RESUMEN

The compartmentalization of chromatin reflects its underlying biological activities. Inferring chromatin sub-compartments using Hi-C data is challenged by data resolution constraints. Consequently, comprehensive characterizations of sub-compartments have been limited to a select number of Hi-C experiments, with systematic comparisons across a wide range of tissues and conditions still lacking. Our original Calder algorithm marked a significant advancement in this field, enabling the identification of multi-scale sub-compartments at various data resolutions and facilitating the inference and comparison of chromatin architecture in over 100 datasets. Building on this foundation, we introduce Calder2, an updated version of Calder that brings notable improvements. These include expanded support for a wider array of genomes and organisms, an optimized bin size selection approach for more accurate chromatin compartment detection, and extended support for input and output formats. Calder2 thus stands as a refined analysis tool, significantly advancing genome-wide studies of 3D chromatin architecture and its functional implications.

Asunto(s)

RESUMEN

The digestion of starch have been of great interest, yet little is known about the structure changes and structure-digestibility relationships of waxy rice starch during digestion. In this study, waxy rice starch from Indica and Japonica cultivars were in vitro pre-digested for different times, and the changes in their structure and properties were investigated, including granule morphology, chain length distribution, short-range ordered structure, crystallinity, thermal properties, and digestibility. Pre-digested Indica and Japonica waxy rice starch had the characteristics of porous starch, showing similar surface erosion and pores. With the prolongation of pre-digestion time, the amylose content decreased by 0.74 %-2.69 %, the proportion of amylopectin short A chain (DP6-12) and B1 chain (DP13-24) decreased, and the proportion of long B2 (DP25-36) and B3 chain (DP ≥ 37) increased, especially in pre-digested Indica waxy rice starch. The short- and long-range ordered structure of pre-digested starch increased, manifested by an increase in the absorbance ratio at 1047/1022 cm-1, a decrease at 1022/995 cm-1, and an increase in relative crystallinity, leading to higher gelatinization temperature and enthalpy. Pre-digested waxy rice starch had a reduced rapidly digestible starch of 18.27 %-33.93 % and an increased resistant starch of 29.51 %-41.32 %, which will be applied in functional starch and healthy starchy foods.

RESUMEN

Deep learning-based denoising of low-dose medical CT images has received great attention both from academic researchers and physicians in recent years, and has shown important application value in clinical practice. In this work, a novel two-branch and multi-scale residual attention-based network for low-dose CT image denoising is proposed. It adopts a two-branch framework structure, to extract and fuse image features at shallow and deep levels respectively, to recover image texture and structure information as much as possible. We propose the adaptive dynamic convolution block (ADCB) in the local information extraction layer. It can effectively extract the detailed information of low-dose CT denoising and enables the network to better capture the local details and texture features of the image, thereby improving the denoising effect and image quality. Multi-scale edge enhancement attention block (MEAB) is proposed in the global information extraction layer, to perform feature fusion through dilated convolution and a multi-dimensional attention mechanism. A multi-scale residual convolution block (MRCB) is proposed to integrate feature information and improve the robustness and generalization of the network. To demonstrate the effectiveness of our method, extensive comparison experiments are conducted and the performances evaluated on two publicly available datasets. Our model achieves 29.3004 PSNR, 0.8659 SSIM, and 14.0284 RMSE on the AAPM-Mayo dataset. It is evaluated by adding four different noise levels σ = 15, 30, 45, and 60 on the Qin_LUNG_CT dataset and achieves the best results. Ablation studies show that the proposed ADCB, MEAB, and MRCB modules improve the denoising performances significantly. The source code is available at https://github.com/Ye111-cmd/LDMANet .

RESUMEN

BACKGROUND: Fragile X syndrome (FXS) and autism spectrum disorder (ASD) are neurodevelopmental conditions that often have a substantial impact on daily functioning and quality of life. FXS is the most common cause of inherited intellectual disability (ID) and the most common monogenetic cause of ASD. Previous literature has shown that electrophysiological activity measured by electroencephalogram (EEG) during resting state is perturbated in FXS and ASD. However, whether electrophysiological profiles of participants with FXS and ASD are similar remains unclear. The aim of this study was to compare EEG alterations found in these two clinical populations presenting varying degrees of cognitive and behavioral impairments. METHODS: Resting state EEG signal complexity, alpha peak frequency (APF) and power spectral density (PSD) were compared between 47 participants with FXS (aged between 5-20), 49 participants with ASD (aged between 6-17), and 52 neurotypical (NT) controls with a similar age distribution using MANCOVAs with age as covariate when appropriate. MANCOVAs controlling for age, when appropriate, and nonverbal intelligence quotient (NVIQ) score were subsequently performed to determine the impact of cognitive functioning on EEG alterations. RESULTS: Our results showed that FXS participants manifested decreased signal complexity and APF compared to ASD participants and NT controls, as well as altered power in the theta, alpha and low gamma frequency bands. ASD participants showed exaggerated beta power compared to FXS participants and NT controls, as well as enhanced low and high gamma power compared to NT controls. However, ASD participants did not manifest altered signal complexity or APF. Furthermore, when controlling for NVIQ, results of decreased complexity in higher scales and lower APF in FXS participants compared to NT controls and ASD participants were not replicated. CONCLUSIONS: These findings suggest that signal complexity and APF might reflect cognitive functioning, while altered power in the low gamma frequency band might be associated with neurodevelopmental conditions, particularly FXS and ASD.

Asunto(s)

RESUMEN

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Asunto(s)

RESUMEN

With the development of automated malware toolkits, cybersecurity faces evolving threats. Although visualization-based malware analysis has proven to be an effective method, existing approaches struggle with challenging malware samples due to alterations in the texture features of binary images during the visualization preprocessing stage, resulting in poor performance. Furthermore, to enhance classification accuracy, existing methods sacrifice prediction time by designing deeper neural network architectures. This paper proposes PAFE, a lightweight and visualization-based rapid malware classification method. It addresses the issue of texture feature variations in preprocessing through pixel-filling techniques and applies data augmentation to overcome the challenges of class imbalance in small sample datasets. PAFE combines multi-scale feature fusion and a channel attention mechanism, enhancing feature expression through modular design. Extensive experimental results demonstrate that PAFE outperforms the current state-of-the-art methods in both efficiency and effectiveness for malware variant classification, achieving an accuracy rate of 99.25 % with a prediction time of 10.04 ms.

RESUMEN

Defect detection is critical to industrial quality control in leather production engineering. The various sizes and locations of defects in leather, as well as significant differences within the same class and indistinctive variations between different classes of defects, contribute to the complexity of the problem. To address this challenge, we propose a Multi-Layer Residual Convolutional Attention (MLRCA) approach. MLRCA enhances its ability to capture both intra-class and inter-class differences by enhancing the semantic feature representation in the backbone network. To improve multiscale fusion effects, we also incorporate the MLRCA module into the feature pyramid network (FPN) and propose a new multi-layer residual convolution attention feature pyramid network (ML-FPN). This approach enables more accurate identification of leather defects at a more detailed level by selectively capturing contextual information from different domains. We then implement the Side-Aware Boundary Localization (SABL) detection head, which accurately locates defects and helps the network distinguish between similar defect categories for more precise positioning. To validate the effectiveness of our approach, we conducted ablation experiments on the created leather dataset. Comparative experiments demonstrate the excellent capability of our model to detect minor defects. The model achieved 83.4, 89.7, and 85.6 for the AP, AP50, and AP75 evaluation metrics. In addition, the model achieves 71.3, 89.9, and 88.9 for APS, APM, and APL. Our approach has been confirmed feasible through experimentation and provides new insights for automated leather defect detection methods.

RESUMEN

Understanding the responses of ecosystem service trade-offs and synergies in metropolitan areas to the multidimensional expansion of urban space is of great significance for the optimization of regional land spatial pattern and high-quality development. With the Guangfo Metropolitan Area as research region, we used land use data and natural ecological environment data from 2000 to 2020 to measure the expansion characteristics of urban space in the dimensions of scale, distribution, and morphology by using the landscape pattern indices. We further calculated four main ecosystem services: urban cooling, habitat quality, recreation, and water conservation by the InVEST model, quantified the trade-off and synergistic relationship of multiple ecosystem services by the coupling coordination degree model, and explored its response to multidimensional urban spatial expansion by using the multi-scale geographically weighted regression model. The results showed that urban land use scale in the Guangfo Metropolitan Area continued to increase from 2000 to 2020, with an accelerated growth rate from 2010 to 2020. The ave-rage patch area of urban land in the central area and the urban land of small patches in the northeast increased, evolving from a "dual-center" structure to a "single-center" one. The distance between urban land patches in the Guangfo Metropolitan Area was relatively small, indicating a compact distribution of urban land. The distance between newly developed urban land patches was also small, but had gradually increased in recent years. The patch shape of urban land was relatively regular and less complex, but the complexity of the newly added urban land gra-dually increased. The ecosystem service trade-offs and synergies in the Guangfo Metropolitan Area had undergone significant changes, with a decrease in synergies and an increase in trade-off, and extreme trade-offs had gradually become dominant. The response of ecosystem services synergies to changes in urban land use scale was the most intense and had spatial heterogeneity, while the response to the change of distribution and morphological characte-ristics of urban land showed periodic differences.

Asunto(s)

RESUMEN

This paper presents a novel multi-scale method for convection-dominated diffusion problems in the regime of large Péclet numbers. The method involves applying the solution operator to piecewise constant right-hand sides on an arbitrary coarse mesh, which defines a finite-dimensional coarse ansatz space with favorable approximation properties. For some relevant error measures, including the L 2 -norm, the Galerkin projection onto this generalized finite element space even yields ε -independent error bounds, ε being the singular perturbation parameter. By constructing an approximate local basis, the approach becomes a novel multi-scale method in the spirit of the Super-Localized Orthogonal Decomposition (SLOD). The error caused by basis localization can be estimated in an a posteriori way. In contrast to existing multi-scale methods, numerical experiments indicate ε -robust convergence without pre-asymptotic effects even in the under-resolved regime of large mesh Péclet numbers.

RESUMEN

Invasive species are a major threat to global diversity and can interact synergistically or antagonistically with various components of climate change. Using species distribution models (SDMs) at different spatial scales and resolutions, we determined the main variables affecting the distribution of six invasive macroalgae present on European coasts. We also studied occupation of the thermal realized niche and predicted areas potentially at risk of invasion. The climatic variables related to warming had a greater influence on distribution at large scales, while non-climatic variables related to river influence and maritime transport at regional scale. Invaders often seemed to occupy colder areas than in their native area. The combination of SDMs with thermal niche of species is a useful way of clarifying the invasion process. This approach will help in the development of preventive strategies whereby the responsible authorities can implement early detection systems and respond swiftly to the appearance of biopollutants.

RESUMEN

Transformer-based methods effectively capture global dependencies in images, demonstrating outstanding performance in multiple visual tasks. However, existing Transformers cannot effectively denoise large noisy images captured under low-light conditions owing to (1) the global self-attention mechanism causing high computational complexity in the spatial dimension owing to a quadratic increase in computation with the number of tokens; (2) the channel-wise self-attention computation unable to optimise the spatial correlations in images. We propose a local-global interaction Transformer (LGIT) that employs an adaptive strategy to select relevant patches for global interaction, achieving low computational complexity in global self-attention computation. A top-N patch cross-attention model (TPCA) is designed based on superpixel segmentation guidance. TPCA selects top-N patches most similar to the target image patch and applies cross attention to aggregate information from them into the target patch, effectively enhancing the utilisation of the image's nonlocal self-similarity. A mixed-scale dual-gated feedforward network (MDGFF) is introduced for the effective extraction of multiscale local correlations. TPCA and MDGFF were combined to construct a hierarchical encoder-decoder network, LGIT, to compute self-attention within and across patches at different scales. Extensive experiments using real-world image-denoising datasets demonstrated that LGIT outperformed state-of-the-art (SOTA) convolutional neural network (CNN) and Transformer-based methods in qualitative and quantitative results.

RESUMEN

The lung is characterized by high elasticity and complex structure, which implies that the lung is capable of undergoing complex deformation and the shape variable is substantial. Large deformation estimation poses significant challenges to lung image registration. The traditional U-Net architecture is difficult to cover complex deformation due to its limited receptive field. Moreover, the relationship between voxels weakens as the number of downsampling times increases, that is, the long-range dependence issue. In this paper, we propose a novel multilevel registration framework which enhances the correspondence between voxels to improve the ability of estimating large deformations. Our approach consists of a convolutional neural network (CNN) with a two-stream registration structure and a cross-scale mapping attention (CSMA) mechanism. The former extracts the robust features of image pairs within layers, while the latter establishes frequent connections between layers to maintain the correlation of image pairs. This method fully utilizes the context information of different scales to establish the mapping relationship between low-resolution and high-resolution feature maps. We have achieved remarkable results on DIRLAB (TRE 1.56 ± 1.60) and POPI (NCC 99.72% SSIM 91.42%) dataset, demonstrating that this strategy can effectively address the large deformation issues, mitigate long-range dependence, and ultimately achieve more robust lung CT image registration.

RESUMEN

Timely discovery and disposal of road risk sources constitute the cornerstone of road operation safety. Presently, the detection of road risk sources frequently relies on manual inspections via inspection vehicles, a process that is both inefficient and time-consuming. To tackle this challenge, this paper introduces a novel automated approach for detecting road risk sources, termed the multi-scale lightweight network (MSLN). This method primarily focuses on identifying road surfaces, potholes, and scattered objects. To mitigate the influence of real-world factors such as noise and uneven brightness on test results, pavement images were carefully collected. Initially, the collected images underwent grayscale processing. Subsequently, the median filtering algorithm was employed to filter out noise interference. Furthermore, adaptive histogram equalization techniques were utilized to enhance the visibility of cracks and the road background. Following these preprocessing steps, the MSLN model was deployed for the detection of road risk sources. Addressing the challenges associated with two-stage network models, such as prolonged training and testing times, as well as deployment difficulties, this study adopted the lightweight feature extraction network MobileNetV2. Additionally, transfer learning was incorporated to elevate the model's training efficiency. Moreover, this paper established a mapping relationship model that transitions from the world coordinate system to the pixel coordinate system. This model enables the calculation of risk source dimensions based on detection outcomes. Experimental results reveal that the MSLN model exhibits a notably faster convergence rate. This enhanced convergence not only boosts training speed but also elevates the precision of risk source detection. Furthermore, the proposed mapping relationship coordinate transformation model proves highly effective in determining the scale of risk sources.

RESUMEN

Road crack detection is of paramount importance for ensuring vehicular traffic safety, and implementing traditional detection methods for cracks inevitably impedes the optimal functioning of traffic. In light of the above, we propose a USSC-YOLO-based target detection algorithm for unmanned aerial vehicle (UAV) road cracks based on machine vision. The algorithm aims to achieve the high-precision detection of road cracks at all scale levels. Compared with the original YOLOv5s, the main improvements to USSC-YOLO are the ShuffleNet V2 block, the coordinate attention (CA) mechanism, and the Swin Transformer. First, to address the problem of large network computational spending, we replace the backbone network of YOLOv5s with ShuffleNet V2 blocks, reducing computational overhead significantly. Next, to reduce the problems caused by the complex background interference, we introduce the CA attention mechanism into the backbone network, which reduces the missed and false detection rate. Finally, we integrate the Swin Transformer block at the end of the neck to enhance the detection accuracy for small target cracks. Experimental results on our self-constructed UAV near-far scene road crack i(UNFSRCI) dataset demonstrate that our model reduces the giga floating-point operations per second (GFLOPs) compared to YOLOv5s while achieving a 6.3% increase in mAP@50 and a 12% improvement in mAP@ [50:95]. This indicates that the model remains lightweight meanwhile providing excellent detection performance. In future work, we will assess road safety conditions based on these detection results to prioritize maintenance sequences for crack targets and facilitate further intelligent management.

RESUMEN

Unmanned aerial vehicles (UAVs) with cameras offer extensive monitoring capabilities and exceptional maneuverability, making them ideal for real-time ship detection and effective ship management. However, ship detection by camera-equipped UAVs faces challenges when it comes to multi-viewpoints, multi-scales, environmental variability, and dataset scarcity. To overcome these challenges, we proposed a data augmentation method based on stable diffusion to generate new images for expanding the dataset. Additionally, we improve the YOLOv8n OBB model by incorporating the BiFPN structure and EMA module, enhancing its ability to detect multi-viewpoint and multi-scale ship instances. Through multiple comparative experiments, we evaluated the effectiveness of our proposed data augmentation method and the improved model. The results indicated that our proposed data augmentation method is effective for low-volume datasets with complex object features. The YOLOv8n-BiFPN-EMA OBB model we proposed performed well in detecting multi-viewpoint and multi-scale ship instances, achieving the mAP (@0.5) of 92.3%, the mAP (@0.5:0.95) of 77.5%, a reduction of 0.8 million in model parameters, and a detection speed that satisfies real-time ship detection requirements.

RESUMEN

Magnetite nanoparticles (Fe3O4-NPs) have been demonstrated to be involved in direct interspecies electron transfer between syntrophic bacteria, yet a comprehensive assessment of the ability of Fe3O4-NPs to cope with process instability and volatile fatty acids (VFAs) accumulation in scaled-up anaerobic reactors is still lacking. Here, we investigated the start-up characteristics of an expanded granular sludge bed (EGSB) with Fe3O4-NPs as an adjuvant at high organic loading rate (OLR). The results showed that the methane production rate of R1 (with Fe3O4-NPs) was approximately 1.65 folds of R0 (control), and effluent COD removal efficiency was maintained at approximately 98.32% upon 20 kg COD/(m3·d) OLR. The components of volatile fatty acids are acetate and propionate, and the rapid scavenging of propionate accumulation was the difference between R1 and the control. The INT-ETS activity of R1 was consistently higher than that of R0 and R2, and the electron transfer efficiencies increased by 68.78% and 131.44%, respectively. Meanwhile, the CV curve analysis showed that the current of R1 was 40% higher than R3 (temporary addition of Fe3O4-NPs), indicating that multiple electron transfer modes might coexist. High-throughput analysis further revealed that it was difficult to reverse the progressive deterioration of system performance with increasing OLR by simply reconfiguring bacterial community structure and abundance, demonstrating that the Fe3O4-NPs-mediated DIET pathway is a prerequisite for establishing multiple electron transfer systems. This study provides a long-term and multi-scale assessment of the gaining effect of Fe3O4-NPs in anaerobic digestion scale-up devices, and provides technical support for their practical engineering applications.

RESUMEN

In recent years, the rapid accumulation of marine waste not only endangers the ecological environment but also causes seawater pollution. Traditional manual salvage methods often have low efficiency and pose safety risks to human operators, making automatic underwater waste recycling a mainstream approach. In this paper, we propose a lightweight multi-scale cross-level network for underwater waste segmentation based on sonar images that provides pixel-level location information and waste categories for autonomous underwater robots. In particular, we introduce hybrid perception and multi-scale attention modules to capture multi-scale contextual features and enhance high-level critical information, respectively. At the same time, we use sampling attention modules and cross-level interaction modules to achieve feature down-sampling and fuse detailed features and semantic features, respectively. Relevant experimental results indicate that our method outperforms other semantic segmentation models and achieves 74.66 % mIoU with only 0.68 M parameters. In particular, compared with the representative PIDNet Small model based on the convolutional neural network architecture, our method can improve the mIoU metric by 1.15 percentage points and can reduce model parameters by approximately 91 %. Compared with the representative SeaFormer T model based on the transformer architecture, our approach can improve the mIoU metric by 2.07 percentage points and can reduce model parameters by approximately 59 %. Our approach maintains a satisfactory balance between model parameters and segmentation performance. Our solution provides new insights into intelligent underwater waste recycling, which helps in promoting sustainable marine development.

RESUMEN

Accurate consumption forecasting is of great importance to grasp the energy consumption habits of consumers and promote the stable and efficient operation of integrated energy system (IES). To this end, this paper proposes an interactive multi-scale convolutional module-based short-term multi-energy consumption forecasting method for IES. Firstly, based on multi-scale feature fusion and multi-energy interactive learning, a novel interactive multi-scale convolutional module is proposed to extract and share the coupling information between energy consumption from different scales without increasing network parameters. Then, a short-term multi-energy consumption forecasting method is proposed, where different forecasting network structures are selected in different seasons to make full use of seasonal and coupling characteristics of the energy consumption, thus enhancing prediction performance. Furthermore, a Laplace distribution-based loss function weight optimization method is proposed to dynamically balance the loss magnitude and training speed of joint forecast tasks more robustly. Finally, the effectiveness and superiority of the proposed method are verified by comparative simulation experiments.

RESUMEN

Conventional solid oral dosage form development is not typically challenged by reliance on an amorphous drug substance as a direct ingredient in the drug product, as this may result in product development hurdles arising from process design and scale-up, control of physical quality attributes, drug product processability and stability. Here, we present the Chemistry, Manufacturing and Controls development journey behind the successful commercialization of an amorphous drug substance, Elagolix Sodium, a first-in-class, orally active gonadotropin-releasing hormone antagonist. The reason behind the lack of crystalline state was assessed via Molecular Dynamics (MD) at the molecular and inter-molecular level, revealing barriers for nucleation due to prevalence of intra-molecular hydrogen bond, repulsive interactions between active pharmaceutical ingredient (API) molecules and strong solvation effects. To provide a foundational basis for the design of the API manufacturing process, we modeled the solvent-induced plasticization behavior experimentally and computationally via MD for insights into molecular mobility. In addition, we applied material science tetrahedron concepts to link API porosity to drug product tablet compressibility. Finally, we designed the API isolation process, incorporating computational fluid dynamics modeling in the design of an impinging jet mixer for precipitation and solvent-dependent glass transition relationships in the cake wash, blow-down and drying process, to enable the consistent manufacture of a porous, non-sintered amorphous API powder that is suitable for robust drug product manufacturing.

RESUMEN

Accurately predicting drug-target affinity is crucial in expediting the discovery and development of new drugs, which is a complex and risky process. Identifying these interactions not only aids in screening potential compounds but also guides further optimization. To address this, we propose a multi-perspective feature fusion model, MFF-DTA, which integrates chemical structure, biological sequence, and other data to comprehensively capture drug-target affinity features. The MFF-DTA model incorporates multiple feature learning components, each of which is capable of extracting drug molecular features and protein target information, respectively. These components are able to obtain key information from both global and local perspectives. Then, these features from different perspectives are efficiently combined using specific splicing strategies to create a comprehensive representation. Finally, the model uses the fused features to predict drug-target affinity. Comparative experiments show that MFF-DTA performs optimally on the Davis and KIBA data sets. Ablation experiments demonstrate that removing specific components results in the loss of unique information, thus confirming the effectiveness of the MFF-DTA design. Improvements in DTA prediction methods will decrease costs and time in drug development, enhancing industry efficiency and ultimately benefiting patients.