MCAMEF-BERT: an efficient deep learning method for RNA N7-methylguanosine site prediction via multi-branch feature integration.

Accurate identification of N7-methylguanosine (m7G) modification sites plays a critical role in uncovering the regulatory mechanisms of various biological processes, including human development, tumor initiation, and progression. However, existing prediction methods still suffer from limited representational power, redundant feature fusion, insufficient utilization of biological prior knowledge, and poor interpretability. In this study, we propose a novel deep learning model named MCAMEF-BERT.

Protective effects of Yiqi Huoxue Huatan formula on atherosclerosis: An in vivo and in vitro study.

Atherosclerosis (AS) is a significant pathological contributor to cardiovascular disease, marked by high rates of death and illness globally. Yiqi Huoxue Huatan formula (YHH), a Chinese traditional decoction, has been clinically validated as effective for patients with AS; however, its underlying mechanisms remain partially unexplained. The goal of this research is to understand the protective effects of YHH against AS and the mechanisms involved.

Defective states of Hermite-Gaussian modes for long-distance image transmission and high-capacity encoding.

Structured light brings a breakthrough in information capacity carried by the laser field, finding an ideal utility in optical information transmission. Advancements in optical intensity-based imaging have facilitated the use of structured light for simple information enconding and decoding. Here, we propose a method for extremely high-capacity information encoding, as well as image direct transmission, by modulating the structured light to defective states.

Cadmium exposure and advanced cardiovascular-kidney-metabolic syndrome: An integrated multi-organ perspective based on epidemiology and adverse outcome pathways.

While metal exposures are linked to cardiovascular and renal diseases, their role in cardiorenal comorbidity remains poorly understood. Using the American Heart Association's Cardiovascular-Kidney-Metabolic Syndrome (CKM syndrome) framework, we combined population epidemiology and Adverse Outcome Pathway (AOP) analysis to explore how cadmium exposure influences CKM progression and advanced-stage outcomes. Data from 5865 adults aged 30-79 years in the National Health and Nutrition Examination Surveys (NHANES) were analyzed to investigate serum metal exposure patterns and CKM syndrome progression.

ACP-ESM2: Enhancing Anticancer Peptide Prediction With Pre-Trained Protein Language Models.

Anticancer peptide (ACP) are short peptides with anti-cancer properties that have generated increasing attention in recent years due to their low toxicity, minimal side effects, and their ability to precisely target and kill cancer cells. Traditionally, identifying ACP has relied on experimental methods, which are time-consuming and labor-intensive. While deep learning-based prediction methods have made significant progress, there is still room for improvement in achieving optimal performance.

Autoencoder-Transformed Transcriptome Improves Genotype-Phenotype Association Studies.

Transcriptome-wide association study (TWAS) is an emerging model leveraging gene expressions to direct genotype-phenotype association mapping. A key component in TWAS is the prediction of gene expressions; and many statistical approaches have been developed along this line. However, a problem is that many genes have low expression heritability, limiting the performance of any predictive model.

Loss of C-Terminal Coiled-Coil Domains in SDCCAG8 Impairs Centriolar Satellites and Causes Defective Sperm Flagellum Biogenesis and Male Fertility.

Sperm flagellum defects are tightly associated with male infertility. Centriolar satellites are small multiprotein complexes that recruit satellite proteins to the centrosome and play an essential role in sperm flagellum biogenesis, but the precise mechanisms underlying this role remain unclear. (), which encodes a protein containing eight coiled-coil (CC) domains, has been associated with syndromic ciliopathies and male infertility.

Electrically tunable plasmonic meta-grating on thin film lithium niobate.

Leveraging lithium niobate's electro-optic properties, bound states in the continuum (BICs) offer promising advancements for low-power, high-performance photonic devices. In this study, we present a novel spatial light modulator based on a lithium niobate (LN) with gold nanograting that exploits BIC mechanism to achieve high quality (Q) factor resonances. By intentionally breaking the symmetry of the gold meta-grating, a true BIC mode is transformed into quasi-BIC, to enable strong field confinement and enhanced light-matter interactions.

DiffusionST: a deep generative diffusion model-based framework for enhancing spatial transcriptomics data quality and identifying spatial domains.

Recent advancements in spatial transcriptomics (ST) technology have generated substantial volumes of spatial transcriptome data. However, the quality of this data is often compromised due to the limitations of current sequencing technologies. To address this issue, DiffusionST proposes a method for imputing ST data and clustering the imputed data.

Efficient colorimetric assay promotes the virtual screen of granzyme B inhibitors.

Granzyme B (GrmB) is a key biomarker for immune activation and tumor cell eradication, as well as the therapeutic target for autoimmune and chronic inflammatory disorders. Recent bioinformatic methods have been extensively applied to discover new sites of action, thereby enabling the screening of corresponding inhibitors. However, verification of silico predictions requires efficient experimental tests in vitro, and this work aims to provide an efficient assay method that enables the colorimetric detection of GrmB activity with high specificity and sensitivity (0.

EDNTOM: An Ensemble Learning and Weight Mechanism-Based Nanopore Methylation Detection Tool.

DNA methylation is an epigenetic modification that plays a crucial role in genome stability and cellular specialization, essential for maintaining normal cellular function and development, also a manifestation indicator of some diseases. Various tools have been proposed for methylation detection, typically leveraging a third-generation sequencing technology called nanopore sequencing, which provides more accurate DNA sequencing data. However, existing tools have their own limitations and advantages in terms of computational resources and information processing, without achieving a good balance.

Transcatheter Management of Iatrogenic Right Ventricular Perforation During Salvage Coronary Intervention: A Novel Dual-Closure Strategy.

This case report describes the emergency management of a 70-year-old man who developed acute cardiac tamponade owing to right coronary artery rupture during chronic total occlusion percutaneous coronary intervention. Despite successful covered stent deployment and pericardiocentesis, iatrogenic right ventricular perforation occurred owing to a misplaced pericardial sheath. A novel dual-device strategy combining ProGlide and StarClose (Abbott) SE vascular closure devices achieved complete hemostasis under real-time transthoracic echocardiography and digital subtraction angiography.

Phase transition and in-plane anisotropy of GeAs under high pressure.

GeAs exhibits excellent chemical stability and high in-plane anisotropy under ambient conditions. Pressure is one effective approach to regulate structures or properties of two-dimensional materials. In this work, the high-pressure effect on the phase transition and in-plane anisotropic properties is investigated for GeAs using Raman spectroscopy, infrared spectroscopy, high-pressure resistance measurement, and density functional theory calculations.

Endoplasmic reticulum-targeted strategies for programmed cell death in cancer therapy: Approaches and prospects.

The endoplasmic reticulum (ER) plays a dual role in cancer biology, functioning both to preserve cellular homeostasis and to facilitate pathological progression. Rapidly proliferating cancer cells, which exhibit heightened metabolic activity, frequently experience ER stress that activates the unfolded protein response (UPR), a mechanism that promotes cellular adaptation and survival. However, when ER stress is prolonged or excessive, it can shift the balance toward programmed cell death (PCD), including apoptosis, autophagy, ferroptosis, pyroptosis, and necroptosis.

m5U-HybridNet: Integrating an RNA Foundation Model with CNN Features for Accurate Prediction of 5-Methyluridine Modification Sites.

The 5-methyluridine (m5U) modification in RNA is vital for numerous biological processes, making its precise identification a key focus in computational biology. However, traditional wet-lab detection methods are cumbersome and time-consuming, whereas existing machine learning and deep learning computational prediction models still have room for improvement. Consequently, this study introduces m5U-HybridNet, an innovative framework that strategically integrates an RNA foundation model (RNA-FM) for deep semantic feature extraction with convolutional neural network-derived characteristics, attaining unparalleled success in identifying RNA m5U modification sites.

Blood pressure change patterns during pregnancy and neurodevelopment trajectories in early childhood: A birth cohort study.

Background: The impact of maternal blood pressure (BP) changes during pregnancy on offspring's neurodevelopment has been understudied. We investigated the associations between maternal BP change patterns and neurodevelopmental trajectories in children.

Methods: We included 2084 mother-child pairs from an ongoing birth cohort study launched in 2018 in Shenzhen, China.

Exposure to ambient air pollution over developmental stages induced neurodevelopmental impairment in mice offspring via microbiome-gut-brain axis.

Exposure to air pollution has been increasingly recognized as a risk factor for neurodevelopmental disorders, and gut microbiome may play a critical role. However, current evidence still remains scarce. In the present study, mice were exposed to real-time ambient air pollution from conception through young adulthood, with neurobehavioral performance and gut microbiome being assessed across different developmental stages.

RMDNet: RNA-aware dung beetle optimization-based multi-branch integration network for RNA-protein binding sites prediction.

RNA-binding proteins (RBPs) play crucial roles in gene regulation. Their dysregulation has been increasingly linked to neurodegenerative diseases, liver cancer, and lung cancer. Although experimental methods like CLIP-seq accurately identify RNA-protein binding sites, they are time-consuming and costly.

Deep Learning in Antimicrobial Peptide Prediction.

Antimicrobial peptides (AMPs) have garnered significant attention from researchers as effective alternatives to antibiotics. In recent years, deep learning has demonstrated unique advantages in AMP prediction, surpassing traditional machine learning methods and offering new avenues to address the issue of antibiotic resistance. This review introduces the research foundations of deep learning in AMP prediction, covering data set status, processing methods, and representation learning approaches.

FusionMVSA: Multi-View Fusion Strategy with Self-Attention for Enhancing Drug Recommendation.

Leveraging the wealth of biomedical data available, we can derive insights into the relationships between biological entities from various angles. This underscores the complexity and significance of developing a dynamic approach for integrating data from multiple sources, a critical endeavor in drug recommendation. In this study, we introduce an innovative deep learning approach termed "Multi-View Fusion Strategy with Self-Attention" (FusionMVSA), designed to predict associations between drugs and diseases.

Early-life exposure to tobacco, inflammation, and risk of rheumatic diseases: a prospective cohort study.

Background: Tobacco smoke exposure was associated with inflammation and adverse health outcomes. However, the impact of early-life tobacco exposure on rheumatic diseases, including rheumatoid arthritis, osteoarthritis, gout, and spondyloarthritis, and the potential modifying role of inflammation are unclear.

Methods: A prospective analysis of over 200 000 participants without rheumatic diseases at baseline in the UK Biobank was conducted.

Multi-scale fusion semantic enhancement network for medical image segmentation.

The application of sophisticated computer vision techniques for medical image segmentation (MIS) plays a vital role in clinical diagnosis and treatment. Although Transformer-based models are effective at capturing global context, they are often ineffective at dealing with local feature dependencies. In order to improve this problem, we design a Multi-scale Fusion and Semantic Enhancement Network (MFSE-Net) for endoscopic image segmentation, which aims to capture global information and enhance detailed information.

High-Performance Electrochromic Energy Storage Devices Based on Hexagonal WO and SnO/PB Composite Films.

Electrochromic devices have garnered significant interest owing to their promising applications in smart multifunctional electrochromic energy storage systems (EESDs) and their emerging next-generation electronic technologies. Tungsten oxide (WO), possessing both electrochromic and pseudocapacitive characteristics, offers great potential for developing multifunctional devices with enhanced performance. However, achieving an efficient and straightforward synthesis of WO electrochromic films, while simultaneously ensuring high coloration efficiency and energy storage capability, remains a significant challenge.

Construction of Symmetric Flexible Electrochromic and Rechargeable Supercapacitors Based on a 1,3,6,8-Pyrenetetrasulfonic Acid Tetrasodium Salt-Loaded Polyaniline Nanostructured Film.

Electrochromic supercapacitors (ECSCs), which visually indicate their operating status through color changes, have attracted considerable attention in the field of wearable electronics. The conductive polymer polyaniline (PANI) shows great potential for integrated intelligent devices by combining bi-functional electrochromic spectral modulation and energy storage capabilities. In this work, a microsphere-like structured PANI-based composite film was fabricated on a porous Au/nylon 66 electrode via a one-step electrochemical copolymerization process, using 1,3,6,8-pyrenetetrasulfonic acid tetrasodium salt (PTSA) as both the dopant and cross-linking agent for the PANI backbone, serving as the ECSC electrode.