A Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving.

Improving the ability of autonomous vehicles to accurately identify and follow lanes in various contexts is crucial. This project aims to provide a novel framework for optimizing a self-driving vehicle that can detect lanes and steer accordingly. A virtual sandbox environment was developed in Unity3D that provides a semi-automated procedural road and driving generation framework for a variety of road scenarios.

Isolation, characterization, and analysis of pure compounds from leaf extract for antibacterial, antidiabetic, cytotoxicity and phytotoxicity.

This research aims to isolate, characterize, and analyze pure compounds from leaf extract to investigate its antibacterial, antidiabetic, cytotoxic, and phytotoxic effects. Fresh leaves were collected, dried, and subjected to methanol extraction to obtain a crude extract. From the petroleum ether fraction (PEF) of this extract, three fractions-designated LM1, LM2, and LM3-were prepared using column chromatography.

UBL3 Interacts with PolyQ-Expanded Huntingtin Fragments and Modifies Their Intracellular Sorting.

Background/objectives: UBL3 (Ubiquitin-like 3) is a protein that plays a crucial role in post-translational modifications, particularly in regulating protein transport within small extracellular vesicles. While previous research has predominantly focused on its interactions with α-synuclein, this study investigates UBL3's role in Huntington's disease (HD). HD is characterized by movement disorders and cognitive impairments, with its pathogenesis linked to toxic, polyglutamine (polyQ)-expanded mutant huntingtin fragments (mHTT).

Occurrence, characteristics and distribution of microplastics in commercial marine fishes of the Bay of Bengal.

The study aimed to assess and characterize microplastics (MPs) in muscles, guts, and gills of six commercially important marine fish from the Bay of Bengal. FTIR was utilized to identify MP's polymer compositions. A total 7085 MPs identified, where tuna exhibited the highest count and Bombay duck had the lowest.

Marine natural compounds as potential CBP bromodomain inhibitors for treating cancer: an in-silico approach using molecular docking, ADMET, molecular dynamics simulations and MM-PBSA binding free energy calculations.

Unlabelled: The cAMP-responsive element binding protein (CREB) binding protein (CBP), a bromodomain-containing protein, engages with multiple transcription factors and enhances the activation of many genes. CBP bromodomain acts as an epigenetic reader and plays an important role in the CBP-chromatin interaction which makes it an important drug target for treating many diseases. Though inhibiting CBP bromodomain was reported to have great potential in cancer therapeutics, approved CBP bromodomain inhibitor is yet to come.

Adhesion Mechanics and Detachment Dynamics of Vanishing Surface Layers on Hydrogels.

Cross-linked hydrogel surfaces exhibit reduced stiffness when polymerized against polymeric hydrophobic surfaces. As such, these layers play a critical role in contact mechanics, particularly exhibiting strong relative adhesion with colloidal probes when the contact area is small. This prevents the use of continuum models of adhesive soft contact.

Predictive landslide susceptibility modeling in the southeastern hilly region of Bangladesh: application of machine learning algorithms in Khagrachari district.

Landslides pose a severe threat to people, buildings, and infrastructure. The rugged terrain of the Chattogram Hill Tract region in southeastern Bangladesh frequently experiences landslides, particularly during rainy seasons. This study provides a comparative analysis of innovative machine learning (ML) algorithms used for the purpose of landslide susceptibility (LS) mapping for the Khagrachari district of Bangladesh.

Comparison of RNN-LSTM, TFDF and stacking model approach for weather forecasting in Bangladesh using historical data from 1963 to 2022.

Forecasting the weather in an area characterized by erratic weather patterns and unpredictable climate change is a challenging endeavour. The weather is classified as a non-linear system since it is influenced by various factors that contribute to climate change, such as humidity, average temperature, sea level pressure, and rainfall. A reliable forecasting system is crucial in several industries, including transportation, agriculture, tourism, & development.

UBL3 overexpression enhances EV-mediated Achilles protein secretion in conditioned media of MDA-MB-231 cells.

Cancer cells communicate within the tumor microenvironment (TME) through extracellular vesicles (EVs), which act as crucial messengers in intercellular communication, transporting biomolecules to facilitate cancer progression. Ubiquitin-like 3 (UBL3) facilitates protein sorting into small EVs as a post-translational modifier. However, the effect of UBL3 overexpression in EV-mediated protein secretion has not been investigated yet.

Mitigating Sociodemographic Bias in Opioid Use Disorder Prediction: Fairness-Aware Machine Learning Framework.

Background: Opioid use disorder (OUD) is a critical public health crisis in the United States, affecting >5.5 million Americans in 2021. Machine learning has been used to predict patient risk of incident OUD.

Genomic characterization of carbapenemase-producing Enterobacterales from Dhaka food markets unveils the spread of high-risk antimicrobial-resistant clones and plasmids co-carrying and .

Background: The transmission of carbapenemase-producing Enterobacterales (CPE) in the external environment, especially through food, presents a significant public health risk.

Objectives: To investigate the prevalence and genetic characteristics of CPE in food markets of Dhaka, Bangladesh, using WGS.

Methods: CPE isolates were obtained from different food and water samples collected from food markets in the southern part of Dhaka, Bangladesh.

Zoonotic linkage and environmental contamination of Methicillin-resistant (MRSA) in dairy farms: A one health perspective.

Methicillin-Resistant (MRSA) is a ubiquitous public health challenge, with its prevalence in human, animal, and environmental interfaces posing significant concerns. This study aimed to characterize and detect the zoonotic linkages of MRSA within the cow-environment-human interfaces in dairy farms to address the One Health perspective. A comprehensive investigation, involving 636 samples (an equal number of raw milk and cow nasal swab samples, along with varying numbers of human nasal swab and environmental samples), revealed an overall MRSA prevalence of 13.

Alpha-Synuclein Interaction with UBL3 Is Upregulated by Microsomal Glutathione S-Transferase 3, Leading to Increased Extracellular Transport of the Alpha-Synuclein under Oxidative Stress.

Aberrant aggregation of misfolded alpha-synuclein (α-syn), a major pathological hallmark of related neurodegenerative diseases such as Parkinson's disease (PD), can translocate between cells. Ubiquitin-like 3 (UBL3) is a membrane-anchored ubiquitin-fold protein and post-translational modifier. UBL3 promotes protein sorting into small extracellular vesicles (sEVs) and thereby mediates intercellular communication.

Prediction and assessment of deleterious and disease causing nonsynonymous single nucleotide polymorphisms (nsSNPs) in human gene: An study.

In humans, gene family is involved in embryonic development and cancer progression. The (Forkhead box protein P4) gene belongs to this gene family. gene plays a crucial role in oncogenesis.

Responsible AI for cardiovascular disease detection: Towards a privacy-preserving and interpretable model.

Background And Objective: Cardiovascular disease (CD) is a major global health concern, affecting millions with symptoms like fatigue and chest discomfort. Timely identification is crucial due to its significant contribution to global mortality. In healthcare, artificial intelligence (AI) holds promise for advancing disease risk assessment and treatment outcome prediction.

Availability of Hypertension and Diabetes Mellitus Care Services at Subdistrict Level in Bangladesh.

Background: In Bangladesh, the rapid rise of noncommunicable diseases (NCDs) has become a significant public health concern. This study assesses the readiness of hypertension (HTN)- and diabetes mellitus-related services at primary health-care facilities in Northeast Bangladesh.

Methodology: A cross-sectional survey using a semi-structured interview was conducted between April 2021 and May 2021 among 51 public primary health-care facility staff (upazila health complexes [UHCs]).

An explainable machine learning framework for predicting the risk of buprenorphine treatment discontinuation for opioid use disorder among commercially insured individuals.

Objectives: Buprenorphine is an effective evidence-based medication for opioid use disorder (OUD). Yet premature discontinuation undermines treatment effectiveness, increasing the risk of mortality and overdose. We developed and evaluated a machine learning (ML) framework for predicting buprenorphine care discontinuity within 12 months following treatment initiation.

Effects of Commercial Probiotics on the Growth Performance, Intestinal Microbiota and Intestinal Histomorphology of Nile Tilapia () Reared in Biofloc Technology (BFT).

Though different types of commercial probiotics are supplemented in biofloc technology (BFT), very little information is available on their effects on the farmed fish. Therefore, this study focused on evaluating the effects of three most commonly used commercial probiotics on the growth performance, intestinal histomorphology, and intestinal microbiota of Nile tilapia () reared in BFT. Tilapia fry, with an average weight of 3.

In silico functional, structural and pathogenicity analysis of missense single nucleotide polymorphisms in human MCM6 gene.

Single nucleotide polymorphisms (SNPs) are one of the most common determinants and potential biomarkers of human disease pathogenesis. SNPs could alter amino acid residues, leading to the loss of structural and functional integrity of the encoded protein. In humans, members of the minichromosome maintenance (MCM) family play a vital role in cell proliferation and have a significant impact on tumorigenesis.

Hazard-mapping and health risk analysis of iron and arsenic contamination in the groundwater of Sylhet district.

This study investigates groundwater contamination by arsenic and iron and its health implications within the Sylhet district in Bangladesh. Utilizing geographic information system (GIS) and inverse distance weighting (IDW) methods, hazard maps have been developed to evaluate contamination risk across various upazilas. The findings show significant arsenic and iron pollution, particularly in the northwestern part of the district.

Comparison of hypoxia- and hyperoxia-induced alteration of epigene expression pattern in lungs of Pleurodeles waltl and Mus musculus.

Epigenetics is an emerging field of research because of its involvement in susceptibility to diseases and aging. Hypoxia and hyperoxia are known to be involved widely in various pathophysiologies. Here, we compared the differential epigene expression pattern between Pleurodeles waltl and Mus musculus (commonly known as Iberian ribbed newt and mouse, respectively) exposed to hypoxia and hyperoxia.