Search

Chronic kidney diseases (CKDs) are a significant public health issue with potential for severe complications such as hypertension, anemia, and renal failure. Timely diagnosis is crucial for effective management. Leveraging machine learning within healthcare offers promising advancements in predictive diagnostics. In this paper, we developed a machine learning-based kidney diseases prediction (ML‐CKDP) model with dual objectives: to enhance dataset preprocessing for CKD classification and to develop a web-based application for CKD prediction. The proposed model involves a comprehensive data preprocessing protocol, converting categorical variables to numerical values, imputing missing data, and normalizing via Min-Max scaling. Feature selection is executed using a variety of techniques including Correlation, Chi-Square, Variance Threshold, Recursive Feature Elimination, Sequential Forward Selection, Lasso Regression, and Ridge Regression to refine the datasets. The model employs seven classifiers: Random Forest (RF), AdaBoost (AdaB), Gradient Boosting (GB), XgBoost (XgB), Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT), to predict CKDs. The effectiveness of the models is assessed by measuring their accuracy, analyzing confusion matrix statistics, and calculating the Area Under the Curve (AUC) specifically for the classification of positive cases. Random Forest (RF) and AdaBoost (AdaB) achieve a 100% accuracy rate, evident across various validation methods including data splits of 70:30, 80:20, and K-Fold set to 10 and 15. RF and AdaB consistently reach perfect AUC scores of 100% across multiple datasets, under different splitting ratios. Moreover, Naive Bayes (NB) stands out for its efficiency, recording the lowest training and testing times across all datasets and split ratios. Additionally, we present a real-time web-based application to operationalize the model, enhancing accessibility for healthcare practitioners and stakeholders.Web app link: https://rajib-research-kedney-diseases-prediction.onrender.com/

DNA methylation is an epigenetic modification that plays a crucial role in various biological processes, including gene expression regulation, cell differentiation, and the development of diseases such as cancer. Identifying DNA methylation patterns is essential for understanding its functional implications. Traditional experimental methods for detecting DNA methylation are costly, time-consuming, and inefficient for analyzing large-scale sequencing data. In this research, we explore the application of machine learning techniques to accurately identify DNA methylation sites. Our research aims to develop a Particle Swarm Optimization-Assisted Multilayer Ensemble Model (PSO-MEM) with several significant contributions. These include extracting semantic features from genetic sequences, optimizing feature dimensions to reduce classification errors, developing a multilayer dynamic approach that transfers learned information between layers during classification, and incorporating ensemble techniques for improved prediction and optimal results. To evaluate the performance of our proposed model, we compare it with existing models using eight publicly available datasets. The results demonstrate the efficacy of our approach, with AUC values of 91.99%, 92.80%, 90.28%, 91.03%, 93.09%, 90.79%, 90.68%, and 91.88% for the C. elegans, D. melanogaster, A. thaliana, E. coli, G. subterraneus, G. pickeringi, F. vesca, and R. chinensis datasets, respectively. The results highlight the potential of machine learning techniques for efficient and reliable identification of DNA methylation sites in large-scale genomic data, facilitating advancements in understanding epigenetic modifications and their functional implications.

ABSTRACT: Background: Trayodashang guggulu (TG) is a compound Ayurvedic formulation used in Indian traditional system of medicine for the treatment of various inflammatory conditions like arthritis and associated pain.Purpose:To study the analgesic and anti-inflammatory effects of trayodashang guggulu.Methods: Trayodashang guggulu (TG) was standardized as per standard procedures and TLC profile was carried as per Ayurvedic Pharmacopoeia of India and LC-MS analysis was done to identify its bioactive constituents. Trayodashang guggulu was suspended in water and administered orally at 270 and 540 mg/kg dose for evaluating pain and inflammation in rats. Analgesic activity was assessed by Eddy's hot plate, tail immersion and formalin-induced pain models while anti-inflammatory activity was assessed by carrageenan and formalin-induced inflammation models. Further, the mechanism of anti-inflammatory action is predicted through various in silico methods like molecular docking and dynamics studies using AutodockVina and AMBER, respectively.Results: TG was found compliant as per pharmacopoeial standards. TG (270 and 540 mg/kg, orally) did not cause significant reduction in pain in centrally acting pain models i.e. Eddy's hot plate and tail immersion tests as like Pentazocin (10 mg/kg). In formalin-induced pain model, TG (270 and 540 mg/kg, orally) significantly decreased both flinching and licking pain responses in early and late phase while indomethacin (10 mg/kg) only affected late phase flinching and licking. Further, TG showed significant time-dependent reduction in formalin and carrageenan-induced inflammation as compared to vehicle control. Indomethacin (10 mg/kg), standard drug also showed significant reduction in pain and inflammation. LC-MS analysis revealed the presence of 17 phytoconstituents in TG. Further, in silico studies revealed that some of the identified phytochemicals may have inhibitory activity against COX-2 enzyme and the synergistic effects due to multi components may be responsible for the anti-inflammatory properties of TG.Conclusion: In conclusion, trayodashang guggulu inhibited the inflammatory pain as well as showed anti-inflammatory activity in rats. The effect may be attributed to the presence of anti-inflammatory phytoconstituents through the inhibition of anti-inflammatory enzymes like COX-2. The study further validates its traditional use in various painful inflammatory conditions.

Objective: Various studies have shown racial differences in adult cardiac chamber measurements by echocardiography. There is lack of any large scale data from India regarding the echocardiographic chamber measurements in cardiologically healthy individuals. In this study we present the normal reference values of echocardiographic chamber dimensions in young eastern Indian adults and compare it with the data in present guidelines and recent studies involving Indian subjects. Methods: This study was performed on 1377 healthy adults aged 18–35 years. Standard transthoracic echocardiographies were performed to obtain basic measurements. All measurements were indexed to body surface area. Results: The mean maximal aortic valve cusp separation (ACS) and indexed ACS were significantly more in females (p = 0.002, p = 0.03). Mean left ventricular (LV) ejection fraction (LVEF) and LV fractional shortening were marginally higher in females. Upper normal reference limit of LV end diastolic dimension (LVEdD) is slightly more for males. Comparing to ASE data, LVEdD, LV end systolic dimension, LV end diastolic volume, indexed LV end systolic volume, left atrial anteroposterior dimension, aortic root dimension and right ventricle outflow diameter were significantly lower in study population while LVEF was significantly higher (p

The inhibition of retinal ischemia-induced damage by post-ischemic prothymosin alpha (ProTα) was not affected in toll-like receptor 4 knockout (TLR4−/−) mice but blocked by the pretreatment with antibody against F0/F1 ATPase α- or β-subunit, novel candidate for ProTα-receptor. In addition to the previous observation of ProTα-induced ATP release from cells, the present study showed a ProTα-induced enhancement of ATP hydrolysis activity of recombinant ATP5A1/5B complex. As the protection of retinal function by post-ischemic ProTα was abolished by anti-P2Y12 antibody, the activation of F0/F1 ATPase and subsequent P2Y12 receptor system may play roles in beneficial actions by post-ischemic ProTα.

Tuberculosis (TB) continuously poses a major public health concern around the globe, with a mounting death toll of approximately 1.4 million in 2019. Reduced bioavailability, elevated toxicity, increased side effects, and resistance of multiple first-line and second-line TB medications, including isoniazid, ethionamide necessitate studies of new drugs. The method of computational biology and bioinformatics approach allows virtual screening of a large number of drugs, reduces growing side effects of medications, and predicts potential drug resistance over time. In this study, we have analyzed fifty small molecules with antituberculosis properties using in silico approach including molecular docking, drug-likeness assessment, ADMET (absorption, distribution, metabolism, excretion, toxicity) profile evaluation, P450 site of metabolism prediction, and molecular dynamics simulation. Among those fifty compounds, 3-[3-(4-Fluorophenyl)-1,2,4-oxadiazol-5-yl]-N-(2-methylphenyl) piperidine-1-carboxamide (C22) and 5-(4-Ethyl-phenyl)-2-(1H-tetrazol-5-ylmethyl)-2H-tetrazole (C29) were found to pass the two-step molecular docking, P450 site of metabolism prediction and pharmacokinetics analysis successfully. Their binding stability for target proteins has been evaluated through root mean square deviation and root mean square fluctuation, Radius of gyration analysis from 10 ns Molecular Dynamics Simulation (MDS). Our identified drugs (C22 and C29) performed better than the control drugs (Isoniazid, Ethionamide) regarding binding affinity and molecular stability with the regulatory proteins (InhA, EthR) of Mycobacterium tuberculosis. The study proposed these compounds as effective therapeutic agents for Tuberculosis drug discovery, but further in vitro and in vivo testing are needed to substantiate their potential as novel drugs and modes of action.

In this study, an isolated yeast strain AKP1 was selected (out of 10 isolates) on the basis of the cumulative probiotic score. Genotypic characterization confirmed that it was a Saccharomyces cerevisiae. Gastroprotective effect of AKP1 was evaluated by cold-induced gastric ulcer model in rats. Prior supplementation of AKP1 along with the food led to significant reduction of the cold-induced gastric lesion in stomach. The histological study clearly showed that the mucosal columnar epithelial cells of the stomach were protected from cold injury. The relative expressions of some inflammatory marker genes such as up-regulation of IL-10 and down-regulation of IL-12, IFN-γ, IFN-λ of gastric mucosa also supported the anti-inflammatory activity of AKP1. Therefore, the newly isolated yeast strain Saccharomyces cerevisiae AKP1 might be a novel candidate of probiotic with an anti-ulcerogenic potential and can be used as a therapeutic component to prevent this widespread disease.

Cardiovascular disease is defined as a set of conditions related to the disorder of the heart and blood vessels. Predicting and diagnosing cardiovascular disease is significant to ensure the appropriate treatment of this disease. Machine learning approaches are generally utilized to automatically detect the hidden patterns in vast amounts of data without human intervention. In the early stage of cardiovascular disease, a machine learning model can aid physicians in making the right decision about the medication. This research aims to develop an intelligent agent to predict cardiovascular disease to investigate what steps should be taken before any untoward incident occurs. This paper proposes an ensemble method-based multilayer dynamic system (MLDS) that can improve its current knowledge in every layer. The proposed model applies Correlation Attribute Evaluator (CAE), Gain Ratio Attribute Evaluator (GRAE), Information Gain Attribute Evaluator (IGAE), Lasso, and Extra Trees classifier (ETC) for feature selection. Finally, Random Forest (RF), Naïve Bayes (NB), and Gradient Boosting (GB) classifiers combinedly construct the ensemble method for classification in the model. The K Nearest Neighbor (KNN) algorithm is applied to find the test data's neighborhood data points while the base classifiers mentioned are failed to classify correctly in any layer. To test the proposed model's efficiency, we have used a realistic dataset (70,000 instances) collected from Kaggle. The proposed model has achieved 88.84%, 89.44%, 91.56%, 92.72%, and 94.16% accuracy based on the train and test data's different splitting ratios (50:50, 60:40, 70:30, 80:20, and 87.5:12.5). Our proposed model has achieved a 0.94 AUC value. AUC = 0.94 means it has a 94% probability of correctly classifying positive and negative classes, Whereas the splitting ratio is 87.5:12.5. The Cleveland, Hungarian, and Cleveland-Hungary-Switzerland-Long Beach datasets have also been applied to train the model, and the model achieved 98.88%, 99.53%, 99.98%, 98.36%, 96.66%, 97.77%, 99.56, and 94.37% accuracy depending on the different splitting ratios of these datasets. The proposed model has been compared to five other models, indicating that the proposed model can effectively predict cardiovascular disease.

Prothymosin alpha (ProTα) suppresses stress-induced necrosis of cultured cortical neurons. As neuroprotection alone could not explain the long-lasting protective actions against cerebral ischemia by ProTα, we further examined whether ProTα, in addition to neuroprotective effects, has other anti-ischemic activities. When recombinant mouse ProTα (rmProTα) at 0.3 mg/kg was intravenously (i.v.) given 2 h after the start of tMCAO, all mice survived for more than 14 days. In evaluation of CD31- and tomato lectin-labeling as well as IgG and Evans blue leakage, rmProTα treatment (0.1 mg/kg) largely blocked ischemia-induced vascular damages. Therefore, rmProTα has novel beneficial effects against ischemia-induced brain damage through vascular mechanisms.