No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Machine learning-based prediction of drug-drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties
Abstract
Drug-drug interactions (DDIs) are an important consideration in both drug development and clinical application, especially for co-administered medications. While it is necessary to identify all possible DDIs during clinical trials, DDIs are frequently reported after the drugs are approved for clinical use, and they are a common cause of adverse drug reactions (ADR) and increasing healthcare costs. Computational prediction may assist in identifying potential DDIs during clinical trials.
Here we propose a heterogeneous network-assisted inference (HNAI) framework to assist with the prediction of DDIs. First, we constructed a comprehensive DDI network that contained 6946 unique DDI pairs connecting 721 approved drugs based on DrugBank data. Next, we calculated drug-drug pair similarities using four features: phenotypic similarity based on a comprehensive drug-ADR network, therapeutic similarity based on the drug Anatomical Therapeutic Chemical classification system, chemical structural similarity from SMILES data, and genomic similarity based on a large drug-target interaction network built using the DrugBank and Therapeutic Target Database. Finally, we applied five predictive models in the HNAI framework: naive Bayes, decision tree, k-nearest neighbor, logistic regression, and support vector machine, respectively.
The area under the receiver operating characteristic curve of the HNAI models is 0.67 as evaluated using fivefold cross-validation. Using antipsychotic drugs as an example, several HNAI-predicted DDIs that involve weight gain and cytochrome P450 inhibition were supported by literature resources.
Through machine learning-based integration of drug phenotypic, therapeutic, structural, and genomic similarities, we demonstrated that HNAI is promising for uncovering DDIs in drug development and postmarketing surveillance.
... Deng et al. [5] presented a molecular similarity-based machine learning framework to predict DDIs using various classification algorithms such as naive bayes, decision tree, random forest, and so on. Cheng et al. [6] extracted drug features such as phenotypic, chemical, therapeutic, and genomic properties for classification, and applied five predictive models in the framework: naive bayes, decision tree, k-means, logistic regression, and support vector machine, respectively. The results indicated that integrating multiple classifiers is feasible. ...
... DDI prediction block At this stage, the embeddings of all the nodes in the heterogeneous network are obtained and these aggregations will be fed into the DDI prediction block to predict DDIs. For binary DDI prediction tasks, the interaction score is calculated by the sigmoid function as shown in Eq. (6). ...
... The combination of the local feature learning for individual drug information and the global feature learning for drug pairs generates a 2 by 64 graph vector as the model input. The block layers for individual drugs are set to 10, while the block layers for drug pairs are set to 8. The binary cross-entropy (BCE) loss function being used is demonstrated in Eq. (6). ...
Recent studies suggest that drug-drug interaction (DDI) prediction via computational approaches has significant importance for understanding the functions and co-prescriptions of multiple drugs. However, the existing silico DDI prediction methods either ignore the potential interactions among drug-drug pairs (DDPs), or fail to explicitly model and fuse the multi-scale drug feature representations for better prediction. In this study, we propose RGDA-DDI, a residual graph attention network (residual-GAT) and dual-attention based framework for drug-drug interaction prediction. A residual-GAT module is introduced to simultaneously learn multi-scale feature representations from drugs and DDPs. In addition, a dual-attention based feature fusion block is constructed to learn local joint interaction representations. A series of evaluation metrics demonstrate that the RGDA-DDI significantly improved DDI prediction performance on two public benchmark datasets, which provides a new insight into drug development.
... Moreover, ML/AI tools are scalable, which is particularly valuable in screening large libraries of drugs and herbal products and in prioritizing candidates for further experimental validation [47]. In addition, AI tools can integrate information regarding pharmacological pathways with chemoinformatic data and potentially provide mechanistic insights into DHIs [48]. In addition to pharmacological parameters, AI tools can also include patient clinical information, such as multimorbidity, pharmacogenomic data or even demographic characteristics, which align with the vision of ...
... AI methods have emerged as a powerful tool for the assessment of DDIs by analyzing different levels of data such as chemoinformatics, pharmacological pathways and clinical parameters [27,[82][83][84]. Various AI methods, including traditional ML, DL and other network-based approaches, have been employed to predict DDIs [27,33,34,48,[89][90][91]. Since the underlying pharmacology is similar, these approaches can be further extended for DHIs studies. ...
Artificial intelligence (AI) has emerged as a powerful tool in medical sciences that is revolutionizing various fields of drug research. AI algorithms can analyze large-scale biological data and identify molecular targets and pathways advancing pharmacological knowledge. An especially promising area is the assessment of drug interactions. The AI analysis of large datasets, such as drugs’ chemical structure, pharmacological properties, molecular pathways, and known interaction patterns, can provide mechanistic insights and identify potential associations by integrating all this complex information and returning potential risks associated with these interactions. In this context, an area where AI may prove valuable is in the assessment of the underlying mechanisms of drug interactions with natural products (i.e., herbs) that are used as dietary supplements. These products pose a challenging problem since they are complex mixtures of constituents with diverse and limited information regarding their pharmacological properties, especially their pharmacokinetic data. As the use of herbal products and supplements continues to grow, it becomes increasingly important to understand the potential interactions between them and conventional drugs and the associated adverse drug reactions. This review will discuss AI approaches and how they can be exploited in providing valuable mechanistic insights regarding the prediction of interactions between drugs and herbs, and their potential exploitation in experimental validation or clinical utilization.
... Исследования в области применения машинного обучения для анализа взаимодействия ЛС предпринимаются давно и ведутся достаточно интенсивно. Однако практически все эти работы относятся к анализу последствий парного взаимодействия (см., напр., [1][2][3][4][5]), тогда как практический интерес представляет анализ приема 5 и более ЛС. Парный анализ привлекателен тем, что он может быть проведен для весьма большого (порядка 10 тыс.) числа ЛС. ...
... На рисунке 1 дана визуализация матрицы инцидентности для пар в соответствии с формулой (1). Верхняя поверхность куба показывает возможность сочетания соответствующих препаратов, номера которых отложены по осям. ...
The model for ranking side effects in the combined use of drugs is constructed using the example of chronic heart failure. A numerical algorithm based on the allocation of fully connected subgraphs has been developed, which reduces the amount of calculations when analyzing combinations of several drugs. The results of the test calculations are presented. The program being developed can be useful as a medical decision support system.
... GANs generate novel drug-like molecules by training on chemical datasets, proposing compounds with desirable properties like strong binding affinity and optimal pharmacokinetics [69][70][71]. VAEs explore chemical space by interpolating between known compounds optimizing molecular properties for solubility, toxicity, and bioavailability [72][73][74]. Together, GANs and VAEs enhance drug discovery, facilitating the rapid development of novel therapeutics [75,76]. ...
Artificial Intelligence (AI) is transforming the drug development and Clinical Trials by improving efficiency, accuracy, and decision-making. AI predicts Pharmacokinetic (PK) and Pharmacodynamic (PD) properties, automates compound screening and enhances clinical testing throughput. In trial design, AI optimizes patient stratification and outcome prediction by analyzing vast datasets from previous trials and electronic health records, leading to cost-effective and adaptive trials. AI also facilitates real-time data monitoring, identifying discrepancies early to ensure data integrity and regulatory compliance. By integrating diverse data sources it streamlines clinical operations, reducing human error and manual workload. However, challenges persist in data quality and integration due to varying standards across sources, necessitating advanced harmonization techniques. Regulatory frameworks often lag behind AI advancements, creating uncertainty and potential delays. Ethical concerns, including patient privacy and data security, must also be addressed for responsible AI implementation. Establishing standardized protocols and ensuring regulatory alignment are critical for AI’s successful integration into clinical research. In conclusion, AI revolutionizes drug development and clinical trials, enhancing efficiency and accuracy. However, overcoming data, regulatory, and ethical challenges is essential for its widespread adoption.
... Some of them are based on similarity measurements, which are grounded on the assumption that similar drugs may possess similar biological activity. Various similarity matrices -targeting molecule structure, side effect, protein targets, etc.can be used for direct matching (Vilar et al. 2012;Ferdousi, Safdari, and Omidi 2017) or as features to train machine learning classifiers (Gottlieb et al. 2012;Cheng and Zhao 2014;Sridhar, Fakhraei, and Getoor 2016) and neural networks (Rohani and Eslahchi 2019;Lee, Park, and Ahn 2019;Zhang, Lu, and Zang 2022). Other approaches involve matrix decomposition of known DDI matrices combined with multiple relation matrices to predict unknown DDIs (Zhang et al. 2018;Rohani, Eslahchi, and Katanforoush 2020). ...
Predicting unknown drug-drug interactions (DDIs) is crucial for improving medication safety. Previous efforts in DDI prediction have typically focused on binary classification or predicting DDI categories, with the absence of explanatory insights that could enhance trust in these predictions. In this work, we propose to generate natural language explanations for DDI predictions, enabling the model to reveal the underlying pharmacodynamics and pharmacokinetics mechanisms simultaneously as making the prediction. To do this, we have collected DDI explanations from DDInter and DrugBank and developed various models for extensive experiments and analysis. Our models can provide accurate explanations for unknown DDIs between known drugs. This paper contributes new tools to the field of DDI prediction and lays a solid foundation for further research on generating explanations for DDI predictions.
... Traditional approaches are based on similarity measures, where the fundamental concept is that if an interaction exists between drug A and drug B, and drug C is similar to drug A, then an interaction between drug B and drug C may occur [39]. Early works [11,12,40,41] employed various similarity measures with classical algorithms such as logistic regression and SVM. ...
The increasing volume of drug combinations in modern therapeutic regimens needs reliable methods for predicting drug-drug interactions (DDIs). While Large Language Models (LLMs) have revolutionized various domains, their potential in pharmaceutical research, particularly in DDI prediction, remains largely unexplored. This study thoroughly investigates LLMs' capabilities in predicting DDIs by uniquely processing molecular structures (SMILES), target organisms, and gene interaction data as raw text input from the latest DrugBank dataset. We evaluated 18 different LLMs, including proprietary models (GPT-4, Claude, Gemini) and open-source variants (from 1.5B to 72B parameters), first assessing their zero-shot capabilities in DDI prediction. We then fine-tuned selected models (GPT-4, Phi-3.5 2.7B, Qwen-2.5 3B, Gemma-2 9B, and Deepseek R1 distilled Qwen 1.5B) to optimize their performance. Our comprehensive evaluation framework included validation across 13 external DDI datasets, comparing against traditional approaches such as l2-regularized logistic regression. Fine-tuned LLMs demonstrated superior performance, with Phi-3.5 2.7B achieving a sensitivity of 0.978 in DDI prediction, with an accuracy of 0.919 on balanced datasets (50% positive, 50% negative cases). This result represents an improvement over both zero-shot predictions and state-of-the-art machine-learning methods used for DDI prediction. Our analysis reveals that LLMs can effectively capture complex molecular interaction patterns and cases where drug pairs target common genes, making them valuable tools for practical applications in pharmaceutical research and clinical settings.
... Cleverly designed AI algorithm frameworks, based on various omics data, can efficiently identify drug combinations with optimal therapeutic effects. Compared to traditional optimization algorithms, these AI-based methods exhibit superior robustness and global optimization capabilities 6,9 . AI-assisted synergistic and antagonistic drug prediction algorithms have been successfully applied in various fields, including anti-tumor drug screening 10 and antimicrobial drug optimization 11 , significantly enhancing the efficiency of drug combination optimization. ...
While drug combinations are increasingly important in disease treatment, predicting their therapeutic interactions remains challenging. This review systematically analyzes computational methods for predicting drug combination effects through multi-omics data integration. We comprehensively assess key algorithms including DrugComboRanker and AuDNNsynergy, and evaluate integration approaches encompassing kernel regression and graph networks. The review elucidates artificial intelligence applications in predicting drug synergistic and antagonistic effects.
... Drug-drug interaction prediction approaches can be categorized into classification-based and similaritybased methods. Classification-based methods consider drug-drug interaction prediction as a binary classification problem (Cheng and Zhao, 2014;Huang et al., 2014a;Zitnik and Zupan, 2016;Chen et al., 2016b;Shi et al., 2017). These methods use known interacting drug pairs as positive examples and other drug pairs as negative examples, and train classification models, such as naive Bayes, logistic regression, and support vector machine. ...
The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases and co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change if taken with another drug. The knowledge of drug interactions is limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality. Here, we present Decagon, an approach for modeling polypharmacy side effects. The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Decagon predicts the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well side effects with a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon creates opportunities to use large pharmacogenomic and patient data to flag and prioritize side effects for follow-up analysis.
... Therapeutic strategies targeting these receptors may enhance periodontal regeneration. Drug-gene interactions (8,9) involve the interplay between drugs and specific genes in the biological pathways targeted by the drug. For the RTK-VEGF4 receptor family, drugs can modulate the activity or expression of these receptors, influencing angiogenesis and periodontal regeneration. ...
Background: The RTK-VEGF4 receptor family, which includes VEGFR-1, VEGFR-2, and VEGFR-3, plays a cru- cial role in tissue regeneration by promoting angiogenesis, the formation of new blood vessels, and recruiting stem cells and immune cells. Machine learning, particularly graph neural networks (GNNs), has shown high accuracy in predicting these interactions. This study aims to predict drug-gene interactions of the RTK-VEGF4 receptor family in periodontal regeneration using graph neural networks.
Material and Methods: The study utilized a dataset comprising 19,154 drug-gene interactions to analyze the rela- tionships between drugs and protein-coding genes. The dataset was split into training and testing sets, with 80% of the data used for training and 20% for testing. Cytoscape, an open-source software platform, was employed to visualize and analyze the drug-gene interaction network, and CytoHubba, a plugin, was used to identify highly con- nected nodes. Topological measures were applied to determine the influence and importance of each node. GNNs were used to manage the complex relationships and dependencies within the graphs.
Results: The drug-gene interaction network, comprising 815 nodes and 13,436 edges, was found to be complex and highly interconnected. It was divided into 11 components, displaying low density and heterogeneity, indicative of a sparse structure. The GNN model achieved 97% accuracy in predicting interaction types, including single protein interactions and protein complex groups.
Conclusions: The study demonstrates that graph neural networks outperform traditional machine learning methods in predicting drug-gene interactions within the RTK-VEGF protein family in periodontal regeneration, highlighting their potential in advancing therapeutic strategies and drug discovery.
... In recent years, with the rapid development of computer technology, numerous machine learning- [6][7][8] and deep learning-based methods [9][10][11] have been proposed for DDI prediction. These methods are not only faster and more efficient but also help reduce unexpected drug interactions, lower drug development costs, and optimize the drug design process. ...
This study introduces a deep learning framework based on SMILES representations of chemical structures to predict drug–drug interactions (DDIs). The model extracts Morgan fingerprints and key molecular descriptors, transforming them into raw graphical features for input into a modified ResNet18 architecture. The deep residual network, enhanced with regularization techniques, efficiently addresses training issues such as gradient vanishing and exploding, resulting in superior predictive performance. Experimental results show that StructNet-DDI achieved an AUC of 99.7%, an accuracy of 94.4%, and an AUPR of 99.9%, demonstrating the model’s effectiveness and reliability. These findings highlight that StructNet-DDI can effectively extract crucial features from molecular structures, offering a simple yet robust tool for DDI prediction.
... For DDI prediction, Li et al. [7] employed a Bayesian network, combined with molecular and pharmacological phenotypes, to predict drug-drug combinations. Chen et al. [8] proposed the HNAI framework to assist in DDI prediction by constructing a DDI network, calculating the drug-drug pair similarity using four features, and finally applying five prediction models within the HNAI framework: plain Bayesian, decision tree, k-nearest neighbor, logistic regression, and support vector machine. Sridhar et al. [9] proposed a scalable probabilistic framework for inferring DDIs from a network constructed based on similarities and known interactions between multiple drugs. ...
Multi-drug combinations are an effective strategy for the teatment of complex diseases. Due to the numerous unknown interactions between drugs, accurate prediction of drug-drug interactions (DDIs) is essential to avoid adverse drug reactions that can cause significant harm to patients. Therefore, DDI prediction is crucial in pharmacology.Methods: In this paper, we propose a multi-source feature fusion DDI prediction method based on the self-attention mechanism of a capsule neural network (ACaps-DDI). This method effectively integrates the chemical information of a drug's internal substructure, as well as the bioinformation of the drug's external targets and enzymes, to predict drug-drug interactions.Results: Comparison experiments on two benchmark datasets show that the six classification metrics of the ACaps-DDI model outperform those of the other seven comparison models, demonstrating the superior performance and generalization ability of the ACaps-DDI model. Ablation studies further validate the effectiveness of certain ACaps-DDI modules. Finally, case validation with three drugs—cannabidiol, torasemide, and dexamethasone—demonstrates the model's effectiveness in predicting unknown drug interactions.
Conclusion: The ACaps-DDI model has demonstrated a good predictive effect on known drugs and some predictive ability on unseen drugs, which is of great practical significance for clinical drug interaction studies.
... Recognizing the importance of predictive DDI models in the drug development process, the US Food and Drug Administration (FDA) has recently issued guidelines advocating for their consideration in regulatory pathways for new drugs (4,5). While such models have been well-established for metabolic DDIs involving cytochrome P450s (6), there is a notable lack of predictive models for transporter-mediated DDIs (tDDIs). This deficiency is particularly concerning in the context of organic anion transporting polypeptides (OATPs), a family of proteins responsible for transporting a wide range of drugs into the liver for bile-mediated elimination. ...
Organic anion transporting polypeptides (OATPs) are crucial for hepatic drug uptake, influencing drug efficacy and toxicity. Predicting OATP-mediated drug-drug interactions (DDIs) is challenging due to limited structural data and inconsistent experimental OATP inhibition data across studies. This study introduces Heterogeneous OATP-Ligand Interaction Graph Neural Network (HOLI-GNN), a novel computational approach that integrates molecular modeling with graph neural networks to enhance the prediction of OATP-mediated drug inhibition. By combining ligand molecular features with protein-ligand interaction data, HOLI-GNN outperforms traditional ligand-based methods. HOLI-GNN achieved median F1 and AUC scores of 0.78 and 0.90, respectively, compared to ECFP- and RDKit-based models built upon XGBoost (F1: 0.68 and 0.78, respectively; AUC: 0.70 and 0.75, respectively). Beyond improving inhibition prediction, we characterize protein residues involved in inhibitory versus non-inhibitory drug interactions, specifically highlighting residues T42, F224, I353, F356, and F386. We speculate that local position shifts in these hydrophobic packing residues, or the inhibition thereof, may be an important aspect of competitive inhibition mechanisms. Our model enhances the performance of OATP inhibitor prediction and, critically, offers interpretable interaction information to inform future mechanistic investigations.
Significance Statement
Concurrent administration of different drugs can cause potentially lethal drug-drug interactions (DDIs), and membrane protein transporters like OATPs can mediate such DDIs. While many current models predict OATP-mediated DDIs, all thus far rely solely on drug features without considering intricate drug-OATP interactions. In this work, we present HOLI-GNN, a graph neural network that leverages both drug and OATP-drug interaction features to predict OATP inhibition. The use of OATP-drug interaction features in the prediction was made possible by the recent publication of cryo-EM structures for OATP1B1 and high-throughput protein-ligand docking. We demonstrate that HOLI-GNN outperforms conventional OATP-mediated DDI predictors which rely solely on drug features, while enabling important mechanistic insights into OATP transport.
... The similarity-based method assumes that medications with similar properties may interact [15,24]. The literature extraction-based method treats the extraction of DDIs as a multiclass classification job, often extracting data from the literature's instructive phrases before detecting and classifying possible DDIs [25][26][27][28][29]. The deep learning approaches extract highquality pharmacological characteristics, which have seen extensive use in biology with encouraging outcomes [30][31][32][33][34][35]. ...
Finding drug-drug interaction is crucial for patient safety and treatment efficacy. Two drugs may show a synergistic effect but may sometimes cause a severe health issue, including lethality. Wet lab studies are often performed to understand such interactions but are limited by cost and time. However, the biochemical data generated can be explored to compute unknown interactions. Here, we developed a computational model named UniGEN-DDI ( Uni fied G raph E mbedding N etwork for D rug- D rug Interaction) for the estimation of interactions between drugs. It is a simple unified network model containing the biochemical information of drug association developed using the compiled data from DrugBank 5.1.0. The feature learning of the drugs was carried out using a combination of GraphSAGE and Node2Vec algorithms, which were found efficient in extracting diverse features. The simple architecture of our model led to a significant reduction in computational time compared to the baselines, while maintaining a high prediction accuracy. The model performed well on the data, which was equally distributed between interacting and non-interacting drugs. As a more challenging evaluation, we performed non-overlapping splitting of the data based on the drug action on different parts of the body, and our model performed well in both interaction estimation and time efficiency. Our model successfully identified the 12 unknown drug interactions in DrugBank 5.1.0, which were updated in DrugBank 6.0.
Highlights
UniGEN-DDI: A simple unified network model was developed for drug-drug interactions.
Node embeddings were generated using GraphSAGE and Node2Vec algorithms.
A significantly higher computational efficiency was achieved compared to baselines.
Model validated in non-overlapping splitting of data targetting multiple body parts.
UniGEN-DDI estimated unknown interactions verified in the updated DrugBank 6.0.
Graphical abstract
... -can be used for direct matching (Vilar et al. 2012;Ferdousi, Safdari, and Omidi 2017) or as features to train ma-chine learning classifiers (Gottlieb et al. 2012;Cheng and Zhao 2014;Sridhar, Fakhraei, and Getoor 2016) and neural networks (Rohani and Eslahchi 2019;Lee, Park, and Ahn 2019;Zhang, Lu, and Zang 2022). Other approaches involve matrix decomposition of known DDI matrices combined with multiple relation matrices to predict unknown DDIs (Zhang et al. 2018;Rohani, Eslahchi, and Katanforoush 2020). ...
Predicting unknown drug-drug interactions (DDIs) is crucial for improving medication safety. Previous efforts in DDI prediction have typically focused on binary classification or predicting DDI categories, with the absence of explanatory insights that could enhance trust in these predictions. In this work, we propose to generate natural language explanations for DDI predictions, enabling the model to reveal the underlying pharmacodynamics and pharmacokinetics mechanisms simultaneously as making the prediction. To do this, we have collected DDI explanations from DDInter and DrugBank and developed various models for extensive experiments and analysis. Our models can provide accurate explanations for unknown DDIs between known drugs. This paper contributes new tools to the field of DDI prediction and lays a solid foundation for further research on generating explanations for DDI predictions.
... The vector mapping technique is applied to autonomously single out the most informative features for prediction tasks in these methods. In practice, the characteristics of small molecule compounds are used as input data of ML methods for the prediction of drug-target interaction, drug clinical efficacy, compound chemicophysical property as well as bio-molecular activity [83][84][85][86]. Specially, Artificial Neural Network (ANN) becomes a popular framework of machine learning, which mimics the working means of human neural cells. ...
Purpose
Target-based strategy is a prevalent means of drug research and development (R&D), since targets provide effector molecules of drug action and offer the foundation of pharmacological investigation. Recently, the artificial intelligence (AI) technology has been utilized in various stages of drug R&D, where AI-assisted experimental methods show higher efficiency than sole experimental ones. It is a critical need to give a comprehensive review of AI applications in drug R &D for biopharmaceutical field.
Methods
Relevant literatures about AI-assisted drug R&D were collected from the public databases (Including Google Scholar, Web of Science, PubMed, IEEE Xplore Digital Library, Springer, and ScienceDirect) through a keyword searching strategy with the following terms [(“Artificial Intelligence” OR “Knowledge Graph” OR “Machine Learning”) AND (“Drug Target Identification” OR “New Drug Development”)].
Results
In this review, we first introduced common strategies and novel trends of drug R&D, followed by characteristic description of AI algorithms widely used in drug R&D. Subsequently, we depicted detailed applications of AI algorithms in target identification, lead compound identification and optimization, drug repurposing, and drug analytical platform construction. Finally, we discussed the challenges and prospects of AI-assisted methods for drug discovery.
Conclusion
Collectively, this review provides comprehensive overview of AI applications in drug R&D and presents future perspectives for biopharmaceutical field, which may promote the development of drug industry.
... Healthcare settings are investigating machine learning (ML) methods for various purposes [9,10,30]. ML systems can precisely diagnose sepsis using accumulated data from intensive care units (ICUs) and emergency rooms [11,12]. Many researchers have concentrated on ML techniques to outperform severity scoring systems and attain high accuracy. ...
Sepsis, a critical condition from the body's response to infection, poses a major global health crisis affecting all age groups. Timely detection and intervention are crucial for reducing healthcare expenses and improving patient outcomes. This paper examines the limitations of traditional sepsis screening tools like Systemic Inflammatory Response Syndrome, Modified Early Warning Score, and Quick Sequential Organ Failure Assessment, highlighting the need for advanced approaches. We propose using machine learning techniques - Random Forest, Extreme Gradient Boosting, and Decision Tree models - to predict sepsis onset. Our study evaluates these models individually and in a combined meta-ensemble approach using key metrics such as Accuracy, Precision, Recall, F1 score, and Area Under the Receiver Operating Characteristic Curve. Results show that the meta-ensemble model outperforms individual models, achieving an AUC-ROC score of 0.96, indicating superior predictive accuracy for early sepsis detection. The Random Forest model also performs well with an AUC-ROC score of 0.95, while Extreme Gradient Boosting and Decision Tree models score 0.94 and 0.90, respectively.
... D RUG-DRUG interaction (DDI) prediction is critical for drug repositioning, drug recommendation, and drug discovery, and unknown changes in drug function can result in adverse drug reactions [1], [2]. Predicting potential interactions between factors such as drugs, diseases, and proteins is essential for avoiding severe side effects. ...
Predicting drug-drug interaction (DDI) plays a crucial role in drug recommendation and discovery. However, wet lab methods are prohibitively expensive and time-consuming due to drug interactions. In recent years, deep learning methods have gained widespread use in drug reasoning. Although these methods have demonstrated effectiveness, they can only predict the interaction between a drug pair and do not contain any other information. However, DDI is greatly affected by various other biomedical factors (such as the dose of the drug). As a result, it is challenging to apply them to more complex and meaningful reasoning tasks. Therefore, this study regards DDI as a link prediction problem on knowledge graphs and proposes a DDI prediction model based on Cross-Transformer and Graph Convolutional Networks (GCN) in first-order logical query form, TransFOL. In the model, a biomedical query graph is first built to learn the embedding representation. Subsequently, an enhancement module is designed to aggregate the semantics of entities and relations. Cross-Transformer is used for encoding to obtain semantic information between nodes, and GCN is used to gather neighbour information further and predict inference results. To evaluate the performance of TransFOL on common DDI tasks, we conduct experiments on two benchmark datasets. The experimental results indicate that our model outperforms state-of-the-art methods on traditional DDI tasks. Additionally, we introduce different biomedical information in the other two experiments to make the settings more realistic. Experimental results verify the strong drug reasoning ability and generalization of TransFOL in complex settings. Data and code are available at
https://github.com/Cheng0829/TransFOL
.
... Previous methods were primarily based on drug molecular structural features, 27 utilizing structural similarity, and interaction spectral fingerprint similarity to predict potential DDIs. For instance, the HNAI framework 28 incorporated four similarity features to compute drugdrug pair similarity, while the INDI (inferring drug interactions) approach 29 utilized seven distinct drug-drug similarity measures for this purpose. Zhang et al. 30 creatively integrated multi-source data and drug pair similarities to predict potential DDIs. ...
... Due to the importance of DDIs throughout drug development and for the clinical management of PLWH, efficient computational methods for predicting DDI risks are in need. Currently, the cutting-edge approach to this problem is via machine learning [6][7][8][9] , which is a branch of artificial intelligence that uses algorithms to extract patterns from given data to make predictions. Deep learning, a sub-field of machine learning, is inspired by the human neural network that offers powerful tools to generalise learning by mapping the artificial neurons between the given input and output data 10 . ...
Drug-drug interaction (DDI) may result in clinical toxicity or treatment failure of antiretroviral therapy (ARV) or comedications. Despite the high number of possible drug combinations, only a limited number of clinical DDI studies are conducted. Computational prediction of DDIs could provide key evidence for the rational management of complex therapies. Our study aimed to assess the potential of deep learning approaches to predict DDIs of clinical relevance between ARVs and comedications. DDI severity grading between 30,142 drug pairs was extracted from the Liverpool HIV Drug Interaction database. Two feature construction techniques were employed: 1) drug similarity profiles by comparing Morgan fingerprints, and 2) embeddings from SMILES of each drug via ChemBERTa, a transformer-based model. We developed DeepARV-Sim and DeepARV-ChemBERTa to predict four categories of DDI: i) Red: drugs should not be co-administered, ii) Amber: interaction of potential clinical relevance manageable by monitoring/dose adjustment, iii) Yellow: interaction of weak relevance and iv) Green: no expected interaction. The imbalance in the distribution of DDI severity grades was addressed by undersampling and applying ensemble learning. DeepARV-Sim and DeepARV-ChemBERTa predicted clinically relevant DDI between ARVs and comedications with a weighted mean balanced accuracy of 0.729 ± 0.012 and 0.776 ± 0.011, respectively. DeepARV-Sim and DeepARV-ChemBERTa have the potential to leverage molecular structures associated with DDI risks and reduce DDI class imbalance, effectively increasing the predictive ability on clinically relevant DDIs. This approach could be developed for identifying high-risk pairing of drugs, enhancing the screening process, and targeting DDIs to study in clinical drug development.
... With the rapid development of machine learning, data-driven sensing applications have been widely used. For example, machine learning can explore the causal relationship between drugs, biomarkers and diseases [17], [18], which promotes datadriven decision-making, and may accelerate drug development and reduce the failure rate. Machine learning can also used to predict drug-drug interactions, which reduces adverse drug reactions and medical care costs. ...
... These flexible frameworks integrate diverse models through various ensemble techniques. To aid in DDI categorization, [99] designed a heterogeneous network assisted inference (HNAI) system. The initial stage is to build a comprehensive DDI network using DrugBank data, which includes 6946 distinct DDI pairs that connect 721 authorized drugs. ...
The interactions between therapeutics and their targets are an important part of the drug development process. To counter the cost, time and accuracy related issues, novel and efficient DL algorithms are required. These approaches have proven successful in quickly identifying and predicting possible drug interactions. Here, we examine computational strategies for predicting drug interactions in the context of drug development, focusing on artificial intelligence-based approaches. We start by providing a succinct overview of deep learning in drug development and drug interactions. Next, we review and evaluate AI-based methods used to forecast Drug–Target Interactions, drug–drug interactions, drug–disease interactions, and ploy-pharmacy side effects, including both sequential and graph-based modern DL algorithms. Lastly, we examine databases with their brief description and sources that are frequently utilized to research drug interactions.
... The HNAI models achieved an area under curve (AUC) of 0.67, as evaluated through fivefold cross-validation. The study focused on antipsychotic drugs and demonstrated that HNAI showed promise in uncovering DDIs during drug development and post-marketing surveillance [38]. ...
Prescribing medications is a fundamental practice in the management of illnesses that necessitates in-depth knowledge of clinical pharmacology. Polypharmacy, or the concurrent use of multiple medications by individuals with complex health conditions, poses significant challenges, including an increased risk of drug interactions and adverse reactions. The Saudi Vision 2030 prioritises enhancing healthcare quality and safety, including addressing polypharmacy. Artificial intelligence (AI) offers promising tools to optimise medication plans, predict adverse drug reactions and ensure drug safety. This review explores AI's potential to revolutionise polypharmacy management in Saudi Arabia, highlighting practical applications, challenges and the path forward for the integration of AI solutions into healthcare practices.
... For example, Chen et al. proposed a scheme to assess the similarity of two drugs and used the nearest neighbor algorithm to identify DDIs based on this scheme [3]. Cheng et al. employed support vector machines to identify DDIs, where each drug pair was represented by features derived from simplified molecular input line entry system (SMILES) formats of two drugs in the pair and their side effects [4]. Ran et al. adopted drug fingerprints and random forest to build a model for identifying DDIs [5]. ...
Drugs are an effective way to treat various diseases. Some diseases are so complicated that the effect of a single drug for such diseases is limited, which has led to the emergence of combination drug therapy. The use multiple drugs to treat these diseases can improve the drug efficacy, but it can also bring adverse effects. Thus, it is essential to determine drug-drug interactions (DDIs). Recently, deep learning algorithms have become popular to design DDI prediction models. However, most deep learning-based models need several types of drug properties, inducing the application problems for drugs without these properties. In this study, a new deep learning-based model was designed to predict DDIs. For wide applications, drugs were first represented by commonly used properties, referred to as fingerprint features. Then, these features were perfectly fused with the drug interaction network by a type of graph convolutional network method, GraphSAGE, yielding high-level drug features. The inner product was adopted to score the strength of drug pairs. The model was evaluated by 10-fold cross-validation, resulting in an AUROC of 0.9704 and AUPR of 0.9727. Such performance was better than the previous model which directly used drug fingerprint features and was competitive compared with some other previous models that used more drug properties. Furthermore, the ablation tests indicated the importance of the main parts of the model, and we analyzed the strengths and limitations of a model for drugs with different degrees in the network. This model identified some novel DDIs that may bring expected benefits, such as the combination of PEA and cannabinol that may produce better effects. DDIs that may cause unexpected side effects have also been discovered, such as the combined use of WIN 55,212-2 and cannabinol. These DDIs can provide novel insights for treating complex diseases or avoiding adverse drug events.
... These SSPs are then fed into a Deep Neural Network (DNN) for predicting interactions. More recent research has highlighted the benefits of integrating multiple feature sources for improved prediction accuracy (Gottlieb et al., 2012;Cheng and Zhao, 2014;Yan et al., 2020). For instance, Lee et al. (Lee et al., 2019) combined SSPs, target genes, and gene ontology, encoding each feature separately using an AutoEncoder (AE) for classification. ...
Potential drug-drug interactions (DDI) can lead to adverse drug reactions (ADR), and DDI prediction can help pharmacy researchers detect harmful DDI early. However, existing DDI prediction methods fall short in fully capturing drug information. They typically employ a single-view input, focusing solely on drug features or drug networks. Moreover, they rely exclusively on the final model layer for predictions, overlooking the nuanced information present across various network layers. To address these limitations, we propose a multi-scale dual-view fusion (MSDF) method for DDI prediction. More specifically, MSDF first constructs two views, topological and feature views of drugs, as model inputs. Then a graph convolutional neural network is used to extract the feature representations from each view. On top of that, a multi-scale fusion module integrates information across different graph convolutional layers to create comprehensive drug embeddings. The embeddings from the two views are summed as the final representation for classification. Experiments on two real-world datasets demonstrate that MSDF achieves higher accuracy than state-of-the-art methods, as the dual-view, multi-scale approach better captures drug characteristics.
... Recently, numerous works have emerged to address the problem of predicting DDIs. Based on the hypothesis that similar drugs exhibit a higher propensity for interacting, some previous studies have attempted to predict drug interactions using analogous feature derived from molecular structure [28] and various properties (e.g., phenotypic [29], functionality [30], and side efects [31]). In the study by Ruy et al, DDI types were estimated by using a deep neural network (DNN) model trained on chemical structure similarity [32]. ...
Drug combinations can reduce drug resistance and side effects and enable the improvement of disease treatment efficacy. Therefore, how to effectively identify drug-drug interactions (DDIs) is a challenging problem. Currently, there exist several approaches that leverage advanced representation learning and graph-based techniques for DDIs prediction. While these methods have demonstrated promising results, a limited number of approaches effectively utilize the potential of knowledge graphs (KGs), which provide information on drug attributes and multirelation among entities. In this work, we introduce a novel attention-based KGs representation learning framework. To encode drug SMILES sequence, a pretrained model is used, while molecular structure information is mapped as the initialization of nodes within the KG using a message-passing neural network. Additionally, the knowledge-aware graph attention network is employed to capture the drug and its topological neighbor representation in the KG representation module. To prevent the oversmoothing problem, the residual layer is used in the DDI prediction module. Comprehensive experiments on several datasets have demonstrated that the proposed method outperforms the state-of-the-art algorithms on the DDI prediction task across a range of evaluation metrics. It achieves an accuracy of 0.924 and an AUC of 0.9705 on the KEGG dataset and attains an ACC of 0.9777 and an AUC of 0.9959 on the OGB-biokg dataset. These experimental findings affirm that our approach is a dependable model for predicting the association of drugs.
... D RUG-DRUG interactions (DDIs) frequently arise when one drug induces a pharmacokinetic (PK) or pharmacodynamic (PD) effect in the presence of another, and they are primary factors leading to medical injuries [1,2]. DDIs commonly contribute to adverse drug reactions (ADRs) and elevated healthcare expenditures, which pose substantial threats to patients and public health [3]. For instance, acetylsalicylic acid, more commonly known as aspirin, is a medication employed to alleviate pain and fever stemming from diverse etiologies. ...
Predicting potential drug-drug interactions (DDIs) can effectively mitigate unforeseen interactions throughout the entire drug development process, playing a pivotal role in ensuring drug safety. However, traditional methods are laborious and require specific expert knowledge. This paper proposes RPDAnet, a novel molecular substructure-aware network based on Reinforced Pooling and Deep Attention mechanism, to investigate the interactive relationships between drugs and predict the potential DDIs. Particularly, RPDAnet leverages reinforcement learning to dynamically select informative molecular fragments, thus enhancing its generalization capacity without relying on prior knowledge. Subsequently, RPDAnet develops Communicative Message Massing Neural Network (CMPNN) to enhance the representation of molecular structures by reinforcing message interactions between nodes and edges through a communicative kernel. Finally, RPDAnet aggregates the interactions between substructures of drugs to predict the DDI between a pair of drugs. The experimental results on two real-world datasets demonstrate that our proposed RPDAnet outperforms the state-of-the-art methods with more than 5% performance gains in DDI prediction.
The life sciences have experienced a significant increase in the utilization of artificial intelligence (AI) in pharmaceutical research and drug delivery. The amalgamation of AI technology with human expertise has resulted in the rapid analysis and interpretation of genetic and biological data, leading to the acceleration of drug discovery processes and the identification of novel molecules. AI algorithms have also been employed to optimize drug development and delivery systems, predict disease progression, and evaluate drug candidates' pharmacological profiles. Additionally, AI has played a critical role in personalized medicine, scrutinizing patient data to customize treatments and improve patient outcomes. Although challenges still persist, sustained investments and exploration hold the promise of a fascinating future for healthcare and pharmaceuticals, with AI potentially revolutionizing pharmaceutical processes, reducing expenses, and enhancing patient care.
Accurate prediction of drug-drug interaction (DDI) is essential to improve clinical efficacy, avoid adverse effects of drug combination therapy, and enhance drug safety. Recently researchers have developed several computer-aided methods for DDI prediction. However, these methods lack the substructural features that are critical to drug interactions and are not effective in generalizing across domains and different distribution data. In this work, we present SAGAN, a domain adaptive interpretable substructure-aware graph attention network for DDI prediction. Based on attention mechanism and unsupervised clustering algorithm, we propose a new substructure segmentation method, which segments the drug molecule into multiple substructures, learns the mechanism of drug interaction from the perspective of interaction, and identifies important interaction regions between drugs. To enhance the generalization ability of the model, we improve and apply a conditional domain adversarial network to achieve cross-domain generalization by alternately optimizing the cross-entropy loss on the source domain and the adversarial loss of the domain discriminator. We evaluate and compare SAGAN with the state-of-the-art DDI prediction model on four real-world datasets for both in-domain and cross-domain scenarios, and show that SAGAN achieves the best overall performance. Moreover, the visualization results of the model show that SAGAN has achieved pharmacologically significant substructure extraction, which can help drug developers screen for some undiscovered local interaction sites, and provide important information for further drug structure optimization. The codes and datasets are available online at https://github.com/wyx2012/SAGAN.
Vetinformatics is an emerging field with the potential to revolutionize veterinary
science and improve animal health and welfare. It has various applications
in various fields, including animal genetics and medicine. Integrating and
analyzing these data for effective disease diagnosis and treatment is a significant
challenge for veterinary professionals. Integrating multi-omics data can aid in
identifying drug targets for our desired therapeutic target. This approach can
contribute to disease prevention and management and enhance productivity
and sustainability in veterinary research. This chapter explored the use of
multi-omics data in disease diagnostics, therapeutic target identification,
and biomarker development for animal diseases. It aims to aid researchers in
exploring novel drug targets and understanding the intricate interrelationships
among biological systems for drug identification and advancement. This chapter
also discusses the connection between data from different branches of omics
science. It examines them in a multi-omics field to facilitate the discovery
of novel prognostic, diagnostic, and therapeutic approaches. It also discusses
the potential implications of this technology in veterinary care, highlighting
the potential of researchers to gain insights into complex biological processes
and systems in animals using informatics databases. This knowledge can help
veterinarians and healthcare professionals develop more effective treatments
and interventions for animals in need and improve farmed animals’ well-being
and overall health. This chapter discusses future directions for multi-omics data
analysis in veterinary science. It explores the potential of new technologies and
techniques and their impact on veterinary research using machine learning and
network biology.
In brief
Clinical drug trials often do not include pregnant people due to health risks; therefore, many medications have an unknown effect on the developing fetus. Machine learning QSAR models have been used successfully to predict the fetal risk of pharmaceutical use during pregnancy.
Abstract
Those undergoing pregnancy are often excluded from clinical drug trials due to the risk that participation would pose to their health and the health of the developing fetus. However, they often require pharmaceuticals to manage health conditions that, if left untreated, could harm themselves or the fetus. This can mean that such individuals take one or more pharmaceuticals during pregnancy, many of which have unknown reproductive effects. Machine learning models have been used to successfully predict a number of reproductive toxicological outcomes for pharmaceuticals, including transplacental transfer, US Food and Drug Administration safety rating, and drug interactions. Models use quantitative chemical and structural features of active compounds as inputs to make predictions concerning the outcome of interest using computational algorithms. Models are validated and evaluated rigorously with metrics such as accuracy, area under the receiver operator curve, sensitivity, and precision. Results from these models can be a potential source of valuable information for pregnant people and their medical providers when making decisions regarding therapeutic drug use. This review summarizes current machine learning applications to make predictions about the risk and toxicity of medication use during pregnancy. Our review of the recent literature revealed that machine learning quantitative structure-activity relationship models can be used successfully to predict the transplacental transfer and the US Food and Drug Administration pregnancy safety category of pharmaceuticals; such models have also been employed to predict drug interactions, though not specifically during pregnancy. This latter topic is a potential area for future research. In this review, no single algorithm or descriptor-calculation software emerged as the most widely used, and their performances depend on a variety of factors, including the outcome of interest and combination of such algorithms and software.
Integrating machine learning (ML) into drug discovery has ushered in a new era of innovation, dramatically enhancing the efficiency and precision of identifying and developing new therapeutics. This review provides a comprehensive analysis of the current applications of machine learning in drug discovery, focusing on its transformative impact across various stages of the drug development pipeline. We delve into key ML methodologies, including supervised and unsupervised learning, neural networks, and reinforcement learning, examining their underlying principles and specific contributions to drug discovery processes. By exploring case studies and recent advancements, this review illustrates how ML algorithms have been utilized to predict drug-target interactions, optimize drug design, and streamline clinical trial processes. Furthermore, we discuss the challenges and limitations of implementing ML techniques in this field and highlight emerging trends and future directions. This review aims to offer researchers a thorough understanding of ML's potential to revolutionize drug discovery and equip them with the insights needed to leverage these technologies effectively.
Appropriate studies on drug–drug interactions (DDIs) can evade possible adverse side effects due to the ingestion of multiple drugs. This paper proposes a novel framework called Similarity Network Fusion and Hybrid Convolutional Neural Network (SNF–HCNN) to predict the DDIs better. The proposed framework leverages data from DrugBank, PubChem, and SIDER. Seven critical drug features are extracted: Target, Transporter, Enzymes, Chemical substructure, Carrier, Offside, and Side effects. The Jaccard Similarity measure evaluates the similarity of drug features to construct a comprehensive similarity matrix that effectively captures potential drug relationships and patterns. The similarity selection process identifies the most relevant features, reduces redundancy, and enhances identifying potential drug interactions. Integrating Similarity Network Fusion (SNF) with the selected similarity matrix ensures a comprehensive representation of drug features
and leads to superior accuracy compared to conventional methods. Our experimental results demonstrate the effectiveness of the proposed hybrid convolutional neural network (HCNN) architectures, such as CNN+LR
(CNN+Logistic Regression), CNN+RF (CNN+Random Forest), and CNN+SVM (CNN+Support Vector Machine), showing impressive accuracies of 95.19%, 94.45%, and 93.65%, respectively. Moreover, CNN+LR outperforms other approaches regarding precision, sensitivity, F1-score, and AUC score, which implicate better outcomes for ensuring medication safety aspects in clinical settings in the future.
These days, combining many medications is the best course of treatment to slow the pathologic process, which includes a number of underlying negative effects brought on by drug-drug interactions (DDIs). The evaluation of pharmacological interactions, pharmacodynamics, and probable adverse effects using artificial intelligence (AI) is a possibility. Many AI-based DDI prediction methods, including both machine learning and deep learning, that make use of the available huge data have been described in recent years. Even if past techniques yielded notable advancements, changes are still essential. In this study, we present the results of three distinct single models: Random Forest (RF), Recurrent Neural Networks (RNNs), and Deep Neural Network (DNN) in our initial filtration round to find a suitable candidate model to predict the risk or severity of negative consequences can be elevated when drug A is combined with drug B. After evaluating the models' performance. This paper suggested DNN as a way to enhance DDIs' predictive capabilities. The prediction algorithm was 96.2% accurate in predicting 86 different kinds of DDIs using a benchmark dataset. The proposed model applies pre-processing techniques on data because these techniques align with our proposed model goals of data-driven decision-making and actionable insights in prediction of DDI. After applying the processing to the dataset, the suggested model DNN classifier outperforms the already proposed approaches on the same dataset. Integrating sustainable principles into DDI prediction using DNNs entails creating models that not only achieve high accuracy but also operate efficiently, reducing the environmental impact of large-scale data processing. The great performance of our model positions it at the top of the list of those well-designed pharmacovigilance-assisted tools that make it easier to find DDIs to support clinical judgment and drug development.
Introduction:
The accelerated discovery and production of pharmaceutical products has resulted in many positive outcomes. However, this progress has also contributed to problematic polypharmacy, one of the rapidly growing threats to public health in this century. Problematic polypharmacy results in adverse patient outcomes and imposes increased strain and financial burden on healthcare systems.
Areas covered:
A review was conducted on the current body of evidence concerning factors contributing to and consequences of problematic polypharmacy. Recent trials investigating interventions that target polypharmacy and emerging solutions, including incorporation of artificial intelligence, are also examined in this article.
Expert opinion:
To shift away from problematic polypharmacy, a multifaceted interdisciplinary approach is necessary. Any potentially successful strategy must be adapted to suit various healthcare settings and must utilize all available resources, including artificial intelligence.
Drug-drug interactions (DDIs) pose a significant issue in modern healthcare, potentially compromising treatment efficacy and patient safety. DDIs arise when significant alterations occur in the pharmacological action of a drug due to its co-administration with another drug, leading to potential adverse drug reactions (ADRs), toxicity or diminished therapeutic efficacy. Apart from the obvious cases of drug combinations that should be avoided, there are instances where risk-benefit analysis may allow co-administration. Hence, DDIs may represent clinically significant cases depending on the clinical outcome, time point of administration, etc. The issue is especially critical in cases of patients with multimorbidity and
complex therapeutic regimens with different time points in drug administrations. This work employs a graph-based approach
aimed at optimizing therapeutic regiments while considering the minimization of DDIs potential. In this approach each drug is
represented as a node, and edges represent the clinical significance of DDIs. We aim to identify sets of drugs that either
have no DDIs or exhibit minor to moderate clinical significance (referred to as Maximal Independent Sets), indicating that they can be taken together. In practice, we solved the complementary problem, which is finding Maximal Cliques. Both problems are NP-hard, but for small graphs, they can be solved exactly. From all the cliques we identify, those selected to be a part of each proposed therapeutic regimen must consist of nodes that appear only once. This problem is once again reduced to clique finding. The above approach is demonstrated using two clinical scenarios involving two patients who are experiencing
polypharmacy and are at risk for ADRs due to potential DDIs of varying clinical significance. By applying our approach, the
therapeutic schemes are optimized towards minimizing the risk of ADRs.
ChEMBL is an open large-scale bioactivity database (https://www.ebi.ac.uk/chembl), previously described in the 2012 Nucleic Acids Research Database Issue. Since then, a variety of new data sources and improvements
in functionality have contributed to the growth and utility of the resource. In particular, more comprehensive tracking of
compounds from research stages through clinical development to market is provided through the inclusion of data from United
States Adopted Name applications; a new richer data model for representing drug targets has been developed; and a number of
methods have been put in place to allow users to more easily identify reliable data. Finally, access to ChEMBL is now available
via a new Resource Description Framework format, in addition to the web-based interface, data downloads and web services.
Sunitinib malate is a multitargeted receptor tyrosine kinase inhibitor used in the treatment of human malignancies. A substantial number of sunitinib-treated patients develop cardiac dysfunction, but the mechanism of sunitinib-induced cardiotoxicity is poorly understood. We show that mice treated with sunitinib develop cardiac and coronary microvascular dysfunction and exhibit an impaired cardiac response to stress. The physiological changes caused by treatment with sunitinib are accompanied by a substantial depletion of coronary microvascular pericytes. Pericytes are a cell type that is dependent on intact platelet-derived growth factor receptor (PDGFR) signaling but whose role in the heart is poorly defined. Sunitinib-induced pericyte depletion and coronary microvascular dysfunction are recapitulated by CP-673451, a structurally distinct PDGFR inhibitor, confirming the role of PDGFR in pericyte survival. Thalidomide, an anticancer agent that is known to exert beneficial effects on pericyte survival and function, prevents sunitinib-induced pericyte cell death in vitro and prevents sunitinib-induced cardiotoxicity in vivo in a mouse model. Our findings suggest that pericytes are the primary cellular target of sunitinib-induced cardiotoxicity and reveal the pericyte as a cell type of concern in the regulation of coronary microvascular function. Furthermore, our data provide preliminary evidence that thalidomide may prevent cardiotoxicity in sunitinib-treated cancer patients.
There are numerous small molecular compounds around us to affect our health, such as drugs, pesticides, food additives, industrial chemicals, and environmental pollutants. Over decades, properties related to absorption, distribution, metabolism, excretion, and toxicity (ADMET) have become one of the most important issues to assess the effects or risks of these compounds on human body. Recent high-rate drug withdrawals increase the pressure on regulators and pharmaceutical industry to improve preclinical safety testing. Since in vivo and in vitro evaluations are costly and laborious, in silico techniques have been widely used to estimate these properties. In this review, we would briefly describe the recent advances of in silico ADMET prediction, with emphasis on substructure pattern recognition method that we developed recently. Challenges and limitions in the area of in silico ADMET prediction were further discussed, such as application domain of model, model validation techniques, global versus local models. At last, several new promising research directions were provided, such as computational systems toxicology (toxicogenomics), data-integration and meta-decision making systems, which could be used for systemic in silico ADMET prediction in drug discovery and hazard risk assessment.
Drug-drug interactions (DDIs) can lead to serious and potentially lethal adverse events. In recent years, several drugs have been withdrawn from the market due to interaction-related adverse events (AEs). Current methods for detecting DDIs rely on the accumulation of sufficient clinical evidence in the post-market stage - a lengthy process that often takes years, during which time numerous patients may suffer from the adverse effects of the DDI. Detection methods are further hindered by the extremely large combinatoric space of possible drug-drug-AE combinations. There is therefore a practical need for predictive tools that can identify potential DDIs years in advance, enabling drug safety professionals to better prioritize their limited investigative resources and take appropriate regulatory action. To meet this need, we describe Predictive Pharmacointeraction Networks (PPINs) - a novel approach that predicts unknown DDIs by exploiting the network structure of all known DDIs, together with other intrinsic and taxonomic properties of drugs and AEs. We constructed an 856-drug DDI network from a 2009 snapshot of a widely-used drug safety database, and used it to develop PPIN models for predicting future DDIs. We compared the DDIs predicted based solely on these 2009 data, with newly reported DDIs that appeared in a 2012 snapshot of the same database. Using a standard multivariate approach to combine predictors, the PPIN model achieved an AUROC (area under the receiver operating characteristic curve) of 0.81 with a sensitivity of 48% given a specificity of 90%. An analysis of DDIs by severity level revealed that the model was most effective for predicting "contraindicated" DDIs (AUROC = 0.92) and less effective for "minor" DDIs (AUROC = 0.63). These results indicate that network based methods can be useful for predicting unknown drug-drug interactions.
Identifying drug-drug interactions (DDIs) is a major challenge in drug development. Previous attempts have established formal approaches for pharmacokinetic (PK) DDIs, but there is not a feasible solution for pharmacodynamic (PD) DDIs because the endpoint is often a serious adverse event rather than a measurable change in drug concentration. Here, we developed a metric "S-score" that measures the strength of network connection between drug targets to predict PD DDIs. Utilizing known PD DDIs as golden standard positives (GSPs), we observed a significant correlation between S-score and the likelihood a PD DDI occurs. Our prediction was robust and surpassed existing methods as validated by two independent GSPs. Analysis of clinical side effect data suggested that the drugs having predicted DDIs have similar side effects. We further incorporated this clinical side effects evidence with S-score to increase the prediction specificity and sensitivity through a Bayesian probabilistic model. We have predicted 9,626 potential PD DDIs at the accuracy of 82% and the recall of 62%. Importantly, our algorithm provided opportunities for better understanding the potential molecular mechanisms or physiological effects underlying DDIs, as illustrated by the case studies.
Despite considerable progress in genome- and proteome-based high-throughput screening methods and in rational drug design, the increase in approved drugs in the past decade did not match the increase of drug development costs. Network description and analysis not only gives a systems-level understanding of drug action and disease complexity, but can also help to improve the efficiency of drug design. We give a comprehensive assessment of the analytical tools of network topology and dynamics. The state-of-the-art use of chemical similarity, protein structure, protein-protein interaction, signaling, genetic interaction and metabolic networks in the discovery of drug targets is summarized. We propose that network targeting follows two basic strategies. The "central hit strategy" selectively targets central node/edges of the flexible networks of infectious agents or cancer cells to kill them. The "network influence strategy" works against other diseases, where an efficient reconfiguration of rigid networks needs to be achieved. It is shown how network techniques can help in the identification of single-target, edgetic, multi-target and allo-network drug target candidates. We review the recent boom in network methods helping hit identification, lead selection optimizing drug efficacy, as well as minimizing side-effects and drug toxicity. Successful network-based drug development strategies are shown through the examples of infections, cancer, metabolic diseases, neurodegenerative diseases and aging. Summarizing >1200 references we suggest an optimized protocol of network-aided drug development, and provide a list of systems-level hallmarks of drug quality. Finally, we highlight network-related drug development trends helping to achieve these hallmarks by a cohesive, global approach.
Unexpected drug activities derived from off-targets are usually undesired and harmful; however, they can occasionally be beneficial for different therapeutic indications. There are many uncharacterized drugs whose target proteins (including the primary target and off-targets) remain unknown. The identification of all potential drug targets has become an important issue in drug repositioning to reuse known drugs for new therapeutic indications.
We defined pharmacological similarity for all possible drugs using the US Food and Drug Administration's (FDA's) adverse event reporting system (AERS) and developed a new method to predict unknown drug-target interactions on a large scale from the integration of pharmacological similarity of drugs and genomic sequence similarity of target proteins in the framework of a pharmacogenomic approach. The proposed method was applicable to a large number of drugs and it was useful especially for predicting unknown drug-target interactions that could not be expected from drug chemical structures. We made a comprehensive prediction for potential off-targets of 1874 drugs with known targets and potential target profiles of 2519 drugs without known targets, which suggests many potential drug-target interactions that were not predicted by previous chemogenomic or pharmacogenomic approaches.
Softwares are available upon request.
yamanishi@bioreg.kyushu-u.ac.jp
Datasets and all results are available at http://cbio.ensmp.fr/~yyamanishi/aers/.
Drug-drug interactions (DDIs) are a common cause of adverse drug events. In this paper, we combined a literature discovery approach with analysis of a large electronic medical record database method to predict and evaluate novel DDIs. We predicted an initial set of 13197 potential DDIs based on substrates and inhibitors of cytochrome P450 (CYP) metabolism enzymes identified from published in vitro pharmacology experiments. Using a clinical repository of over 800,000 patients, we narrowed this theoretical set of DDIs to 3670 drug pairs actually taken by patients. Finally, we sought to identify novel combinations that synergistically increased the risk of myopathy. Five pairs were identified with their p-values less than 1E-06: loratadine and simvastatin (relative risk or RR = 1.69); loratadine and alprazolam (RR = 1.86); loratadine and duloxetine (RR = 1.94); loratadine and ropinirole (RR = 3.21); and promethazine and tegaserod (RR = 3.00). When taken together, each drug pair showed a significantly increased risk of myopathy when compared to the expected additive myopathy risk from taking either of the drugs alone. Based on additional literature data on in vitro drug metabolism and inhibition potency, loratadine and simvastatin and tegaserod and promethazine were predicted to have a strong DDI through the CYP3A4 and CYP2D6 enzymes, respectively. This new translational biomedical informatics approach supports not only detection of new clinically significant DDI signals, but also evaluation of their potential molecular mechanisms.
Understanding drug bioactivities is crucial for early-stage drug discovery, toxicology studies and clinical trials. Network pharmacology is a promising approach to better understand the molecular mechanisms of drug bioactivities. With a dramatic increase of rich data sources that document drugs' structural, chemical, and biological activities, it is necessary to develop an automated tool to construct a drug-target network for candidate drugs, thus facilitating the drug discovery process.
We designed a computational workflow to construct drug-target networks from different knowledge bases including DrugBank, PharmGKB, and the PINA database. To automatically implement the workflow, we created a web-based tool called DTome (Drug-Target interactome tool), which is comprised of a database schema and a user-friendly web interface. The DTome tool utilizes web-based queries to search candidate drugs and then construct a DTome network by extracting and integrating four types of interactions. The four types are adverse drug interactions, drug-target interactions, drug-gene associations, and target-/gene-protein interactions. Additionally, we provided a detailed network analysis and visualization process to illustrate how to analyze and interpret the DTome network. The DTome tool is publicly available at http://bioinfo.mc.vanderbilt.edu/DTome.
As demonstrated with the antipsychotic drug clozapine, the DTome tool was effective and promising for the investigation of relationships among drugs, adverse interaction drugs, drug primary targets, drug-associated genes, and proteins directly interacting with targets or genes. The resultant DTome network provides researchers with direct insights into their interest drug(s), such as the molecular mechanisms of drug actions. We believe such a tool can facilitate identification of drug targets and drug adverse interactions.
Chemical-protein interaction (CPI) is the central topic of target identification and drug discovery. However, large scale determination of CPI is a big challenge for in vitro or in vivo experiments, while in silico prediction shows great advantages due to low cost and high accuracy. On the basis of our previous drug-target interaction prediction via network-based inference (NBI) method, we further developed node- and edge-weighted NBI methods for CPI prediction here. Two comprehensive CPI bipartite networks extracted from ChEMBL database were used to evaluate the methods, one containing 17,111 CPI pairs between 4,741 compounds and 97 G protein-coupled receptors, the other including 13,648 CPI pairs between 2,827 compounds and 206 kinases. The range of the area under receiver operating characteristic curves was 0.73 to 0.83 for the external validation sets, which confirmed the reliability of the prediction. The weak-interaction hypothesis in CPI network was identified by the edge-weighted NBI method. Moreover, to validate the methods, several candidate targets were predicted for five approved drugs, namely imatinib, dasatinib, sertindole, olanzapine and ziprasidone. The molecular hypotheses and experimental evidence for these predictions were further provided. These results confirmed that our methods have potential values in understanding molecular basis of drug polypharmacology and would be helpful for drug repositioning.
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.
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.
Author Summary
Study of drug-target interaction is an important topic toward elucidation of protein functions and understanding of molecular mechanisms inside cells. Traditional methods to predict new targets for known drugs were based on small molecules, protein targets or phenotype features. Here, we proposed a network-based inference (NBI) method which only used drug-target bipartite network topology similarity to infer new targets for known drugs. The performance of NBI outperformed the drug-based similarity inference and target-based similarity inference methods as well as other published methods. Via the NBI method five old drugs, namely montelukast, diclofenac, simvastatin, ketoconazole, and itraconazole, were identified to have polypharmacological effects on human estrogen receptors or dipeptidyl peptidase-IV with half maximal inhibitory or effective concentration from submicromolar to micromolar by in vitro assays. Moreover, simvastatin and ketoconazole showed potent antiproliferative activities on human MDA-MB-231 breast cancer cell line in MTT assays. The results indicated that the drug-target bipartite network-based inference method could be a useful tool for fishing novel drug-target interactions in molecular polypharmacological space.
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.
ABSTRACT:
A frequent problem in computational modeling is the interconversion of chemical structures between different formats. While standard interchange formats exist (for example, Chemical Markup Language) and de facto standards have arisen (for example, SMILES format), the need to interconvert formats is a continuing problem due to the multitude of different application areas for chemistry data, differences in the data stored by different formats (0D versus 3D, for example), and competition between software along with a lack of vendor-neutral formats.
We discuss, for the first time, Open Babel, an open-source chemical toolbox that speaks the many languages of chemical data. Open Babel version 2.3 interconverts over 110 formats. The need to represent such a wide variety of chemical and molecular data requires a library that implements a wide range of cheminformatics algorithms, from partial charge assignment and aromaticity detection, to bond order perception and canonicalization. We detail the implementation of Open Babel, describe key advances in the 2.3 release, and outline a variety of uses both in terms of software products and scientific research, including applications far beyond simple format interconversion.
Open Babel presents a solution to the proliferation of multiple chemical file formats. In addition, it provides a variety of useful utilities from conformer searching and 2D depiction, to filtering, batch conversion, and substructure and similarity searching. For developers, it can be used as a programming library to handle chemical data in areas such as organic chemistry, drug design, materials science, and computational chemistry. It is freely available under an open-source license from http://openbabel.org.
Knowledge and investigation of therapeutic targets (responsible for drug efficacy) and the targeted drugs facilitate target and drug discovery and validation. Therapeutic Target Database (TTD, http://bidd.nus.edu.sg/group/ttd/ttd.asp) has been developed to provide comprehensive information about efficacy targets and the corresponding approved, clinical trial and investigative drugs. Since its last update, major improvements and updates have been made to TTD. In addition to the significant increase of data content (from 1894 targets and 5028 drugs to 2025 targets and 17,816 drugs), we added target validation information (drug potency against target, effect against disease models and effect of target knockout, knockdown or genetic variations) for 932 targets, and 841 quantitative structure activity relationship models for active compounds of 228 chemical types against 121 targets. Moreover, we added the data from our previous drug studies including 3681 multi-target agents against 108 target pairs, 116 drug combinations with their synergistic, additive, antagonistic, potentiative or reductive mechanisms, 1427 natural product-derived approved, clinical trial and pre-clinical drugs and cross-links to the clinical trial information page in the ClinicalTrials.gov database for 770 clinical trial drugs. These updates are useful for facilitating target discovery and validation, drug lead discovery and optimization, and the development of multi-target drugs and drug combinations.
Adverse drug events (ADEs) are common and account for 770 000 injuries and deaths each year and drug interactions account for as much as 30% of these ADEs. Spontaneous reporting systems routinely collect ADEs from patients on complex combinations of medications and provide an opportunity to discover unexpected drug interactions. Unfortunately, current algorithms for such "signal detection" are limited by underreporting of interactions that are not expected. We present a novel method to identify latent drug interaction signals in the case of underreporting.
We identified eight clinically significant adverse events. We used the FDA's Adverse Event Reporting System to build profiles for these adverse events based on the side effects of drugs known to produce them. We then looked for pairs of drugs that match these single-drug profiles in order to predict potential interactions. We evaluated these interactions in two independent data sets and also through a retrospective analysis of the Stanford Hospital electronic medical records.
We identified 171 novel drug interactions (for eight adverse event categories) that are significantly enriched for known drug interactions (p=0.0009) and used the electronic medical record for independently testing drug interaction hypotheses using multivariate statistical models with covariates.
Our method provides an option for detecting hidden interactions in spontaneous reporting systems by using side effect profiles to infer the presence of unreported adverse events.
DrugBank (http://www.drugbank.ca) is a richly annotated database of drug and drug target information. It contains extensive data on the nomenclature, ontology, chemistry, structure, function, action, pharmacology, pharmacokinetics, metabolism and pharmaceutical properties of both small molecule and large molecule (biotech) drugs. It also contains comprehensive information on the target diseases, proteins, genes and organisms on which these drugs act. First released in 2006, DrugBank has become widely used by pharmacists, medicinal chemists, pharmaceutical researchers, clinicians, educators and the general public. Since its last update in 2008, DrugBank has been greatly expanded through the addition of new drugs, new targets and the inclusion of more than 40 new data fields per drug entry (a 40% increase in data 'depth'). These data field additions include illustrated drug-action pathways, drug transporter data, drug metabolite data, pharmacogenomic data, adverse drug response data, ADMET data, pharmacokinetic data, computed property data and chemical classification data. DrugBank 3.0 also offers expanded database links, improved search tools for drug-drug and food-drug interaction, new resources for querying and viewing drug pathways and hundreds of new drug entries with detailed patent, pricing and manufacturer data. These additions have been complemented by enhancements to the quality and quantity of existing data, particularly with regard to drug target, drug description and drug action data. DrugBank 3.0 represents the result of 2 years of manual annotation work aimed at making the database much more useful for a wide range of 'omics' (i.e. pharmacogenomic, pharmacoproteomic, pharmacometabolomic and even pharmacoeconomic) applications.
The Comparative Toxicogenomics Database (CTD) is a public resource that promotes understanding about the interaction of environmental
chemicals with gene products, and their effects on human health. Biocurators at CTD manually curate a triad of chemical–gene,
chemical–disease and gene–disease relationships from the literature. These core data are then integrated to construct chemical–gene–disease
networks and to predict many novel relationships using different types of associated data. Since 2009, we dramatically increased
the content of CTD to 1.4 million chemical–gene–disease data points and added many features, statistical analyses and analytical
tools, including GeneComps and ChemComps (to find comparable genes and chemicals that share toxicogenomic profiles), enriched
Gene Ontology terms associated with chemicals, statistically ranked chemical–disease inferences, Venn diagram tools to discover
overlapping and unique attributes of any set of chemicals, genes or disease, and enhanced gene pathway data content, among
other features. Together, this wealth of expanded chemical–gene–disease data continues to help users generate testable hypotheses
about the molecular mechanisms of environmental diseases. CTD is freely available at http://ctd.mdibl.org.
Motivation: Identifying drug–drug interactions (DDIs) is a critical process in drug administration and drug development. Clinical support tools often provide comprehensive lists of DDIs, but they usually lack the supporting scientific evidences and different tools can return inconsistent results. In this article, we propose a novel approach that integrates text mining and automated reasoning to derive DDIs. Through the extraction of various facts of drug metabolism, not only the DDIs that are explicitly mentioned in text can be extracted but also the potential interactions that can be inferred by reasoning.
Results: Our approach was able to find several potential DDIs that are not present in DrugBank. We manually evaluated these interactions based on their supporting evidences, and our analysis revealed that 81.3% of these interactions are determined to be correct. This suggests that our approach can uncover potential DDIs with scientific evidences explaining the mechanism of the interactions.
Contact: luis.tari@roche.com
The molecular understanding of phenotypes caused by drugs in humans is essential for elucidating mechanisms of action and for developing personalized medicines. Side effects of drugs (also known as adverse drug reactions) are an important source of human phenotypic information, but so far research on this topic has been hampered by insufficient accessibility of data. Consequently, we have developed a public, computer-readable side effect resource (SIDER) that connects 888 drugs to 1450 side effect terms. It contains information on frequency in patients for one-third of the drug-side effect pairs. For 199 drugs, the side effect frequency of placebo administration could also be extracted. We illustrate the potential of SIDER with a number of analyses. The resource is freely available for academic research at http://sideeffects.embl.de.
Much of the information on the Cytochrome P450 enzymes (CYPs) is spread across literature and the internet. Aggregating knowledge
about CYPs into one database makes the search more efficient. Text mining on 57 CYPs and drugs led to a mass of papers, which
were screened manually for facts about metabolism, SNPs and their effects on drug degradation. Information was put into a
database, which enables the user not only to look up a particular CYP and all metabolized drugs, but also to check tolerability
of drug-cocktails and to find alternative combinations, to use metabolic pathways more efficiently. The SuperCYP database
contains 1170 drugs with more than 3800 interactions including references. Approximately 2000 SNPs and mutations are listed
and ordered according to their effect on expression and/or activity. SuperCYP (http://bioinformatics.charite.de/supercyp) is a comprehensive resource focused on CYPs and drug metabolism. Homology-modeled structures of the CYPs can be downloaded
in PDB format and related drugs are available as MOL-files. Within the resource, CYPs can be aligned with each other, drug-cocktails
can be ‘mixed’, SNPs, protein point mutations, and their effects can be viewed and corresponding PubMed IDs are given. SuperCYP
is meant to be a platform and a starting point for scientists and health professionals for furthering their research.
The cytochrome P450 (CYP) gene family catalyzes drug metabolism and bioactivation and is therefore relevant to drug development. We determined potency values for 17,143 compounds against five recombinant CYP isozymes (1A2, 2C9, 2C19, 2D6 and 3A4) using an in vitro bioluminescent assay. The compounds included libraries of US Food and Drug Administration (FDA)-approved drugs and screening libraries. We observed cross-library isozyme inhibition (30-78%) with important differences between libraries. Whereas only 7% of the typical screening library was inactive against all five isozymes, 33% of FDA-approved drugs were inactive, reflecting the optimized pharmacological properties of the latter. Our results suggest that low CYP 2C isozyme activity is a common property of drugs, whereas other isozymes, such as CYP 2D6, show little discrimination between drugs and unoptimized compounds found in screening libraries. We also identified chemical substructures that differentiated between the five isozymes. The pharmacological compendium described here should further the understanding of CYP isozymes.
To identify and evaluate the systems failures that underlie errors causing adverse drug events (ADEs) and potential ADEs.
Systems analysis of events from a prospective cohort study.
All admissions to 11 medical and surgical units in two tertiary care hospitals over a 6-month period.
Errors, proximal causes, and systems failures.
Errors were detected by interviews of those involved. Errors were classified according to proximal cause and underlying systems failure by multidisciplinary teams of physicians, nurses, pharmacists, and systems analysts.
During this period, 334 errors were detected as the causes of 264 preventable ADEs and potential ADEs. Sixteen major systems failures were identified as the underlying causes of the errors. The most common systems failure was in the dissemination of drug knowledge, particularly to physicians, accounting for 29% of the 334 errors. Inadequate availability of patient information, such as the results of laboratory tests, was associated with 18% of errors. Seven systems failures accounted for 78% of the errors; all could be improved by better information systems.
Hospital personnel willingly participated in the detection and investigation of drug use errors and were able to identify underlying systems failures. The most common defects were in systems to disseminate knowledge about drugs and to make drug and patient information readily accessible at the time it is needed. Systems changes to improve dissemination and display of drug and patient data should make errors in the use of drugs less likely.
The purpose of this study was to estimate and compare the effects of antipsychotics-both the newer ones and the conventional ones-on body weight. Method: A comprehensive literature search identified 81 English- and non-English-language articles that included data on weight change in antipsychotic-treated patients. For each agent, a meta-analysis and random effects metaregression estimated the weight change after 10 weeks of treatment at a standard dose. A comprehensive narrative review was also conducted on all articles that did not yield quantitative information but did yield important qualitative information.
Placebo was associated with a mean weight reduction of 0.74 kg. Among conventional agents, mean weight change ranged from a reduction of 0.39 kg with molindone to an increase of 3.19 kg with thioridazine. Among newer antipsychotic agents, mean increases were as follows: clozapine, 4.45 kg; olanzapine, 4.15 kg; sertindole, 2.92 kg; risperidone, 2.10 kg; and ziprasidone, 0.04 kg. Insufficient data were available to evaluate quetiapine at 10 weeks.
Both conventional and newer antipsychotics are associated with weight gain. Among the newer agents, clozapine appears to have the greatest potential to induce weight gain, and ziprasidone the least. The differences among newer agents may affect compliance with medication and health risk.
We provide a unified overview of methods that currently are widely used to assess the accuracy of prediction algorithms, from raw percentages, quadratic error measures and other distances, and correlation coefficients, and to information theoretic measures such as relative entropy and mutual information. We briefly discuss the advantages and disadvantages of each approach. For classification tasks, we derive new learning algorithms for the design of prediction systems by directly optimising the correlation coefficient. We observe and prove several results relating sensitivity and specificity of optimal systems. While the principles are general, we illustrate the applicability on specific problems such as protein secondary structure and signal peptide prediction.
Cytoscape is an open source software project for integrating biomolecular interaction networks with high-throughput expression data and other molecular states into a unified conceptual framework. Although applicable to any system of molecular components and interactions, Cytoscape is most powerful when used in conjunction with large databases of protein-protein, protein-DNA, and genetic interactions that are increasingly available for humans and model organisms. Cytoscape's software Core provides basic functionality to layout and query the network; to visually integrate the network with expression profiles, phenotypes, and other molecular states; and to link the network to databases of functional annotations. The Core is extensible through a straightforward plug-in architecture, allowing rapid development of additional computational analyses and features. Several case studies of Cytoscape plug-ins are surveyed, including a search for interaction pathways correlating with changes in gene expression, a study of protein complexes involved in cellular recovery to DNA damage, inference of a combined physical/functional interaction network for Halobacterium, and an interface to detailed stochastic/kinetic gene regulatory models.
Olanzapine, an atypical antipsychotic, is often regarded as a safe choice for psychosis management. We hereby report an aged case that presented with conscious depression, bradycardia, hypotension, miosis and hypothermia. Olanzapine was thought to be the offending agent. His condition improved with supportive therapy.
In vitro screening for drugs that inhibit cytochrome P450 enzymes is well established as a means for predicting potential metabolism-mediated drug interactions in vivo. Given that these predictions are based on enzyme kinetic parameters observed from in vitro experiments, the miscalculation of the inhibitory potency of a compound can lead to an inaccurate prediction of an in vivo drug interaction, potentially precluding a safe drug from advancing in development or allowing a potent inhibitor to 'slip' into the patient population. Here, we describe the principles underlying the generation of in vitro drug metabolism data and highlight commonly encountered uncertainties and sources of bias and error that can affect extrapolation of drug-drug interaction information to the clinical setting.
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Objective
—To identify and evaluate the systems failures that underlie errors causing adverse drug events (ADEs) and potential ADEs.
Design
—Systems analysis of events from a prospective cohort study.
Participants
—All admissions to 11 medical and surgical units in two tertiary care hospitals over a 6-month period.
Main Outcome Measures
—Errors, proximal causes, and systems failures.
Methods
—Errors were detected by interviews of those involved. Errors were classified according to proximal cause and underlying systems failure by multidisciplinary teams of physicians, nurses, pharmacists, and systems analysts.
Results
—During this period, 334 errors were detected as the causes of 264 preventable ADEs and potential ADEs. Sixteen major systems failures were identified as the underlying causes of the errors. The most common systems failure was in the dissemination of drug knowledge, particularly to physicians, accounting for 29% of the 334 errors. Inadequate availability of patient information, such as the results of laboratory tests, was associated with 18% of errors. Seven systems failures accounted for 78% of the errors; all could be improved by better information systems.
Conclusions
—Hospital personnel willingly participated in the detection and investigation of drug use errors and were able to identify underlying systems failures. The most common defects were in systems to disseminate knowledge about drugs and to make drug and patient information readily accessible at the time it is needed. Systems changes to improve dissemination and display of drug and patient data should make errors in the use of drugs less likely.(JAMA. 1995;274:35-43)
The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data. High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Prediction of polypharmacological profiles of drugs enables us to investigate drug side effects and further find their new indications, i.e. drug repositioning, which could reduce the costs while increase the productivity of drug discovery. Here we describe a new computational framework to predict polypharmacological profiles of drugs by the integration of chemical, side effect, and therapeutic space. On the basis of our previous developed drug side effects database, named MetaADEDB, a drug side effect similarity inference (DSESI) method was developed for drug–target interaction (DTI) prediction on a known DTI network connecting 621 approved drugs and 893 target proteins. The area under the receiver operating characteristic curve was 0.882 ± 0.011 averaged from 100 simulated tests of 10-fold cross-validation for the DSESI method, which is comparative with drug structural similarity inference and drug therapeutic similarity inference methods. Seven new predicted candidate target proteins for seven approved drugs were confirmed by published experiments, with the successful hit rate more than 15.9%. Moreover, network visualization of drug–target interactions and off-target side effect associations provide new mechanism-of-action of three approved antipsychotic drugs in a case study. The results indicated that the proposed methods could be helpful for prediction of polypharmacological profiles of drugs.
The incidence of treatment resistance in schizophrenia (failure to respond to antipsychotic therapy) is about 20%. Factors that may contribute to it include non-adherence (non-compliance) to treatment, comorbid conditions and medication side-effects. The National Institute for Clinical Excellence recommends that clozapine be used for schizophrenia resistant to another atypical antipsychotic. Here we focus on patients who are also resistant to clozapine given in adequate dosage for sufficient duration. Switching from clozapine to a previously untried atypical (e.g. olanzapine, risperidone, quetiapine) might be of benefit in partial treatment resistance. In more difficult cases, augmentation of clozapine with benzamides (sulpiride, amisulpride) and anti-epileptics (lamotrigine) shows some success. In extreme treatment resistance, a strategy is recommended that combines the proven best drug for the particular patient and psychosocial treatments.
Adverse drug events (ADEs) mean the harms associated with uses of given medications at normal dosages, which is crucial for a drug to be approved in clinic use or continue to stay in market. Many ADEs are not identified in clinical trials until the drug is approved for use in clinic, which results in adverse morbidity and mortality. To date millions of ADEs have been reported around the world. How to avoid or reduce ADEs is an important issue for drug discovery and development. Here, we reported a comprehensive database of adverse drug events (namely MetaADEDB), which included more than 52 thousands of drug-ADE associations among 3059 unique compounds (including 1330 drugs) and 13,200 ADE items by data integration and text mining. All compounds and ADEs were annotated with the most commonly used concepts defined in Medical Subject Headings (MeSH). Meanwhile, a computational method, namely phenotypic network inference model (PNIM), was developed for prediction of potential ADEs based on the database. The area under the receive operating characteristic curve (AUC) is more than 0.9 by 10-fold cross validation, while the AUC value was 0.912 for an external validation set extracted from the US-FDA Adverse Events Reporting System, which indicated that the prediction capability of the method was reliable. MetaADEDB is accessible free of charge at http://www.lmmd.org/online_services/metaadedb/. The database and the method provide us a useful tool to search for known side effects or predict potential side effects for a given drug or a compound.
Drug-drug interactions (DDIs) are an emerging threat to public health. Recent estimates indicate that DDIs cause nearly 74000 emergency room visits and 195000 hospitalizations each year in the USA. Current approaches to DDI discovery, which include Phase IV clinical trials and post-marketing surveillance, are insufficient for detecting many DDIs and do not alert the public to potentially dangerous DDIs before a drug enters the market. Recent work has applied state-of-the-art computational and statistical methods to the problem of DDIs. Here we review recent developments that encompass a range of informatics approaches in this domain, from the construction of databases for efficient searching of known DDIs to the prediction of novel DDIs based on data from electronic medical records, adverse event reports, scientific abstracts, and other sources. We also explore why DDIs are so difficult to detect and what the future holds for informatics-based approaches to DDI discovery.
Moves to release more data from clinical trials could provide unprecedented opportunities to understand disease biology and drug effects.
Elucidation of chemical-protein interactions (CPI) is the basis of target identification and drug discovery. It is time-consuming and costly to determine CPI experimentally, and computational methods will facilitate the determination of CPI. In this study, two methods, multitarget quantitative structure-activity relationship (mt-QSAR) and computational chemogenomics, were developed for CPI prediction. Two comprehensive data sets were collected from the ChEMBL database for method assessment. One data set consisted of 81 689 CPI pairs among 50 924 compounds and 136 G-protein coupled receptors (GPCRs), while the other one contained 43 965 CPI pairs among 23 376 compounds and 176 kinases. The range of the area under the receiver operating characteristic curve (AUC) for the test sets was 0.95 to 1.0 and 0.82 to 1.0 for 100 GPCR mt-QSAR models and 100 kinase mt-QSAR models, respectively. The AUC of 5-fold cross validation were about 0.92 for both 176 kinases and 136 GPCRs using the chemogenomic method. However, the performance of the chemogenomic method was worse than that of mt-QSAR for the external validation set. Further analysis revealed that there was a high false positive rate for the external validation set when using the chemogenomic method. In addition, we developed a web server named CPI-Predictor, , which is available for free. The methods and tool have potential applications in network pharmacology and drug repositioning.
Drug-drug interactions (DDIs) are responsible for many serious adverse events; their detection is crucial for patient safety but is very challenging. Currently, the US Food and Drug Administration and pharmaceutical companies are showing great interest in the development of improved tools for identifying DDIs.
We present a new methodology applicable on a large scale that identifies novel DDIs based on molecular structural similarity to drugs involved in established DDIs. The underlying assumption is that if drug A and drug B interact to produce a specific biological effect, then drugs similar to drug A (or drug B) are likely to interact with drug B (or drug A) to produce the same effect. DrugBank was used as a resource for collecting 9454 established DDIs. The structural similarity of all pairs of drugs in DrugBank was computed to identify DDI candidates.
The methodology was evaluated using as a gold standard the interactions retrieved from the initial DrugBank database. Results demonstrated an overall sensitivity of 0.68, specificity of 0.96, and precision of 0.26. Additionally, the methodology was also evaluated in an independent test using the Micromedex/Drugdex database.
The proposed methodology is simple, efficient, allows the investigation of large numbers of drugs, and helps highlight the etiology of DDI. A database of 58 403 predicted DDIs with structural evidence is provided as an open resource for investigators seeking to analyze DDIs.
Virtual screening (VS) can be accomplished in either ligand- or structure-based methods. In recent times, an increasing number of 2D fingerprint and 3D shape similarity methods have been used in ligand-based VS. To evaluate the performance of these ligand-based methods, retrospective VS was performed on a tailored directory of useful decoys (DUD). The VS performances of 14 2D fingerprints and four 3D shape similarity methods were compared. The results revealed that 2D fingerprints ECFP_2 and FCFP_4 yielded better performance than the 3D Phase Shape methods. These ligand-based methods were also compared with structure-based methods, such as Glide docking and Prime molecular mechanics generalized Born surface area rescoring, which demonstrated that both 2D fingerprint and 3D shape similarity methods could yield higher enrichment during early retrieval of active compounds. The results demonstrated the superiority of ligand-based methods over the docking-based screening in terms of both speed and hit enrichment. Therefore, considering ligand-based methods first in any VS workflow would be a wise option.
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Cytochrome P450 inhibitory promiscuity of a drug has potential effects on the occurrence of clinical drug-drug interactions. Understanding how a molecular property is related to the P450 inhibitory promiscuity could help to avoid such adverse effects. In this study, an entropy-based index was defined to quantify the P450 inhibitory promiscuity of a compound based on a comprehensive data set, containing more than 11,500 drug-like compounds with inhibition against five major P450 isoforms, 1A2, 2C9, 2C19, 2D6, and 3A4. The results indicated that the P450 inhibitory promiscuity of a compound would have a moderate correlation with molecular aromaticity, a minor correlation with molecular lipophilicity, and no relations with molecular complexity, hydrogen bonding ability, and TopoPSA. We also applied an index to quantify the susceptibilities of different P450 isoforms to inhibition based on the same data set. The results showed that there was a surprising level of P450 inhibitory promiscuity even for substrate specific P450, susceptibility to inhibition follows the rank-order: 1A2 > 2C19 > 3A4 > 2C9 > 2D6. There was essentially no correlation between P450 inhibitory potency and specificity and minor negative trade-offs between P450 inhibitory promiscuity and catalytic promiscuity. In addition, classification models were built to predict the P450 inhibitory promiscuity of new chemicals using support vector machine algorithm with different fingerprints. The area under the receiver operating characteristic curve of the best model was about 0.9, evaluated by 5-fold cross-validation. These findings would be helpful for understanding the mechanism of P450 inhibitory promiscuity and improving the P450 inhibitory selectivity of new chemicals in drug discovery.
Adverse side effects of drug-drug interactions induced by human cytochrome P450 (CYP) inhibition is an important consideration, especially, during the research phase of drug discovery. It is highly desirable to develop computational models that can predict the inhibitive effect of a compound against a specific CYP isoform. In this study, inhibitor predicting models were developed for five major CYP isoforms, namely 1A2, 2C9, 2C19, 2D6, and 3A4, using a combined classifier algorithm on a large data set containing more than 24,700 unique compounds, extracted from PubChem. The combined classifiers algorithm is an ensemble of different independent machine learning classifiers including support vector machine, C4.5 decision tree, k-nearest neighbor, and naïve Bayes, fused by a back-propagation artificial neural network (BP-ANN). All developed models were validated by 5-fold cross-validation and a diverse validation set composed of about 9000 diverse unique compounds. The range of the area under the receiver operating characteristic curve (AUC) for the validation sets was 0.764 to 0.815 for CYP1A2, 0.837 to 0.861 for CYP2C9, 0.793 to 0.842 for CYP2C19, 0.839 to 0.886 for CYP2D6, and 0.754 to 0.790 for CYP3A4, respectively, using the new developed combined classifiers. The overall performance of the combined classifiers fused by BP-ANN was superior to that of three classic fusion techniques (Mean, Maximum, and Multiply). The chemical spaces of data sets were explored by multidimensional scaling plots, and the use of applicability domain improved the prediction accuracies of models. In addition, some representative substructure fragments differentiating CYP inhibitors and noninhibitors were characterized by the substructure fragment analysis. These classification models are applicable for virtual screening of the five major CYP isoforms inhibitors or can be used as simple filters of potential chemicals in drug discovery.
There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods.
In clinical practice, patients are encountered who are partial responders or nonresponders to clozapine. There are others who are unable to tolerate a high dosage of clozapine. In the two cases presented, we propose an alternative strategy using olanzapine in combination with clozapine in treatment-refractory patients. Olanzapine was found to be helpful in these patients, however, controlled studies are needed.
We define an adverse drug reaction as "an appreciably harmful or unpleasant reaction, resulting from an intervention related to the use of a medicinal product, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product." Such reactions are currently reported by use of WHO's Adverse Reaction Terminology, which will eventually become a subset of the International Classification of Diseases. Adverse drug reactions are classified into six types (with mnemonics): dose-related (Augmented), non-dose-related (Bizarre), dose-related and time-related (Chronic), time-related (Delayed), withdrawal (End of use), and failure of therapy (Failure). Timing, the pattern of illness, the results of investigations, and rechallenge can help attribute causality to a suspected adverse drug reaction. Management includes withdrawal of the drug if possible and specific treatment of its effects. Suspected adverse drug reactions should be reported. Surveillance methods can detect reactions and prove associations.
Drug-drug interactions are a preventable cause of morbidity and mortality, yet their consequences in the community are not well characterized.
To determine whether elderly patients admitted to hospital with specific drug toxicities were likely to have been prescribed an interacting drug in the week prior to admission.
Three population-based, nested case-control studies.
Ontario, Canada, from January 1, 1994, to December 31, 2000.
All Ontario residents aged 66 years or older treated with glyburide, digoxin, or an angiotensin-converting enzyme (ACE) inhibitor. Case patients were those admitted to hospital for drug-related toxicity. Prescription records of cases were compared with those of controls (matched on age, sex, use of the same medication, and presence or absence of renal disease) for receipt of interacting medications (co-trimoxazole with glyburide, clarithromycin with digoxin, and potassium-sparing diuretics with ACE inhibitors).
Odds ratio for association between hospital admission for drug toxicity (hypoglycemia, digoxin toxicity, or hyperkalemia, respectively) and use of an interacting medication in the preceding week, adjusted for diagnoses, receipt of other medications, the number of prescription drugs, and the number of hospital admissions in the year preceding the index date.
During the 7-year study period, 909 elderly patients receiving glyburide were admitted with a diagnosis of hypoglycemia. In the primary analysis, those patients admitted for hypoglycemia were more than 6 times as likely to have been treated with co-trimoxazole in the previous week (adjusted odds ratio, 6.6; 95% confidence interval, 4.5-9.7). Patients admitted with digoxin toxicity (n = 1051) were about 12 times more likely to have been treated with clarithromycin (adjusted odds ratio, 11.7; 95% confidence interval, 7.5-18.2) in the previous week, and patients treated with ACE inhibitors admitted with a diagnosis of hyperkalemia (n = 523) were about 20 times more likely to have been treated with a potassium-sparing diuretic (adjusted odds ratio, 20.3; 95% confidence interval, 13.4-30.7) in the previous week. No increased risk of drug toxicity was found for drugs with similar indications but no known interactions (amoxicillin, cefuroxime, and indapamide, respectively).
Many hospital admissions of elderly patients for drug toxicity occur after administration of a drug known to cause drug-drug interactions. Many of these interactions could have been avoided.