Interaction Mechanisms

Adverse drug events (ADEs) occur when multiple drugs interact within an individual, thus causing effects that were not initially predicted. Such toxic interactions lead to morbidity and mortality. Contemporary research surrounding ADEs has tended to focus on the detection of potential ADEs without great concern for elucidating the associations of drug-drug interaction (DDI) mechanisms that can predict potential adverse drug reactions (ADRs). Such associations are of great practical importance for everyday pharmacovigilance efforts. This study presents a data-driven framework for conducting knowledge-driven data analysis that combines a semantic inference system and enrichment analysis in order to identify potential ADE mechanisms. The framework was used to rank mechanisms according to their relevance for DDIs and also to categorize ADEs based on the number of DDI mechanism associations identified through enrichment analysis. Its validity is demonstrated through using both commercial and publicly available DDI resources. The results of this study solidly prove the framework's effectiveness and highlight potential for future research by way of incorporating additional and broader data to deepen and expand its capabilities.

ADENet: a novel network-based inference method for prediction of drug adverse events

Identification of adverse drug events (ADEs) is crucial to reduce human health risks and improve drug safety assessment. With an increasing number of biological and medical data, computational methods such as network-based methods were proposed for ADE prediction with high efficiency and low cost. However, previous network-based methods rely on the topological information of known drug-ADE networks, and hence cannot make predictions for novel compounds without any known ADE. In this study, we introduced chemical substructures to bridge the gap between the drug-ADE network and novel compounds, and developed a novel network-based method named ADENet, which can predict potential ADEs for not only drugs within the drug-ADE network, but also novel compounds outside the network. To show the performance of ADENet, we collected drug-ADE associations from a comprehensive database named MetaADEDB and constructed a series of network-based prediction models. These models obtained high area under the receiver operating characteristic curve values ranging from 0.871 to 0.947 in 10-fold cross-validation. The best model further showed high performance in external validation, which outperformed a previous network-based and a recent deep learning-based method. Using several approved drugs as case studies, we found that 32-54% of the predicted ADEs can be validated by the literature, indicating the practical value of ADENet. Moreover, ADENet is freely available at our web server named NetInfer (http://lmmd.ecust.edu.cn/netinfer). In summary, our method would provide a promising tool for ADE prediction and drug safety assessment in drug discovery and development.