Machine learning and deep learning approaches for enhanced prediction of hERG blockade: a comprehensive QSAR modeling study.

BACKGROUND: Cardiotoxicity is a major cause of drug withdrawal. The hERG channel, regulating ion flow, is pivotal for heart and nervous system function. Its blockade is a concern in drug development. Predicting hERG blockade is essential for identifying cardiac safety issues. Various QSAR models exist, but their performance varies. Ongoing improvements show promise, necessitating continued efforts to enhance accuracy using emerging deep learning algorithms in predicting potential hERG blockade. STUDY DESIGN AND METHOD: Using a large training dataset, six individual QSAR models were developed. Additionally, three ensemble models were constructed. All models were evaluated using 10-fold cross-validations and two external datasets. RESULTS: The 10-fold cross-validations resulted in Mathews correlation coefficient (MCC) values from 0.682 to 0.730, surpassing the best-reported model on the same dataset (0.689). External validations yielded MCC values from 0.520 to 0.715 for the first dataset, exceeding those of previously reported models (0-0.599). For the second dataset, MCC values fell between 0.025 and 0.215, aligning with those of reported models (0.112-0.220). CONCLUSIONS: The developed models can assist the pharmaceutical industry and regulatory agencies in predicting hERG blockage activity, thereby enhancing safety assessments and reducing the risk of adverse cardiac events associated with new drug candidates.

A comprehensive review on phytochemicals in the treatment and prevention of pancreatic cancer: Focusing on their mechanism of action.

Background and Aims: Pancreatic cancer develops in the normal tissues of the pancreas from malignant cells. The chance of recovery is not good, and the chance of survival 5 years following diagnosis is quite low. Pancreatic cancer treatment strategies such as radiotherapy and chemotherapy had relatively low success rates. Therefore, the present study aims to explore new therapies for treating pancreatic cancer. Methods: The present study searched for information about pancreatic cancer pathophysiology, available treatment options; and their comparative benefits and challenges. Aiming to identify potential alternative therapeutics, this comprehensive review analyzed information from renowned databases such as Scopus, PubMed, and Google Scholar. Results: In recent years, there has been a rise in interest in the possibility that natural compounds could be used as treatments for cancer. Cannabinoids, curcumin, quercetin, resveratrol, and triptolide are some of the anticancer phytochemicals now used to manage pancreatic cancer. The above compounds are utilized by inhibiting or stimulating biological pathways such as apoptosis, autophagy, cell growth inhibition or reduction, oxidative stress, epithelial-mesenchymal transformation, and increased resistance to chemotherapeutic drugs in the management of pancreatic cancer. Conclusion: Right now, surgery is the only therapeutic option for patients with pancreatic cancer. However, most people who get sick have been diagnosed too late to benefit from potentially effective surgery. Alternative medications, like natural compounds and herbal medicines, are promising complementary therapies for pancreatic cancer. Therefore, we recommend large-scale standardized clinical research for the investigation of natural compounds to ensure their consistency and comparability in pancreatic cancer treatment.

Review of machine learning and deep learning models for toxicity prediction.

The ever-increasing number of chemicals has raised public concerns due to their adverse effects on human health and the environment. To protect public health and the environment, it is critical to assess the toxicity of these chemicals. Traditional in vitro and in vivo toxicity assays are complicated, costly, and time-consuming and may face ethical issues. These constraints raise the need for alternative methods for assessing the toxicity of chemicals. Recently, due to the advancement of machine learning algorithms and the increase in computational power, many toxicity prediction models have been developed using various machine learning and deep learning algorithms such as support vector machine, random forest, k-nearest neighbors, ensemble learning, and deep neural network. This review summarizes the machine learning- and deep learning-based toxicity prediction models developed in recent years. Support vector machine and random forest are the most popular machine learning algorithms, and hepatotoxicity, cardiotoxicity, and carcinogenicity are the frequently modeled toxicity endpoints in predictive toxicology. It is known that datasets impact model performance. The quality of datasets used in the development of toxicity prediction models using machine learning and deep learning is vital to the performance of the developed models. The different toxicity assignments for the same chemicals among different datasets of the same type of toxicity have been observed, indicating benchmarking datasets is needed for developing reliable toxicity prediction models using machine learning and deep learning algorithms. This review provides insights into current machine learning models in predictive toxicology, which are expected to promote the development and application of toxicity prediction models in the future.

Machine learning and deep learning for brain tumor MRI image segmentation.

Brain tumors are often fatal. Therefore, accurate brain tumor image segmentation is critical for the diagnosis, treatment, and monitoring of patients with these tumors. Magnetic resonance imaging (MRI) is a commonly used imaging technique for capturing brain images. Both machine learning and deep learning techniques are popular in analyzing MRI images. This article reviews some commonly used machine learning and deep learning techniques for brain tumor MRI image segmentation. The limitations and advantages of the reviewed machine learning and deep learning methods are discussed. Even though each of these methods has a well-established status in their individual domains, the combination of two or more techniques is currently an emerging trend.

Developing a SARS-CoV-2 main protease binding prediction random forest model for drug repurposing for COVID-19 treatment.

The coronavirus disease 2019 (COVID-19) global pandemic resulted in millions of people becoming infected with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus and close to seven million deaths worldwide. It is essential to further explore and design effective COVID-19 treatment drugs that target the main protease of SARS-CoV-2, a major target for COVID-19 drugs. In this study, machine learning was applied for predicting the SARS-CoV-2 main protease binding of Food and Drug Administration (FDA)-approved drugs to assist in the identification of potential repurposing candidates for COVID-19 treatment. Ligands bound to the SARS-CoV-2 main protease in the Protein Data Bank and compounds experimentally tested in SARS-CoV-2 main protease binding assays in the literature were curated. These chemicals were divided into training (516 chemicals) and testing (360 chemicals) data sets. To identify SARS-CoV-2 main protease binders as potential candidates for repurposing to treat COVID-19, 1188 FDA-approved drugs from the Liver Toxicity Knowledge Base were obtained. A random forest algorithm was used for constructing predictive models based on molecular descriptors calculated using Mold2 software. Model performance was evaluated using 100 iterations of fivefold cross-validations which resulted in 78.8% balanced accuracy. The random forest model that was constructed from the whole training dataset was used to predict SARS-CoV-2 main protease binding on the testing set and the FDA-approved drugs. Model applicability domain and prediction confidence on drugs predicted as the main protease binders discovered 10 FDA-approved drugs as potential candidates for repurposing to treat COVID-19. Our results demonstrate that machine learning is an efficient method for drug repurposing and, thus, may accelerate drug development targeting SARS-CoV-2.

Effect of charge on the antimicrobial activity of alpha-helical amphibian antimicrobial peptide.

Antibiotic resistance is a severe threat to the world's public health, which has increased the need to discover novel antibacterial molecules. In this context, an emerging class of naturally occurring short peptide molecules called antimicrobial peptides (AMPs) has been considered potent antibacterial agents. Amphibians are one of the significant sources of AMPs, which have been extensively studied for the last few decades. Most amphibian AMPs are cationic, and several of these cationic AMPs adopt a well-defined alpha-helical structure in the presence of bacterial membranes. These cationic alpha-helical amphibian AMPs (CαAMPs) can selectively and preferentially bind with the negatively charged surfaces of Gram-positive and Gram-negative bacteria through electrostatic interaction, considered the main reason for their antibacterial activities. Here, we categorized these CαAMPs according to their charge, and to calculate the charge density; we divided the charge of each peptide by its corresponding length. To investigate the effect of charge among these categories, charge or charge density under each charge category was plotted against their corresponding minimum inhibitory concentration (MIC). Moreover, the effect of charge modification of some CαAMPs under specific charge categories in the context of MIC and hemolysis was also discussed. The information in this review will help us understand the antibacterial activity of accessible CαAMPs depending on each charge category across species. Additionally, this study suggests that designing novel functional antibacterial agents requires charge modification optimally.

Rice bran oil reduces organ-specific fat deposition, attenuates hyperlipidaemia and abnormal liver function in Long Evans rats with high fat intake

@#Introduction: High-calorie diets, particularly the quality of dietary fats, are regarded as an independent risk factor for developing obesity, hyperlipidaemia, and liver diseases. The present study examined the impact of rice bran oil (RBO) on organ-specific fat deposition, lipid profile, and liver function enzymes in Long Evans rats. Methods: Long Evans rats (n=24) were fed for six weeks with a controlled high-fat diet (HFD) to induce hyperlipidaemia and abnormal liver function. Rats were then divided into two groups: one group continued feeding on HFD, and the other group was fed with a RBO diet, replacing the fat source. After six weeks of feeding, six rats from each group were sacrificed and required analytical tests were performed. The remaining obese rats (n=12) were divided into continued HFD and RBO diet, and after sacrificing, essential analytical tests were done. Results: RBO feeding to hyperlipidaemic rats for six weeks significantly reduced brown adipose tissue, abdominal adipose tissue, epididymal adipose tissue, and liver fat compared to continuing HFD group (p<0.05). Similarly, serum levels of total cholesterol, triacylglycerides, and low-density lipoprotein cholesterol were all decreased, whereas high-density lipoprotein cholesterol increased in response to RBO compared to HFD (p<0.05). Additionally, rats fed with RBO showed reduced alanine aminotransferase, aspartate aminotransferase, and gamma-glutamyl transferase levels when compared with continuing HFD-fed rats (p<0.05). Conclusion: These findings suggest that RBO supports the reduction of fat storage from major fat depots, controls lipid profile, and restores healthy liver functions in rats.

Macrophage-Dependent Interleukin-6-Production and Inhibition of IK Contributes to Acquired QT Prolongation in Lipotoxic Guinea Pig Heart.

In the heart, the delayed rectifier K current, IK, composed of the rapid (IKr) and slow (IKs) components contributes prominently to normal cardiac repolarization. In lipotoxicity, chronic elevation of pro-inflammatory cytokines may remodel IK, elevating the risk for ventricular arrythmias and sudden cardiac death. We investigated whether and how the pro-inflammatory interleukin-6 altered IK in the heart, using electrophysiology to evaluate changes in IK in adult guinea pig ventricular myocytes. We found that palmitic acid (a potent inducer of lipotoxicity), induced a rapid (~24 h) and significant increase in IL-6 in RAW264.7 cells. PA-diet fed guinea pigs displayed a severely prolonged QT interval when compared to low-fat diet fed controls. Exposure to isoproterenol induced torsade de pointes, and ventricular fibrillation in lipotoxic guinea pigs. Pre-exposure to IL-6 with the soluble IL-6 receptor produced a profound depression of IKr and IKs densities, prolonged action potential duration, and impaired mitochondrial ATP production. Only with the inhibition of IKr did a proarrhythmic phenotype of IKs depression emerge, manifested as a further prolongation of action potential duration and QT interval. Our data offer unique mechanistic insights with implications for pathological QT interval in patients and vulnerability to fatal arrhythmias.

Predictors of black fungus fear during the COVID-19 pandemic among the Bangladeshi health workers: a cross-sectional study

BackgroundThe emergence of mucormycosis cases amid the COVID-19 pandemic; fear associated with mucormycosis may turn out to be a terrifying public health issue. This study aimed to assess the association between fear and insomnia status and other predictors of mucormycosis among Bangladeshi healthcare workers. MethodsFrom 25 May 2021 to 05 June 2021, a cross-sectional study was carried out among healthcare workers. A total of 422 healthcare workers participated in this study. A semi-structured online questionnaire was used for data collection during the COVID-19 pandemic, followed by convenient and snowball sampling methods. A multivariable linear regression model was fitted to assess the association between fear and insomnia status and other predictors of mucormycosis. ResultsThe results indicated that the respondents with insomnia status had a higher score of mucormycosis fear than not having insomnia ({beta} = 3.91, 95% CI: 2.49, 5.33, p <0.001), significantly. Alongside the increased knowledge score of mucormycosis, the average score of fear increased significantly({beta} = 0.35, 95% CI: 0.20, 0.50, p <0.001). The gender, profession, and death of friends and family members due to COVID-19 significantly affected mucormycosis fear score increment. ConclusionsThis is the first study that focused on assessing the association between mucormycosis fear and insomnia status among the health care workers so far. These study findings recommend emphasizing the mental health aspects and ensuring support to the healthcare workers to better tackle the ongoing public health crisis.

Association between preference and e-learning readiness among the Bangladeshi female nursing students in the Covid-19 pandemic: a cross-sectional study

BackgroundThe COVID-19 pandemic jeopardized the traditional academic learning calendars due to the closing of all educational institutions across the globe. To keep up with the flow of learning, most of the educational institutions shifted toward e-learning. However, the students e-learning preference for various subdomains of e-learning readiness did not identify, particularly among the female nursing students for a developing country like Bangladesh, where those domains pose serious challenges. ResultsA cross-sectional study was conducted among the female nursing students perceived e-learning readiness in subdomains of readiness; availability, technology use, self-confidence, and acceptance. The findings of the study revealed that the prevalence of preference for e-learning was 43.46%. The students did not prefer e-learning compared to prefer group has significantly less availability of technology ({beta} = -3.01, 95% CI: -4.46, -1.56), less use of technology ({beta} = - 3.08, 95% CI: -5.11, -1.06), less self-confidence ({beta} = -4.50, 95% CI: -7.02, -1.98), less acceptance ({beta} = -5.96, 95% CI: -7.76, -4.16) and less training need ({beta} = -1.86, 95% CI: -2.67, - 1.06). The age, degree, residence, parents highest education, having a single room, having any eye problems were significantly associated with the variation of availability of technology, use of technology, self-confidence, acceptance, and training need of e-learning. ConclusionsThe outcomes of the study could be helpful while developing an effective and productive e-learning infrastructure regarding the preparedness of nursing colleges for the continuation of academia in any adverse circumstances like the COVID-19 pandemic.

Challenges of Deep Learning Methods for COVID-19 Detection Using Public Datasets

A large number of studies in the past months have proposed deep learning-based Artificial Intelligence (AI) tools for automated detection of COVID-19 using publicly available datasets of Chest X-rays (CXRs) or CT scans for training and evaluation. Most of these studies report high accuracy when classifying COVID-19 patients from normal or other commonly occurring pneumonia cases. However, these results are often obtained on cross-validation studies without an independent test set coming from a separate dataset and have biases such as the two classes to be predicted come from two completely different datasets. In this work, we investigate potential overfitting and biases in such studies by designing different experimental setups within the available public data constraints and highlight the challenges and limitations of developing deep learning models with such datasets. We propose a deep learning architecture for COVID-19 classification that combines two very popular classification networks, ResNet and Xception, and use it to carry out the experiments to investigate challenges and limitations. The results show that the deep learning models can overestimate their performance due to biases in the experimental design and overfitting to the training dataset. We compare the proposed architecture to state-of-the-art methods utilizing an independent test set for evaluation, where some of the identified bias and overfitting issues are reduced. Although our proposed deep learning architecture gives the best performance with our best possible setup, we highlight the challenges in comparing and interpreting various deep learning algorithms results. While the deep learning-based methods using chest imaging data show promise in being helpful for clinical management and triage of COVID-19 patients, our experiments suggest that a larger, more comprehensive database with less bias is necessary for developing tools applicable in real clinical settings.

ReCoNet: Multi-level Preprocessing of Chest X-rays for COVID-19 Detection Using Convolutional Neural Networks

Life-threatening COVID-19 detection from radiomic features has become a dire need of the present time for infection control and socio-economic crisis management around the world. In this paper, a novel convolutional neural network (CNN) architecture, ReCoNet (residual image-based COVID-19 detection network), is proposed for COVID-19 detection. This is achieved from chest X-ray (CXR) images shedding light on the preprocessing task considered to be very useful for enhancing the COVID-19 fingerprints. The proposed modular architecture consists of a CNN-based multi-level preprocessing filter block in cascade with a multi-layer CNN-based feature extractor and a classification block. A multi-task learning loss function is adopted for optimization of the preprocessing block trained end-to-end with the rest of the proposed network. Additionally, a data augmentation technique is applied for boosting the network performance. The whole network when pre-trained end-to-end on the CheXpert open source dataset, and trained and tested with the COVIDx dataset of 15,134 original CXR images yielded an overall benchmark accuracy, sensitivity, and specificity of 97.48%, 96.39%, and 97.53%, respectively. The immense potential of ReCoNet may be exploited in clinics for rapid and safe detection of COVID-19 globally, in particular in the low and middle income countries where RT-PCR labs and/or kits are in a serious crisis.

Niclosamide reduces glucagon sensitivity via hepatic PKA inhibition in obese mice: Implications for glucose metabolism improvements in type 2 diabetes.

Type 2 diabetes (T2D) is a global pandemic. Currently, the drugs used to treat T2D improve hyperglycemic symptom of the disease but the underlying mechanism causing the high blood glucose levels have not been fully resolved. Recently published data showed that salt form of niclosamide improved glucose metabolism in high fat fed mice via mitochondrial uncoupling. However, based on our previous work we hypothesised that niclosamide might also improve glucose metabolism via inhibition of the glucagon signalling in liver in vivo. In this study, mice were fed either a chow or high fat diet containing two different formulations of niclosamide (niclosamide ethanolamine salt - NENS or niclosamide - Nic) for 10 weeks. We identified both forms of niclosamide significantly improved whole body glucose metabolism without altering total body weight or body composition, energy expenditure or insulin secretion or sensitivity. Our study provides evidence that inhibition of the glucagon signalling pathway contributes to the beneficial effects of niclosamide (NENS or Nic) on whole body glucose metabolism. In conclusion, our results suggest that the niclosamide could be a useful adjunctive therapeutic strategy to treat T2D, as hepatic glucose output is elevated in people with T2D and current drugs do not redress this adequately.