Antimicrobial resistance, particularly the emergence of resistant strains in fungal pathogens, has become a pressing global health concern. Antifungal peptides (AFPs) have shown great potential as a promising alternative therapeutic strategy due to their inherent antimicrobial properties and potential application in combating fungal infections. However, the identification of antifungal peptides using experimental approaches is time-consuming and costly. Hence, there is a demand to propose fast and accurate computational approaches to identifying AFPs. This paper introduces a novel multi-view feature learning (MVFL) model, called AFP-MVFL, for accurate AFP identification, utilizing multi-view feature learning. By integrating the sequential and physicochemical properties of amino acids and employing a multi-view approach, the AFP-MVFL model significantly enhances prediction accuracy. It achieves 97.9%, 98.4%, 0.98, and 0.96 in terms of accuracy, precision, F1 score, and Matthews correlation coefficient (MCC), respectively, outperforming previous studies found in the literature.
The ascendancy of coronavirus has become widespread all around the world. For the prevention of viral transmission, the pattern of disease is explored. Epidemiological modeling is a vital component of the research. These models assist in studying various aspects of infectious diseases, such as death, recovery, and infection rates. Coronavirus trends across several countries may analyze sufficiently using SIR, SEIR, and SIQR models. Across this study, we propose two modified versions of the SEIRD method for evaluating the transmission of this infectious disease in the South Asian countries, more precisely, in the south Asian subcontinent. The SEIRD model is updated further by fusing some new factors, namely, isolation for the suspected people and recovery and death of the people who are not under the coverage of healthcare schemes or reluctant to receive treatment for various catastrophes. We will investigate the influences of those ingredients on public health‐related issues. Finally, we will predict and display the infection scenario and relevant elements with the concluding remarks through the statistical analysis.
6 February 2026 in Current Research in Biotechnology
The aim of the work is to analyze the socio-economic and healthcare aspects that arise in the contemporary COVID-19 situation from Bangladesh perspective. We elaborately discuss the successive COVID-19 occurrences in Bangladesh with consequential information. The components associated with the COVID-19 commencement and treatment policy with corresponding features and their consequences are patently delineated. The effect of troublesome issues related to the treatment is detailed with supporting real-time data. We elucidate the applications of modern technologies advancement in epidemiological aspects and their existent compatibility in Bangladesh. We statistically analyze the real-time data through figurative and tabular approaches. Some relevant measures of central tendency and dispersion are utilized to explore the data structure and its observable specifications. For a clear manifestation, scores of the COVID-19 components are analyzed through the Box-Whisker plot. We have discovered that the gathered data exhibit features that are unsatisfactory for the normal distribution, are highly positively skewed, and are predominated by the earliest occurrences. Infections and deaths were initially lower than the global average, but they drastically rose in the first quarter of 2021 and persisted for the remainder of the year. Substantial preventive results were produced by the region-wisetime-worthy moves. In the fourth quarter of 2021, the infections and deaths noticeably decreased, and the number of recoveries was highly significant. In the middle of 2022, a lethal rise in infections was observed in Bangladesh and that was quickly stabilized, and the pandemic ingredients were under control. According to our assessment, some concluding remarks are made at the end of this work.
16 July 2024 in International Journal of Automation and Smart Technology
Heart disease, associated with Cardiovascular Disease (CVD), has become the leading global cause of mortality, claiming an estimated 17.9 million lives annually. Recognizing the preventable nature of nearly 90% of these cases, researchers have turned to data mining methodologies to aid healthcare professionals in early diagnosis. Machine learning improves operational efficiency. Early heart disease prediction will simplify patient management, reduce hospital admissions, and minimize healthcare costs. Beyond that, machine learning technologies improve accuracy, enabling better decision-making and efficient use of medical resources. Our research seeks to establish an effective assumption framework for predicting heart disease probabilities. The ultimate goal is to pinpoint the most accurate classification algorithm, which is crucial for distinguishing between normal and abnormal cases. Notably, our analysis highlights the efficacy of the XGBoost algorithm, boasting an impressive 99.90% accuracy. This discovery holds promise for advancing early detection strategies and mitigating the impact of heart-related conditions on global health.