Two-Dimensional Deep Learning Frameworks for Drug-Induced Cardiotoxicity Detection.

The identification of drug-induced cardiotoxicity remains a pressing challenge with far-reaching clinical and economic ramifications, often leading to patient harm and resource-intensive drug recalls. Current methodologies, including in vivo and in vitro models, have severe limitations in accurate identification of cardiotoxic substances. Pioneering a paradigm shift from these conventional techniques, our study presents two deep learning-based frameworks, STFT-CNN and SST-CNN, to assess cardiotoxicity with markedly improved accuracy and reliability. Leveraging the power of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) as a more human-relevant cell model, we record mechanical beating signals through impedance measurements. These temporal signals were converted into enriched two-dimensional representations through advanced transformation techniques, specifically short-time Fourier transform (STFT) and synchro-squeezing transform (SST). These transformed data are fed into the proposed frameworks for comprehensive analysis, including drug type classification, concentration classification, cardiotoxicity classification, and new drug identification. Compared to traditional models like recurrent neural network (RNN) and 1-dimensional convolutional neural network (1D-CNN), SST-CNN delivered an impressive test accuracy of 98.55% in drug type classification and 99% in distinguishing cardiotoxic and noncardiotoxic drugs. Its feasibility is further highlighted with a stellar 98.5% average accuracy for classification of various concentrations, and the superiority of our proposed frameworks underscores their promise in revolutionizing drug safety assessments. With a potential for scalability, they represent a major leap in drug safety assessments, offering a pathway to more robust, efficient, and human-relevant cardiotoxicity evaluations.

3D-printed portable device for illicit drug identification based on smartphone-imaging and artificial neural networks.

In this manuscript, a 3D-printed analytical device has been successfully developed to classify illicit drugs using smartphone-based colorimetry. Representative compounds of different families, including cocaine, 3,4-methylenedioxy-methamphetamine (MDMA), amphetamine and cathinone derivatives, pyrrolidine cathinones, and 3,4-methylenedioxy cathinones, have been analyzed and classified after appropriate reaction with Marquis, gallic acid, sulfuric acid, Simon and Scott reagents. A picture of the colored products was acquired using a smartphone, and the corrected RGB values were used as input data in the chemometric treatment. ANN using two active layers of nodes (6 nodes in layer 1 and 2 nodes in layer 2) with a sigmoidal transfer function and a minimum strict threshold of 0.50 identified illicit drug samples with a sensitivity higher than 83.4 % and a specificity of 100 % with limits of detection in the microgram range. The 3D printed device can operate connected to a rechargeable lithium-ion cell portable battery, is inexpensive, and requires minimal training. The analytical device has been able to discriminate the analyzed psychoactive substances from cutting and mixing agents, being a useful tool for law enforcement agents to use as a screening method.

Coupling Drug Dissolution with BCS.

PURPOSE: The purpose of this study is to develop a Temporal Biopharmaceutic Classification System (T-BCS), linking Finite Dissolution Time (F.D.T.) and Mean Dissolution Time (M.D.T.) for Class I/III drugs and Mean Dissolution Time for saturation (M.D.T.s.) for Class II/IV drugs. METHODS: These parameters are estimated graphically or by fitting dissolution models to experimental data and coupled with the dose-to-solubility ratio (q) for each drug normalized in terms of the actual volume of dissolution medium (900 mL). RESULTS: Class I/III drugs consistently exhibited q values less than 1, aligning with expectations based on their solubility, while some Class II/IV drugs presented a deviation from anticipated q values, with observations of q < 1. This irregularity was rendered to the dissolution volume of 250 mL used for biopharmaceutical classification purposes instead of 900 mL applied as well as the dual classification of some sparingly soluble drugs. Biowaivers were also analyzed in terms of M.D.T., F.D.T. estimates and the regulatory dissolution time limits for rapidly and very-rapidly dissolved drugs. CONCLUSIONS: The T-BCS is useful for establishing correlations and assessing the magnitude of M.D.T., F.D.T., or M.D.T.s. for inter- and intra-class comparisons of different drugs and provide relationships between these parameters across all the models that were utilized.

Necroptosis in Pneumonia: Therapeutic Strategies and Future Perspectives.

Pneumonia remains a major global health challenge, necessitating the development of effective therapeutic approaches. Recently, necroptosis, a regulated form of cell death, has garnered attention in the fields of pharmacology and immunology for its role in the pathogenesis of pneumonia. Characterized by cell death and inflammatory responses, necroptosis is a key mechanism contributing to tissue damage and immune dysregulation in various diseases, including pneumonia. This review comprehensively analyzes the role of necroptosis in pneumonia and explores potential pharmacological interventions targeting this cell death pathway. Moreover, we highlight the intricate interplay between necroptosis and immune responses in pneumonia, revealing a bidirectional relationship between necrotic cell death and inflammatory signaling. Importantly, we assess current therapeutic strategies modulating necroptosis, encompassing synthetic inhibitors, natural products, and other drugs targeting key components of the programmed necrosis pathway. The article also discusses challenges and future directions in targeting programmed necrosis for pneumonia treatment, proposing novel therapeutic strategies that combine antibiotics with necroptosis inhibitors. This review underscores the importance of understanding necroptosis in pneumonia and highlights the potential of pharmacological interventions to mitigate tissue damage and restore immune homeostasis in this devastating respiratory infection.

Multitask joint learning with graph autoencoders for predicting potential MiRNA-drug associations.

The occurrence of many diseases is associated with miRNA abnormalities. Predicting potential drug-miRNA associations is of great importance for both disease treatment and new drug discovery. Most computation-based approaches learn one task at a time, ignoring the information contained in other tasks in the same domain. Multitask learning can effectively enhance the prediction performance of a single task by extending the valid information of related tasks. In this paper, we presented a multitask joint learning framework (MTJL) with a graph autoencoder for predicting the associations between drugs and miRNAs. First, we combined multiple pieces of information to construct a high-quality similarity network of both drugs and miRNAs and then used a graph autoencoder (GAE) to learn their embedding representations separately. Second, to further improve the embedding quality of drugs, we added an auxiliary task to classify drugs using the learned representations. Finally, the embedding representations of drugs and miRNAs were linearly transformed to obtain the predictive association scores between them. A comparison with other state-of-the-art models shows that MTJL has the best prediction performance, and ablation experiments show that the auxiliary task can enhance the embedding quality and improve the robustness of the model. In addition, we show that MTJL has high utility in predicting potential associations between drugs and miRNAs by conducting two case studies.

Adaptation of a European categorization system for driving-impairing medicines in Iran.

OBJECTIVE: Road traffic crashes due to impaired driving are a leading cause of preventable injuries and deaths. The purpose of this study was adaptation of a European categorization system for driving-impairing medicines in Iran. METHODS: DRUID categorization system was used as a leading model to classify medicines. Medicines that were compatible with DRUID categorization system were identified and classified accordingly. Medicines that were not compatible with DRUID categorization system were assessed in an expert panel in terms of possiblity of classification. Instructions for health care providers and advice for patients were prepared based on the medicine's influence on fitness to drive. RESULTS: Of the 1255 medicines in Iranian pharmacopeia, 488 medicines were classified in four categories. Among classified medicines 43.85% and 25.41% belonged to Category 0 and Category 1. About 13.94%, 10.04%, and 6.76% pertained to Category 2, Category 3, and Multiple categories respectively. Majority of the medicines with moderate and severe adverse influences on driving fitness belonged to the nervous system medicines (72.65%). Most of the medicines with non-existing or minor adverse influences on driving fitness pertained to cardiovascular medicines (16.56%). Majority of uncategorized medicines belonged to Iranian herbal medicines. CONCLUSION: The current study disclosed that DRUID categorization system was implementable for most of the commonly prescribed medicines. Experimental studies are needed to determine the influence of uncategorized medicines of Iranian pharmacopeia. Other countries with similar settings can adapt DRUID categorization system until they develop their own model using original studies.

Current and future prospective of pharmaceutical manufacturing in Saudi Arabia.

This observational descriptive study that was carried out with the objective of exploring the contribution of the local pharmaceutical industry to the Saudi drug security. Using a drug formulary provided from the Saudi Food and Drug Authority, containing all registered pharmaceutical products available in Saudi Arabia, we extracted information about drug class, drug type, country and place of manufacturing, shelf-life and price. Results showed that the majority of drugs in the market are manufactured in Europe (43.86%), followed by Saudi Arabia (22.55%), China and India (20.47%), Americas (10.24%), and other nations (2.61%). Most of the manufactured drugs were prescription drugs (90.62%). In this work, the local pharmaceutical industry with the highest percentage of contribution to local drug security was Pharmaceutical Solution Industries (PSI), representing the 5% of the items available in the Saudi market. The second highest percentage was 4% by TABUK Pharmaceutical Manufacturing CO., followed by SPIMACO (3%), JAMJOOM pharmaceutical company (2%), Riyadh pharma (2%), and Jazeera pharmaceutical industries (2%). In addition, results from this study provide information about the most essential pharmaceutical products that needs to be nationally manufactured or increased in production in order to rise the contribution of local pharmaceutical industries in Saudi drug security. Unfortunately, the small contribution of the Saudi pharmaceutical industry in local drug security increases the burden on the Kingdom's annual budget due to the over-reliance on international pharmaceuticals.

Simplifying the Extended Clearance Concept Classification System (EC3S) to Guide Clearance Prediction in Drug Discovery.

PURPOSE: The Extended Clearance Concept Classification System was established as a development-stage tool to provide a framework for identifying fundamental mechanism(s) governing drug disposition in humans. In the present study, the applicability of the EC3S in drug discovery has been investigated. In its current format, the EC3S relies on low-throughput hepatocyte uptake data, which are not frequently generated in a discovery setting. METHODS: A relationship between hepatocyte uptake clearance and MDCK permeability was first established along with intrinsic clearance from human liver microsomes. The performance of this approach was examined by categorizing 64 drugs into EC3S classes and comparing the predicted major elimination pathway(s) to that observed in humans. As an extension of the work, the ability of the simplified EC3S to predict human systemic clearance based on intrinsic clearance generated using in-vitro metabolic systems was evaluated. RESULTS: The assessment enabled the use of MDCK permeability and unscaled unbound intrinsic clearance to generate cut-off criteria to categorize compounds into four EC3S classes: Class 12ab, 2cd, 34ab, and 34cd, with major elimination mechanism(s) assigned to each class. The predictivity analysis suggested that systemic clearance could generally be predicted within threefold for EC3S class 12ab and 34ab compounds. For classes 2cd and 34cd, systemic clearance was poorly predicted using in-vitro systems explored in this study. CONCLUSION: Collectively, our simplified classification approach is expected to facilitate the identification of mechanism(s) involved in drug elimination, faster resolution of in-vitro to in-vivo disconnects, and better design of mechanistic pharmacokinetic studies in drug discovery.

A model with deep analysis on a large drug network for drug classification.

Drugs are an important means to treat various diseases. They are classified into several classes to indicate their properties and effects. Those in the same class always share some important features. The Kyoto Encyclopedia of Genes and Genomes (KEGG) DRUG recently reported a new drug classification system that classifies drugs into 14 classes. Correct identification of the class for any possible drug-like compound is helpful to roughly determine its effects for a particular type of disease. Experiments could be conducted to confirm such latent effects, thus accelerating the procedures for discovering novel drugs. In this study, this classification system was investigated. A classification model was proposed to assign one of the classes in the system to any given drug for the first time. Different from traditional fingerprint features, which indicated essential drug properties alone and were very popular in investigating drug-related problems, drugs were represented by novel features derived from a large drug network via a well-known network embedding algorithm called Node2vec. These features abstracted the drug associations generated from their essential properties, and they could overview each drug with all drugs as background. As class sizes were of great differences, synthetic minority over-sampling technique (SMOTE) was employed to tackle the imbalance problem. A balanced dataset was fed into the support vector machine to build the model. The 10-fold cross-validation results suggested the excellent performance of the model. This model was also superior to models using other drug features, including those generated by another network embedding algorithm and fingerprint features. Furthermore, this model provided more balanced performance across all classes than that without SMOTE.

Amphetamine-type stimulants (ATS) drug classification using shallow one-dimensional convolutional neural network.

Amphetamine-type stimulants (ATS) drug analysis and identification are challenging and critical nowadays with the emergence production of new synthetic ATS drugs with sophisticated design compounds. In the present study, we proposed a one-dimensional convolutional neural network (1DCNN) model to perform ATS drug classification as an alternative method. We investigate as well as explore the classification behavior of 1DCNN with the utilization of the existing novel 3D molecular descriptors as ATS drugs representation to become the model input. The proposed 1DCNN model is composed of one convolutional layer to reduce the model complexity. Besides, pooling operation that is a standard part of traditional CNN is not applied in this architecture to have more features in the classification phase. The dropout regularization technique is employed to improve model generalization. Experiments were conducted to find the optimal values for three dominant hyper-parameters of the 1DCNN model which are the filter size, transfer function, and batch size. Our findings found that kernel size 11, exponential linear unit (ELU) transfer function and batch size 32 are optimal for the 1DCNN model. A comparison with several machine learning classifiers has shown that our proposed 1DCNN has achieved comparable performance with the Random Forest classifier and competitive performance with the others.

Are European marketed acyclovir 5% cream products similar? Comparison with EU and US reference product.

OBJECTIVE: The aim was to perform a comparative evaluation of composition and in vitro release performance of multisource acyclovir 5% creams. SIGNIFICANCE: The outcome was analyzed in relation with the principles of the Topical drug Classification System (TCS). METHODS: The in vitro drug release testing (IVRT) was based on selection of an inert artificial membrane and a medium providing sink conditions, and utilizing the vertical diffusion cells. US and European innovator products, with marked difference in excipients, were used as references for the assessment of the in vitro release similarity. The qualitative composition of the topical semisolid products was inventoried, with no quantitative details being available. A Principal Component Analysis was applied by either dichotomy ranking or grouping the individual excipients into categories according to their functional role. RESULTS: The results confirmed the sensitivity and discriminative characteristics of IVRT with respect to the qualitative composition, as well as its relevance in the comparative assessment of multisource drug products beyond the current strict requirements of Q1 and Q2 similarity. CONCLUSIONS: This is in line with the principles of the TCS and with the central role assigned to IVRT.

Rheological and in vitro release measurements of manufactured acyclovir 5% creams: confirming sensitivity of the in vitro release.

Previous evaluation of marketed acyclovir 5% creams using in vitro release testing (IVRT) and its correlation with the qualitative composition confirmed the discriminative characteristics of this methodology. This was in line with the principles of Topical drug Classification System (TCS). For the current research, experimental formulations were designed and prepared by applying controlled changes in manufacturing process, sources of raw materials, and amount of the excipients. The topical semisolids were representative for the four classes of TCS. The outcome of the IVRT and rheological assessments was evaluated in relation with the nature of the change and the functional role of the excipients. The variations in propylene glycol content from 5% to 40% impacted both the in vitro release rates (gradual decrease from 16.23 to 8.97 µg/cm2/min0.5) and the microstructural characteristics (proportional increase of yield stress from 17.98 to 46.40 Pa). The inert excipients e.g. cetostearyl alcohol or white soft paraffin altered majorly the rheological behavior, as their functionality is mainly related to vehicle properties. IVRT was discriminative for the microstructural differences induced by both categories of excipients according to TCS dichotomy. This simple, reliable, and reproducible test reflected the impact of difference in quantitative composition and characteristics of excipients.

Visual Comparison of Guidelines: Method and Application to Potentially Inappropriate Medication Lists.

Therapeutic guidelines developed by experts are essential tools for improving therapy and drug prescription. Several guidelines often exist that target the same patient, from different organizations and countries. The case of lists for the detection of potentially inappropriate medications (PIMs) is an example which illustrates how these guidelines can be varied and multiple. In order to have an overview to the divergences and similarities between different lists of PIMs, we propose a visual method to compare PIMs lists, based on set visualization, and we apply it to 5 guidelines.

Evaluation of medical students' knowledge of psychoactive substances in the context of their future role in addiction prevention and therapy.

This study assesses the knowledge of medical students on the health effects of the use of psychoactive substances, in the context of their future role in prevention and treatment of addictions. The study was conducted using a questionnaire containing questions about classification, symptoms and effects of psychoactive substances, and the existing prevention programs. The study involved 430 students of medicine and allied faculties. Only 20.8% of medicine students and 12.5% of students of other faculties could correctly classify different psychoactive substances. Correct symptoms of drug misuse were mentioned by 20.4% of medicine students and 19.2% of students of other faculties. The overall knowledge of medical students was no greater than the knowledge of students of other allied faculties. Medical students showed insufficient knowledge about psychoactive substances and their effects on the human body, thus indicating the need to introduce into their study programme a more teaching in this area.

Solubility, Permeability, and Dissolution Rate of Naftidrofuryl Oxalate Based on BCS Criteria.

The Biopharmaceutics Classification System (BCS) was conceived to classify drug substances by their in vitro aqueous solubility and permeability properties. The essential activity of naftidrofuryl oxalate (NF) has been described as the inhibition of the serotonin receptors (5-HT2), resulting in vasodilation and decreasing blood pressure. Since the early 1980s, NF has been used to treat several venous and cerebral diseases. There is no data available on the BCS classification of NF. However, based on its physical-chemical properties, NF might be considered to belong to the 1st or the 3rd BCS class. The present study aimed to provide data concerning the solubility and permeability of NF through Caco-2 monolayers and propose its preliminary classification into BCS. We showed that NF is a highly soluble and permeable drug substance; thus, it might be suggested to belong to BCS class I. Additionally, a high dissolution rate of the encapsulated NF based on Praxilene® 100 mg formulation was revealed. Hence, it might be considered as an immediate-release (IR).

Classification of the present pharmaceutical agents based on the possible effective mechanism on the COVID-19 infection.

OBJECTIVES: There are several types of research on the COVID-19 disease which have been conducting. It seems that prevailing over the pandemic would be achieved only by mastering over the virus pathophysiology. We tried to categorize the massive amount of available information for useful interpretation. EVIDENCE ACQUISITION: We searched databases with different keywords and search strategies that focus on virulence and pathophysiology of COVID-19. The present review has aimed to gather and categorize all implemented drugs based on the susceptible virulence mechanisms, and the pathophysiological events in the host cells, discussing and suggesting treatments. RESULTS: As a result, the COVID-19 lifecycle were categorized as following steps: "Host Cell Attachment" which is mainly conducted with ACE2 receptors and TMPRSS2 from the host cell and Spike (S) protein, "Endocytosis Pathway" which is performed mainly by clathrin-mediated endocytosis, and "Viral Replication" which contains translation and replication of RNA viral genome. The virus pathogenicity is continued by "Inflammatory Reactions" which mainly caused moderate to severe COVID-19 disease. Besides, the possible effective therapeutics' mechanism and the pharmaceutical agents that had at least one experience as a preclinical or clinical study on COVID-19 were clearly defined. CONCLUSION: The treatment protocol would be occasional based on the stage of the infection and the patient situation. The cocktail of medicines, which could affect almost all mentioned stages of COVID-19 disease, might be vital for patients with severe phenomena. The classification of the possible mechanism of medicines based on COVID-19 pathogenicity.

The message passing neural networks for chemical property prediction on SMILES.

Drug metabolism is determined by the biochemical and physiological properties of the drug molecule. To improve the performance of a drug property prediction model, it is important to extract complex molecular dynamics from limited data. Recent machine learning or deep learning based models have employed the atom- and bond-type information, as well as the structural information to predict drug properties. However, many of these methods can be used only for the graph representations. Message passing neural networks (MPNNs) (Gilmer et al., 2017) is a framework used to learn both local and global features from irregularly formed data, and is invariant to permutations. This network performs an iterative message passing (MP) operation on each object and its neighbors, and obtain the final output from all messages regardless of their order. In this study, we applied the MP-based attention network (Nikolentzos et al., 2019) originally developed for text learning to perform chemical classification tasks. Before training, we tokenized the characters, and obtained embeddings of each molecular sequence. We conducted various experiments to maximize the predictivity of the model. We trained and evaluated our model using various chemical classification benchmark tasks. Our results are comparable to previous state-of-the-art and baseline models or outperform. To the best of our knowledge, this is the first attempt to learn chemical strings using an MP-based algorithm. We will extend our work to more complex tasks such as regression or generation tasks in the future.

ATC-NLSP: Prediction of the Classes of Anatomical Therapeutic Chemicals Using a Network-Based Label Space Partition Method.

Anatomical Therapeutic Chemical (ATC) classification system proposed by the World Health Organization is a widely accepted drug classification scheme in both academic and industrial realm. It is a multilabeling system which categorizes drugs into multiple classes according to their therapeutic, pharmacological, and chemical attributes. In this study, we adopted a data-driven network-based label space partition (NLSP) method for prediction of ATC classes of a given compound within the multilabel learning framework. The proposed method ATC-NLSP is trained on the similarity-based features such as chemical-chemical interaction and structural and fingerprint similarities of a compound to other compounds belonging to the different ATC categories. The NLSP method trains predictors for each label cluster (possibly intersecting) detected by community detection algorithms and takes the ensemble labels for a compound as final prediction. Experimental evaluation based on the jackknife test on the benchmark dataset demonstrated that our method has boosted the absolute true rate, which is the most stringent evaluation metrics in this study, from 0.6330 to 0.7497, in comparison to the state-of-the-art approaches. Moreover, the community structures of the label relation graph were detected through the label propagation method. The advantage of multilabel learning over the single-label models was shown by label-wise analysis. Our study indicated that the proposed method ATC-NLSP, which adopts ideas from network research community and captures the correlation of labels in a data driven manner, is the top-performing model in the ATC prediction task. We believed that the power of NLSP remains to be unleashed for the multilabel learning tasks in drug discovery. The source codes are freely available at https://github.com/dqwei-lab/ATC.

A proposed anti-maladaptive aggression agent classification: improving our approach to treating impulsive aggression.

Proper drug categorization enables clinicians to readily identify the agents most appropriate for patients in need. Currently, patients with maladaptive aggression do not all always fall into a single existing diagnostic or treatment category. Such is the case for those with impulsive aggression (IA). IA is an associated feature of numerous neuropsychiatric disorders, and can be described as eruptive, aggressive behavior or a 'short fuse'. Although agents from a broad spectrum of drug classes have been used to treat maladaptive aggression, few have been tested distinctly in patients with IA, and there is no drug specifically indicated by the US Food and Drug Administration (US FDA) for IA. Further, current treatments often fail to sufficiently treat IA symptomatology. These issues create an unclear and inadequate treatment path for patients. Here we will propose the establishment of a class of anti-maladaptive aggression agents to begin addressing this clinical issue. The development of such a class would unify the various drugs currently used to treat maladaptive aggression and streamline the treatment approach towards IA. As an important case example of the range of candidate drugs that could fit into a new anti-maladaptive aggression agent category, we will review an investigational IA pharmacotherapy. SPN-810 (extended-release molindone) is currently being investigated as a novel treatment for children with IA and ADHD. Based on these studies we will review how SPN-810 may be well suited for a new, anti-maladaptive aggression drug class and more precisely, a proposed subgroup of IA modulators. The goal of this review is to begin improving the identification of and therapeutic approach for maladaptive aggression as well as IA through more precise anti-maladaptive aggression agent categorization.