Search Results (16,198)

Cold-active cellulases are highly desirable for temperature-sensitive biomass valorization and food processing, yet they remain scarce in conventional industrial fungal platforms. In this study, a novel cold-induced cellobiohydrolase, VvCBHI-II, was mined from the mushroom Volvariella volvacea and successfully engineered into the industrial workhorse Trichoderma reesei via site-specific homologous replacement. Structural homology modeling revealed that the substitution of the flexible B3 loop with a β-sheet creates a more open substrate-binding cleft in VvCBHI-II. Consequently, the purified VvCBHI-II exhibited robust endoglucanase-like characteristics with superior catalytic efficiency on amorphous cellulose. At 10 °C, the engineered cellulase complex demonstrated an 8.1-fold increase in filter paper activity compared to the wild-type strain. Mechanistic structural analyses indicated that the open cleft architecture elongates and weakens the hydrogen-bonding network with the cellobiose product, facilitating rapid product dissociation and alleviating severe cold-induced product inhibition. In practical applications, the engineered cold-active enzyme complex exhibited an exceptional saccharification capacity on natural pear pomace at 10 °C. Furthermore, when applied to simulated fruit juice processing, it significantly maximized the extraction yield, elevated the sweetness response, and substantially mitigated undesirable bitterness and astringency. This study elucidates the structural-functional paradigm of cold-adapted cellobiohydrolases and provides a promising strategy for formulating highly efficient, energy-saving biocatalysts for the food and biorefinery industries. Full article

Deep learning is increasingly integrated into oral rehabilitation workflows, particularly in implant planning, prosthodontic design automation, and peri-implant diagnosis. However, reported performance is heterogeneous and difficult to compare across tasks, modalities, and validation designs. The goal of this study was to critically analyze deep learning architecture families applied to oral rehabilitation and to provide task-driven selection guidance supported by an evidence table reporting dataset characteristics, validation strategy, and performance metrics. A focused narrative review was conducted using transparent, database-specific search criteria (final n = 10 included studies), emphasizing implant planning (cone–beam computed tomography [CBCT]-based segmentation), prosthodontic design (intraoral scan [IOS]/mesh inputs), and peri-implant diagnosis (periapical/panoramic radiographs). Evidence certainty for each clinical task was assessed using GRADE-informed ratings (High/Moderate/Low/Very Low). Extracted variables included clinical task, imaging modality, dataset size, architecture, validation strategy (internal vs. internal + external), split level, ground truth protocol, and performance metrics. A structured computational and hardware feasibility analysis was conducted for each architecture family to support real-world deployment planning. Encoder–decoder networks (U-Net/nnU-Net) dominate CBCT segmentation for implant planning, while detection architectures (Faster R-CNN, YOLO) support implant localization and peri-implant assessment on radiographs. Generative models (3D GANs, transformer-based point-to-mesh networks) enable crown design from three-dimensional scans. Hybrid CNN–Transformer architectures show promise for multimodal CBCT–IOS fusion, though direct evidence from the included studies remains limited to a single study. External validation remains uncommon yet essential given the risk of domain shift. In conclusion, architecture selection should be anchored to task geometry (2D vs. 3D), artifact burden, and required clinical output type. Reporting standards should prioritize dataset transparency, validation rigor, multi-center external testing, and uncertainty-aware outputs. Full article

Acute Lymphoblastic Leukemia (ALL) is a highly prevalent hematological malignancy, especially in children, for whom precise and prompt subtype identification is essential to establish suitable treatment protocols. Current deep learning-based computer-aided diagnosis (CAD) methods for identifying ALL are hindered by numerous drawbacks, such as a dependence on solely spatial feature depictions, elevated feature dimensions, computationally extensive deep learning architectures, inadequate multi-layer feature utilization, and poor interpretability. This paper introduces LUMINA-Net, a custom, lightweight, and interpretable deep learning CAD for the automated identification and subtype diagnosis of ALL using microscopic blood smear pictures. LUMINA-Net makes four principal contributions: first, it integrates a self-attention module within a lightweight custom Convolution Neural Network (CNN) to effectively capture long-range spatial relationships across clinically pertinent cytological patterns while preserving a compact design. Second, it employs a Discrete Wavelet Transform (DWT)-based wavelet pooling layer that decreases feature dimensions by up to 96.875% while enhancing the obtained depictions with spatial-spectral information. Third, it utilizes a multi-layer feature fusion strategy that combines wavelet-pooled features from two deep layers with a third fully connected layer to create a discriminating multi-scale feature vector. Fourth, it incorporates Gradient-weighted Class Activation Mapping as a dedicated explainability process to furnish clinicians with apparent visual explanations for each classification decision. Withoit the need for image enhancement or segmentation preprocessing, LUMINA-Net outperforms the competing state-of-the-art methods on the same dataset, achieving a peak accuracy of 99.51%, specificity of 99.84%, and sensitivity of 99.51% on the publicly available Kaggle ALL dataset. This demonstrates that LUMINA-Net has the potential to be a dependable, effective, and clinically interpretable CAD tool for ALL diagnosis. Full article

Folic acid, an essential vitamin for human health, plays a crucial role in maintaining intestinal homeostasis and functional stability, and its absorption is frequently impaired in Crohn’s disease, where it is closely associated with clinical complications and nutritional management. Nevertheless, the quantitative relationship between the complex multiscale architecture of intestinal villi, their morphological dynamics, and the efficiency of folic acid absorption remains insufficiently understood, primarily because existing studies rely on oversimplified representations of villous geometry and neglect the internal vascular structure, thereby limiting their ability to capture the coupled transport processes within individual villi. While existing studies have considered the influence of villous morphology on intestinal absorption, they generally rely on oversimplified representations and do not account for the internal structural organization of villi. This study aims to elucidate the quantitative relationship between villous multiscale architecture and folic acid absorption efficiency under pathological conditions of Crohn’s disease. Herein, a two-dimensional multiphysics numerical model is developed that integrates the external environment of intestinal villi with their internal microstructure, simulating folic acid transport via diffusion and Michaelis–Menten kinetics, coupled with convection–diffusion in the microvascular network under Stokes flow conditions. We find a reduction in villus height to 400 μm or local blood flow velocity to 0.01 mm/s leads to a marked decrease in folic acid absorption capacity, by approximately 57% and 50%, respectively. These changes are primarily attributed to inflammation-induced villus atrophy, which reduces the effective absorptive surface area. Furthermore, reduced blood flow velocity lowers the Peclet number, facilitating the accumulation of folic acid within the villi, which in turn further reduces the efficiency of folic acid absorption. This work contributes to a deeper understanding of how diseases affect the absorptive function of intestinal villi and provides a theoretical basis for the pathological mechanisms of the gut. Full article

Background: The cochlea is a specialized sensory organ essential for hearing. To elucidate its cellular and molecular architecture and prioritize candidate genes associated with hearing loss (HL), we constructed a cross-species single-cell transcriptomic atlas of human fetal and postnatal mouse cochleae. Methods: We integrated single-cell and single-nucleus RNA sequencing datasets from human fetal cochleae and postnatal mouse cochleae to build a comprehensive cross-species single-cell transcriptomic atlas. Cell-type annotation, transcriptional regulator analysis, intercellular communication, and disease phenotypes were performed to dissect the cochlear cellular landscape, regulatory programs, and potential HL gene candidates. Results: A total of 19 major cochlear cell types were identified in both species, with conserved cellular composition and transcriptional programs. Comparative analysis revealed strong transcriptional conservation between matched human and mouse cell types, particularly in supporting, schwann cells and hair cells. Cell–cell communication analysis revealed conserved signaling pathways, including the BDNF-NTRK2 axis, potentially involved in cochlear development and auditory function. Regulatory network inference uncovered conserved and previously undercharacterized transcription factors, such as SKOR1, RFX2, and PAX2, predicted to be associated with hair cell identity and function. We further defined a conserved gene module of 3138 hair cell-enriched genes, from which 24 candidate HL-associated genes (e.g., ATP8B1, BDNF, and SOD1) were prioritized through integration with human disease databases and mouse auditory phenotype annotations. Conclusions: This study provides a high-resolution cross-species cochlear atlas, revealing conserved molecular programs and candidate HL-associated genes, offering valuable insights into auditory biology and potential avenues for further investigation. Full article

Despite the success of artificial neural networks in solving numerous tasks, they face significant challenges, including difficulties in online adaptation and rapidly increasing energy consumption. As a biologically plausible alternative, spiking neural networks offer promising capabilities for efficient cognitive computing. Recently, a three-element spiking neuron model consisting of a threshold selector, a tunnel diode, and a capacitor was proposed. In this work, we experimentally validate this model using a threshold selector hardware emulator and demonstrate its dynamical equivalence to the biologically plausible Izhikevich neuron model. To evaluate the novel neuron’s applicability for cognitive computing, we implement a liquid state machine (LSM) reservoir architecture with spatially dependent random topology for synaptic weight distribution. Our simulations on the MNIST and Fashion-MNIST benchmarks demonstrate competitive classification accuracy (97.9% and 89.5%, respectively) while offering estimated energy efficiency and processing speed enhancements compared to existing FPGA-based and memristor-based spiking reservoir implementations. The developed reservoir is feasible for processing neuromorphic sensors output, including visual perception tasks. Full article

This paper presents a deterministic embedded control architecture for an industrial electroplating line. The validated system includes two autonomous trolleys, 18 station-aligned process positions, shared-track motion, and redundant grouped baths. The proposed controller addresses the limitations of rigid sequential automation by combining asynchronous finite-state trolley execution, runtime allocation of equivalent technological stations, dwell-time-preserving retrieval, distributed thermal supervision, and layered fail-safe protection within a single ATmega2560-based implementation. The core contribution is the integration of virtual process groups and temporal FIFO logic into a compact plant-side embedded controller. This enables adaptive bath selection and process-completion-based retrieval without reliance on a real-time operating system or a computationally heavy supervisory runtime. The architecture also incorporates predictive pre-start validation, runtime software arbitration, hardware-wired interlocks, binary-coded trolley positioning, and a distributed 1-Wire thermal measurement network. Validation was performed in a controller-centered hardware-in-the-loop representation of an 18-station zinc electroplating line. Over a 100-batch horizon, the proposed architecture reduced makespan from 1642 min to 1244 min, corresponding to a 24.2% throughput improvement. Average trolley idle time decreased from 18.4 min/batch to 4.1 min/batch. Grouped-bath utilization increased from 64% to 91%, while tracked bottleneck incidents decreased from 18 to 2. These results show that adaptive, resource-aware, and safety-layered electroplating control can be realized effectively on a compact embedded platform in an industry-representative HIL setting, while preserving dwell-time integrity and controller-level safety invariants. Full article

The evolutionary history and contemporary biogeography jointly shape the genetic architecture of marine species. This study investigates the phylogeny and population genetics of two closely related syngnathid fishes, Trachyrhamphus serratus and Trachyrhamphus longirostris. We report the first record of T. longirostris along the mainland coast of China, with samples collected from Yantai, Kenting, Zhanjiang, and Beihai. Population genetic analyses reveal genetic differentiation within T. longirostris, which exhibits low levels of genetic diversity across all sampled populations compared to T. serratus. The star-like haplotype network and significantly negative neutrality test values collectively indicate a recent population expansion event in T. longirostris. This study offers important insights into the evolutionary dynamics and biogeographic patterning of syngnathid fishes, with clear implications for their conservation and management. Full article

Hybrid supramolecular–nanocomposite hydrogels based on polyethylene glycol (PEG), β-cyclodextrin–adamantane host–guest interactions, and silica nanoparticles represent an important class of hierarchical soft materials with tunable viscoelastic and transport properties. This review critically analyzes recent progress in cyclodextrin–silica hybrid PEG hydrogels, focusing on the mechanistic coupling between stiffness, stress relaxation, and molecular transport arising from the interplay between reversible supramolecular crosslinks and nanoparticle-induced confinement effects. Particular attention is given to how host–guest exchange kinetics regulate dynamic bond rearrangement and affinity-mediated retention of hydrophobic cargo, while silica nanoparticles enhance mechanical reinforcement and modify diffusion pathways through tortuosity and interfacial polymer–particle interactions. The analysis highlights how nanoparticle size, loading level, and surface functionalization influence relaxation spectra and network topology, as well as how environmental stimuli may affect supramolecular bond stability and overall material performance. Comparison with alternative inorganic fillers and mesoporous silica architectures further clarifies the specific advantages of silica in achieving balanced mechanical stability and controlled transport behavior. Overall, current evidence indicates that hybrid CD–silica networks enable partial decoupling of stiffness, relaxation dynamics, and diffusion, although complete independence remains constrained by fundamental polymer physics relationships. These insights support the development of predictive structure–property frameworks for advanced biomedical and controlled release applications. Full article

The deployment of Convolutional Neural Networks (CNNs) on entry-level Edge FPGAs is severely constrained by the scarcity of Digital Signal Processing (DSP) blocks, a phenomenon termed the “DSP Wall”. To circumvent this bottleneck, this paper presents AEMAC, a Software–Hardware Co-Designed accelerator architecture that decouples arithmetic computation from DSP availability. The proposed methodology synergizes a software-level Dynamic Integer Scaling strategy with a hardware-level Adaptive Error-Compensated Multiply-Accumulate unit. By mapping floating-point activations to an optimal integer domain and employing a DSP-free, LUT-based tri-mode datapath, the architecture achieves extreme resource efficiency. To mitigate the precision loss inherent in logic-based truncation, a statistical bias compensation mechanism is integrated into the accumulator chain. Experimental validation on a Xilinx Zynq-7020 FPGA demonstrates a strictly zero-DSP implementation with minimal logic utilization (100 LUTs). Post-implementation timing simulations confirm a dynamic power of 0.490 W for a 64-core cluster under worst-case random workloads, yielding a verified energy efficiency of 26.1 GOPS/W. Micro-level analysis confirms a 16.7% reduction in arithmetic Mean Absolute Error (MAE) compared to naive truncation. Furthermore, macro-level evaluation on the CIFAR-10 dataset reveals that the co-design strategy recovers system accuracy to 64.74%, outperforming the uncompensated baseline by 0.55% and achieving statistical comparability to floating-point baselines. To ensure absolute internal consistency, all hardware metrics are strictly validated via SAIF-based post-implementation simulations. Based on a conservative full-chip projection that incorporates a routing derating model, these internally consistent results establish AEMAC as a highly scalable and reliable solution for breaking the DSP wall in resource-constrained edge intelligence. Full article

Extreme class imbalance is a persistent obstacle for machine learning-driven intrusion detection, as rare but high-impact cyberattacks occur far less frequently than benign traffic in training data. In many real-world cybersecurity datasets, this imbalance becomes extreme, with certain attack types containing a handful of samples, effectively placing the problem in a few-shot learning regime. This paper presents a controlled benchmarking study of Generative Adversarial Network (GAN) objectives for synthesizing minority-class cyberattack data. Using the UWF-ZeekData22 network traffic dataset, each MITRE ATT&CK tactic is framed as a separate binary detection task, and tactic-specific GANs are trained solely on minority samples to generate synthetic attack records. Four widely used GAN variants—Vanilla GAN, Conditional GAN (cGAN), Wasserstein GAN (WGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP)—are compared under unified training steps and fixed augmentation conditions. The utility of generated data is assessed by evaluating downstream detection performance using five traditional classifiers: Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Decision Tree, and Random Forest. The results indicate that GAN augmentation generally strengthens minority-class detection across tactics and models, reducing false negatives and improving recall consistency, while not systematically harming majority-class performance. However, the effectiveness of each GAN objective varies significantly with data sparsity. Specifically, simpler adversarial objectives often outperform more complex architectures by preserving discriminative feature structure, while heavily regularized models may overly smooth minority-class distributions and reduce separability. Wasserstein-based objectives provide improved training stability, but additional regularization does not consistently translate to better detection performance. Overall, the results demonstrate that in extreme-imbalance settings, GAN effectiveness is governed more by data sparsity and structure preservation than by architectural complexity. These findings establish class-specific generative augmentation as a practical strategy for intrusion detection and provide empirical guidance for selecting appropriate GAN objectives for tabular cybersecurity data under highly imbalanced conditions. Full article

Astaxanthin (AST), despite its high bioactivity, exhibits poor stability and low bioavailability due to its strong lipophilicity and inherent degradation susceptibility. To overcome such a challenge, we developed a food-grade oleogel delivery system using a soy protein–arabinoxylan (SA) glycosylated complex modulated by different concentrations (0.5–3%) of sucrose ester (SE) or soy lecithin. We show that the emulsifier concentration has a non-linear effect on the oleogel microstructure: an optimal level of 1% had a significant impact on the interfacial compactness and network density, giving rise to improved thermal stability, rheological strength and AST encapsulation efficiency (81.27%). During in vitro digestion, the SA matrix in combination with emulsifiers allowed gastric protection and intestinal-targeted release of AST with a bioaccessibility of up to 88.84% (SAO-SE-AST). This controlled release profile directly translated into enhanced in vivo antioxidant efficacy in wild-type Bristol N2 Caenorhabditis elegans, as evidenced by reduced lipofuscin accumulation, elevated thermotolerance (survival rate: 64.44–73.33%), suppressed reactive oxygen species levels and activation of endogenous antioxidant enzymes (superoxide dismutase as well as glutathione peroxidase). Collectively, this research has uncovered that food-grade emulsifiers are not only stabilizers, but also key regulators of oleogel architecture and bioactive functionality. These results provide a structure–digestion–bioactivity correlation for protein–polysaccharide oleogels, representing a rational design strategy for high-performance delivery systems of lipid-soluble nutraceuticals. Full article

Accurate regional ocean forecasting requires models that are both computationally efficient and capable of representing predictive uncertainty. This work investigates ensemble learning strategies for sea surface temperature (SST) forecasting using Graph Neural Networks (GNNs), with a focus on how input perturbation design affects forecast skill and uncertainty representation. We adapt a GNN architecture to the Canary Islands region in the North Atlantic and implement a homogeneous ensemble approach inspired by bagging, where diversity is introduced during inference by perturbing initial ocean states rather than retraining multiple models. Several noise-based ensemble generation strategies are evaluated, including Gaussian noise, Perlin noise, and fractal Perlin noise, with systematic variation of noise intensity and spatial structure. Ensemble forecasts are assessed over a 15-day horizon using deterministic metrics (RMSE and bias) and probabilistic metrics, including the Continuous Ranked Probability Score (CRPS) and the Spread–skill ratio. The results show that, while deterministic skill remains comparable to the single-model forecast, the type and structure of input perturbations influence uncertainty representation, particularly at longer lead times. Ensembles generated with spatially coherent perturbations, such as low-resolution Perlin noise, achieve improved calibration and lower CRPS compared to purely random Gaussian perturbations. These findings highlight the role of noise structure and scale in ensemble GNN design, indicating that specifically structured input perturbations can improve ensemble diversity and calibration without additional training cost. These results provide a methodological contribution toward the study of ensemble-based GNN approaches for regional ocean forecasting. Full article

Image inpainting aims to recover missing regions in damaged images while preserving structural coherence and textural authenticity. Although deep learning methods based on generative adversarial networks (GAN) have made significant progress, they still face challenges in modeling long-range dependencies and maintaining semantic consistency, especially when large areas are missing. To address these issues, we propose an innovative multi-stage restoration framework. The coarse restoration stage incorporates attention via a transformer architecture, while the refinement stage introduces a plug-and-play channel-frequency encoder (CF-Encoder). This encoder effectively models both global structure and local details by hierarchically extracting and enhancing features through frequency-domain decomposition combined with an adaptive spatial-channel attention mechanism. Furthermore, we employ a bi-discriminator fusion mechanism to stabilize training and enhance perceptual quality. Experiments across multiple benchmark datasets demonstrate our method’s superior performance in both quantitative metrics and visual fidelity, with particularly notable advantages in high-missing-value scenarios. Full article

Data-driven approaches to blood glucose predictive modeling face significant challenges due to the inherent variability in biological systems. While these methods efficiently capture statistical patterns through automated processes, they often lack the biological interpretability necessary to link model behavior with underlying physiological mechanisms. In contrast, physiological models offer accurate mechanistic representations but require complex parameterization and specialized domain expertise. In this work, we present an approach for predicting blood glucose levels (BGLs) leveraging the concept of physiology-informed neural networks (PINNs). This approach addresses the challenge of BGL prediction by incorporating the parameters of insulin and meal dynamics within the architecture of a predictive network. It employs a two-stage learning approach for modeling physiology and predicting BGLs. The neural network is pretrained to approximate the solutions of the physiological dynamics, and the output of this pretrained model, representing the insulin and glucose concentration states, is then fed as input into a predictive model, enabling simultaneous optimization of predictive accuracy and physiological parameter estimation, offering advantages over traditional modeling approaches in terms of personalized prediction and interpretability. The results highlight the model’s ability to estimate physiological parameters while maintaining strong predictive performance that aligns with the underlying physiological principles. This framework offers significant potential for personalized predictive modeling where precise and efficient understanding of individual metabolism is essential. Full article