Search Results (27)

We present LazyNet, a compact one-step neural-ODE model for single-cell CRISPR activation/interference (A/I) that operates directly on two-snapshot (“pre → post”) measurements and yields parameters with clear mechanistic meaning. The core log–linear–exp residual block exactly represents multiplicative effects, so synergistic multi-locus responses appear as explicit components rather than opaque composites. On a 53k-cell × 18k-gene neuronal Perturb-seq matrix, a three-replica LazyNet ensemble trained under a matched 1 h budget achieved strong threshold-free ranking and competitive error (genome-wide r ≈ 0.67) while running on CPUs. For comparison, we instantiated transformer (scGPT-style) and state-space (RetNet/CellFM-style) architectures from random initialization and trained them from scratch on the same dataset and within the same 1 h cap on a GPU platform, without any large-scale pretraining or external data. Under these strictly controlled, low-data conditions, LazyNet matched or exceeded their predictive performance while using far fewer parameters and resources. A T-cell screen included only for generalization showed the same ranking advantage under the identical evaluation pipeline. Beyond prediction, LazyNet exposes directed, local elasticities; averaging Jacobians across replicas produces a consensus interaction matrix from which compact subgraphs are extracted and evaluated at the module level. The resulting networks show coherent enrichment against authoritative resources (large-scale co-expression and curated functional associations) and concordance with orthogonal GPX4-knockout proteomes, recovering known ferroptosis regulators and nominating testable links in a lysosomal–mitochondrial–immune module. These results position LazyNet as a practical option for from-scratch, low-data CRISPR A/I studies where large-scale pretraining of foundation models is not feasible. Full article

Terminal deoxynucleotidyl transferase (TdT) is a unique DNA polymerase that catalyzes template-independent nucleotide addition at the 3′-end of DNA, playing a critical role in generating immune receptor diversity. While the structural importance of Loop1 in blocking template strand binding and enabling this activity is established, the precise molecular contribution of hydrophobic interactions within Loop1 to the catalytic mechanism of human TdT remains unclear. In the present study, we aim to elucidate the roles of hydrophobic Loop1 residues (L397, F400, F404) in the structural organization and catalytic function of TdT. We engineered alanine and tryptophan substitutions at these positions and systematically analyzed the resulting mutant forms using molecular dynamics simulations and pre-steady-state kinetic measurements. Our results show that substitutions L397A and F400A increase Loop1 flexibility and significantly reduce catalytic activity, particularly for purine nucleotide incorporation, while F404A completely abolishes enzymatic function. The F404W mutant largely preserves activity. All mutant forms retain the ability to bind single-stranded DNA and dNTP, but in some cases, their affinity and thermal stability were reduced. These findings demonstrate that hydrophobic interactions in Loop1 are essential for maintaining the catalytically competent conformation of TdT, ensuring precise substrate positioning and active site stability. Full article

This study focuses on human awareness, a critical component in human–robot interaction, particularly within agricultural environments where interactions are enriched by complex contextual information. The main objective is identifying human activities occurring during collaborative harvesting tasks involving humans and robots. To achieve this, we propose a novel and lightweight deep learning model, named 1D-ResNeXt, designed explicitly for recognizing activities in agriculture-related human–robot collaboration. The model is built as an end-to-end architecture incorporating feature fusion and a multi-kernel convolutional block strategy. It utilizes residual connections and a split–transform–merge mechanism to mitigate performance degradation and reduce model complexity by limiting the number of trainable parameters. Sensor data were collected from twenty individuals with five wearable devices placed on different body parts. Each sensor was embedded with tri-axial accelerometers, gyroscopes, and magnetometers. Under real field conditions, the participants performed several sub-tasks commonly associated with agricultural labor, such as lifting and carrying loads. Before classification, the raw sensor signals were pre-processed to eliminate noise. The cleaned time-series data were then input into the proposed deep learning network for sequential pattern recognition. Experimental results showed that the chest-mounted sensor achieved the highest F1-score of 99.86%, outperforming other sensor placements and combinations. An analysis of temporal window sizes (0.5, 1.0, 1.5, and 2.0 s) demonstrated that the 0.5 s window provided the best recognition performance, indicating that key activity features in agriculture can be captured over short intervals. Moreover, a comprehensive evaluation of sensor modalities revealed that multimodal fusion of accelerometer, gyroscope, and magnetometer data yielded the best accuracy at 99.92%. The combination of accelerometer and gyroscope data offered an optimal compromise, achieving 99.49% accuracy while maintaining lower system complexity. These findings highlight the importance of strategic sensor placement and data fusion in enhancing activity recognition performance while reducing the need for extensive data and computational resources. This work contributes to developing intelligent, efficient, and adaptive collaborative systems, offering promising applications in agriculture and beyond, with improved safety, cost-efficiency, and real-time operational capability. Full article

(1) Background: Integrating assessment with training helps to enhance precision prosthetic rehabilitation of trans-radial amputees. This study aimed to validate a self-developed closed-loop rehabilitation platform combining accurate measurement in comprehensive assessment and immediate interaction in virtual reality (VR) training in refining patient-centered myoelectric prosthesis rehabilitation. (2) Methods: The platform consisted of two modules, a multimodal assessment module and an sEMG-driven VR game training module. The former included clinical scales (OPUS, DASH), task performance metrics (modified Box and Block Test), kinematics analysis (inertial sensors), and surface electromyography (sEMG) recording, verified on six trans-radial amputees and four healthy subjects. The latter aimed for muscle coordination training driven by four-channel sEMG, tested on three amputees. Post 1-week training, task performance and sEMG metrics (wrist flexion/extension activation) were re-evaluated. (3) Results: The sEMG in the residual limb of the amputees upgraded by 4.8%, either the subjects’ number of gold coins or game scores after 1-week training. Subjects uniformly agreed or strongly agreed with all the items on the user questionnaire. In reassessment after training, the average completion time (CT) of all three amputees in both tasks decreased. CTs of the A1 and A3 in the placing tasks were reduced by 49.52% and 50.61%, respectively, and the CTs for the submitting task were reduced by 19.67% and 55.44%, respectively. Average CT of all three amputees in the ADL task after training was 9.97 s, significantly lower than the pre-training time of 15.17 s. (4) Conclusions: The closed-loop platform promotes patients’ prosthesis motor-control tasks through accurate measurement and immediate interaction according to the sensorimotor recalibration principle, demonstrating a potential tool for precision rehabilitation. Full article

Ferritin nanocages with spherical shells carry proteins or antigens that enable their use as highly efficient nanoreactors and nanocarriers. Mimicking the surface Spike (S) receptor-binding domain (RBD) from SARS-CoV-2, ferritin nanocages induce neutralizing antibody production or block viral entry. Herein, by implementing molecular dynamics simulation, we evaluate the efficiency in the interaction pattern (active or alternative sites) of H-ferritin displaying the 24 S RBDs with host-cell-receptor or monoclonal antibodies (mAbs; B38 or VVH-72). Our constructed nanocage targeted the receptor- or antibody-binding interfaces, suggesting that mAbs demonstrate an enhanced binding affinity with the RBD, with key interactions originating from its variable heavy chain. The S RBD interactions with ACE2 and B38 involved the same binding site but led to divergent dynamic responses. In particular, both B38 chains showed that asymmetric fluctuations had a major effect on their engagement with the Spike RBD. Although the receptor increased the binding affinity of VVH-72 for the RBD, the mAb structural orientation on the nanocage remained identical to its conformation when bound to the host receptor. Overall, our findings characterize the essential pharmacophore formed by Spike RBD residues over nanocage molecules, which mediates high-affinity interactions with either binding partner. Importantly, the ferritin-displayed RBD maintained native receptor and antibody binding profiles, positioning it as a promising scaffold for pre-fusion stabilization and protective RBD vaccine design. Full article

In this article, we consider the roles of transcrustal magma- and fluid-conducting faults (TCMFCFs) in the formation of mineral deposits, showing the importance of deep sources of heat and hydrothermal solutions in the genesis and history of deposit formation. As a result of the impact on the lithosphere of mantle plumes rising along TCMFCFs, intense block deformations and tectonic movements are generated; rift systems, and volcanic–plutonic belts spatially combined with them, are formed; and intrusive bodies are introduced. These processes cause epithermal ore formation as a consequence of the impact of mantle plumes rising along TCMFCF to the lithosphere. At hydrocarbon fields, they play extremely important roles in conductive and convective heat, as well as in mass transfer to the area of hydrocarbon generation, determining the relationship between the processes of lithogenesis and tectogenesis, and activating the generation of hydrocarbons from oil and gas source rock. Detection of TCMFCFs was carried out using MMSS (the method of microseismic sounding) and MTSM (the magnetotelluric sounding method), in combination with other geological and geophysical data. Practical examples are provided for mineral deposits where subvertical transcrustal columns of increased permeability, traced to considerable depths, have been found; the nature of these unique structures is related to faults of pre-Paleozoic emplacement, which determined the fragmentation of the sub-crystalline structure of the Earth and later, while developing, inherited the conditions of volumetric fluid dynamics, where the residual forms of functioning of fluid-conducting thermohydrocolumns are granitoid batholiths and other magmatic bodies. Experimental modeling of deep processes allowed us to identify the quantum character of crystal structure interactions of minerals with “inert” gases under elevated thermobaric conditions. The roles of helium, nitrogen, and hydrogen in changing the physical properties of rocks, in accordance with their intrastructural diffusion, has been clarified; as a result of low-energy impact, stress fields are formed in the solid rock skeleton, the structures and textures of rocks are rearranged, and general porosity develops. As the pressure increases, energetic interactions intensify, leading to deformations, phase transitions, and the formation of chemical bonds under the conditions of an unstable geological environment, instability which grows with increasing gas saturation, pressure, and temperature. The processes of heat and mass transfer through TCMFCFs to the Earth’s surface occur in stages, accompanied by a release of energy that can manifest as explosions on the surface, in coal and ore mines, and during earthquakes and volcanic eruptions. Full article

Corn residual herbicides offer a practical approach to comprehensive weed management throughout the growing season. However, the use of residual pre-emergence herbicides can have a negative impact on crops grown in succession or within a rotation. A study was carried out to determine the effect of the residual activity of selected corn herbicides on soybeans. The objective of the study was to evaluate the impact of these herbicides on the germination of inoculated soybean seeds. Experiments were conducted in greenhouse conditions to check the carryover effect on soybean germination. Treatment combinations of two pre-herbicides and two inoculants were applied: atrazine (2241 g ai ha⁻¹), mesotrione (105 g ai ha⁻¹), and Bradyrhizobium japonicum, Bradyrhizobium japonicum + Bacillus subtilis, respectively. A randomized complete block design evaluated six treatment combinations, including the control. All treatments, except uninoculated treatments, presented efficacy in reducing the carryover effects of corn residual herbicides on the germination of soybeans. An increase in final germination percentage was observed with Bradyrhizobium japonicum + Bacillus subtilis co-inoculation plus atrazine (24% increase) and Bradyrhizobium japonicum plus mesotrione treatment combinations (19% increase). Inoculating soybean seeds with rhizobium bacteria can reduce the carryover effects on the germination of soybean seeds grown in soil applied with atrazine and mesotrione. Full article

The precise segmentation of retinal vasculature is crucial for the early screening of various eye diseases, such as diabetic retinopathy and hypertensive retinopathy. Given the complex and variable overall structure of retinal vessels and their delicate, minute local features, the accurate extraction of fine vessels and edge pixels remains a technical challenge in the current research. To enhance the ability to extract thin vessels, this paper incorporates a pyramid channel attention module into a U-shaped network. This allows for more effective capture of information at different levels and increased attention to vessel-related channels, thereby improving model performance. Simultaneously, to prevent overfitting, this paper optimizes the standard convolutional block in the U-Net with the pre-activated residual discard convolution block, thus improving the model’s generalization ability. The model is evaluated on three benchmark retinal datasets: DRIVE, CHASE_DB1, and STARE. Experimental results demonstrate that, compared to the baseline model, the proposed model achieves improvements in sensitivity (Sen) scores of 7.12%, 9.65%, and 5.36% on these three datasets, respectively, proving its strong ability to extract fine vessels. Full article

Deep learning has achieved great success in remote sensing image change detection (CD). However, most methods focus only on the changed regions of images and cannot accurately identify their detailed semantic categories. In addition, most CD methods using convolutional neural networks (CNN) have difficulty capturing sufficient global information from images. To address the above issues, we propose a novel symmetric multi-task network (SMNet) that integrates global and local information for semantic change detection (SCD) in this paper. Specifically, we employ a hybrid unit consisting of pre-activated residual blocks (PR) and transformation blocks (TB) to construct the (PRTB) backbone, which obtains more abundant semantic features with local and global information from bi-temporal images. To accurately capture fine-grained changes, the multi-content fusion module (MCFM) is introduced, which effectively enhances change features by distinguishing foreground and background information in complex scenes. In the meantime, the multi-task prediction branches are adopted, and the multi-task loss function is used to jointly supervise model training to improve the performance of the network. Extensive experimental results on the challenging SECOND and Landsat-SCD datasets, demonstrate that our SMNet obtains 71.95% and 85.65% at mean Intersection over Union (mIoU), respectively. In addition, the proposed SMNet achieves 20.29% and 51.14% at Separated Kappa coefficient (Sek) on the SECOND and Landsat-SCD datasets, respectively. All of the above proves the effectiveness and superiority of the proposed method. Full article

Wildfire is a hazardous natural phenomenon that leads to significant human fatalities, catastrophic environmental damages, and economic losses. Over the past few years, the intensity and frequency of fires have increased worldwide. Studies have been conducted to develop distinctive solutions to minimize forest fires. Systems for distant fire detection and monitoring have been established, showing improvements in data collection and fire characterization. However, wildfires cover vast areas, making other proposed ground systems unsuitable for optimal coverage. Unmanned aerial vehicles (UAVs) have become the subject of active research in recent years. Deep learning-based image-processing methods demonstrate improved performance in various tasks, including detection and segmentation, which can be utilized to develop modern forest firefighting techniques. In this study, we established a novel two-pathway encoder–decoder-based model to detect and accurately segment wildfires and smoke from the images captured using UAVs in real-time. Our proposed nested decoder uses pre-activated residual blocks and an attention-gating mechanism, thereby improving segmentation accuracy. Moreover, to facilitate robust and generalized training, we prepared a new dataset comprising actual incidences of forest fires and smoke, varying from small to large areas. In terms of practicality, the experimental results reveal that our method significantly outperforms existing detection and segmentation methods, despite being lightweight. In addition, the proposed model is reliable and robust for detecting and segmenting drone camera images from different viewpoints in the presence of wildfire and smoke. Full article

An Inertial Measurement Unit (IMU) is a significant component of a spacecraft, and its fault diagnosis results directly affect the spacecraft’s stability and reliability. In recent years, deep learning-based fault diagnosis methods have made great achievements; however, some problems such as how to extract effective fault features and how to promote the training process of deep networks are still to be solved. Therefore, in this study, a novel intelligent fault diagnosis approach combining a deep residual convolutional neural network (CNN) and a data preprocessing algorithm is proposed. Firstly, the short-time Fourier transform (STFT) is adopted to transform the raw time domain data into time–frequency images so the useful information and features can be extracted. Then, the Z-score normalization and data augmentation strategies are both explored and exploited to facilitate the training of the subsequent deep model. Furthermore, a modified CNN-based deep diagnosis model, which utilizes the Parameter Rectified Linear Unit (PReLU) as activation functions and residual blocks, automatically learns fault features and classifies fault types. Finally, the experiment’s results indicate that the proposed method has good fault features’ extraction ability and performs better than other baseline models in terms of classification accuracy. Full article

Current antiretroviral therapy (ART) increases the survival of HIV-infected individuals, yet it is not curative. The major barrier to finding a definitive cure for HIV is our inability to identify and eliminate long-lived cells containing the dormant provirus, termed viral reservoir. When ART is interrupted, the viral reservoir ensures heterogenous and stochastic HIV viral gene expression, which can reseed infection back to pre-ART levels. While strategies to permanently eradicate the virus have not yet provided significant success, recent work has focused on the management of this residual viral reservoir to effectively limit comorbidities associated with the ongoing viral transcription still observed during suppressive ART, as well as limit the need for daily ART. Our group has been at the forefront of exploring the viability of the block-and-lock remission approach, focused on the long-lasting epigenetic block of viral transcription such that without daily ART, there is no risk of viral rebound, transmission, or progression to AIDS. Numerous studies have reported inhibitors of both viral and host factors required for HIV transcriptional activation. Here, we highlight and review some of the latest HIV transcriptional inhibitor discoveries that may be leveraged for the clinical exploration of block-and-lock and revolutionize the way we treat HIV infections. Full article

Biologically inspired spiking neural networks (SNNs) are widely used to realize ultralow-power energy consumption. However, deep SNNs are not easy to train due to the excessive firing of spiking neurons in the hidden layers. To tackle this problem, we propose a novel but simple normalization technique called postsynaptic potential normalization. This normalization removes the subtraction term from the standard normalization and uses the second raw moment instead of the variance as the division term. The spike firing can be controlled, enabling the training to proceed appropriately, by conducting this simple normalization to the postsynaptic potential. The experimental results show that SNNs with our normalization outperformed other models using other normalizations. Furthermore, through the pre-activation residual blocks, the proposed model can train with more than 100 layers without other special techniques dedicated to SNNs. Full article

Due to anthropogenic and natural activities, the land surface continuously changes over time. The accurate and timely detection of changes is greatly important for environmental monitoring, resource management and planning activities. In this study, a novel deep learning-based change detection algorithm is proposed for bi-temporal polarimetric synthetic aperture radar (PolSAR) imagery using a transfer learning (TL) method. In particular, this method has been designed to automatically extract changes by applying three main steps as follows: (1) pre-processing, (2) parallel pseudo-label training sample generation based on a pre-trained model and fuzzy c-means (FCM) clustering algorithm, and (3) classification. Moreover, a new end-to-end three-channel deep neural network, called TCD-Net, has been introduced in this study. TCD-Net can learn more strong and abstract representations for the spatial information of a certain pixel. In addition, by adding an adaptive multi-scale shallow block and an adaptive multi-scale residual block to the TCD-Net architecture, this model with much lower parameters is sensitive to objects of various sizes. Experimental results on two Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) bi-temporal datasets demonstrated the effectiveness of the proposed algorithm compared to other well-known methods with an overall accuracy of 96.71% and a kappa coefficient of 0.82. Full article

Films formulated with polyvinyl alcohol (PVA) (synthetic biopolymer) were reinforced with lignocellulose nanofibres (LCNF) from residues of vegetable production (natural biopolymer). The LCNF were obtained by mechanical and chemical pre-treatment by 2,2,6,6-tetramethylpiperidine-1-oxyl radical (TEMPO) and added to the polyvinyl alcohol (polymer matrix) with the aim of improving the properties of the film for use in food packaging. The mechanical properties, crystallinity, thermal resistance, chemical structure, antioxidant activity, water barrier properties and optical properties (transparency and UV barrier), were evaluated. In general, with the addition of LCNF, an improvement in the studied properties of the films was observed. In terms of mechanical properties, the films reinforced with 7% LCNF TEMPO showed the best results for tensile strength, Young’s modulus and elongation at break. At the same LCNF proportion, the thermal stability (T_max) increased between 5.5% and 10.8%, and the antioxidant activity increased between 90.9% and 191.8%, depending on the raw material and the pre-treatment used to obtain the different LCNF. Finally, a large increase in UV blocking was also observed with the addition of 7% LCNF. In particular, the films with 7% of eggplant LCNF showed higher performance for Young’s modulus, elongation at break, thermal stability and UV barrier. Overall, results demonstrated that the use of LCNF generated from agricultural residues represents a suitable bioeconomy approach able to enhance film properties for its application in the development of more sustainable and eco-friendly food packaging systems. Full article