Binding Affinity Prediction and Pesticide Screening against Using a Heterogeneous Interaction Graph Attention Network-Based Model.

Phytophthora root and stem rot in soybeans results in substantial economic losses worldwide. In this study, a machine learning model based on a heterogeneous interaction graph attention network model was constructed. The PDBbind data set, comprising 13,285 complexes with experimental or K values, was utilized to train and evaluate the model, which was subsequently employed to screen candidate compounds against chitin synthase of (Chs1) in the Traditional Chinese Medicine Systems Pharmacology database, comprising 14,249 compounds.

Optimized Interface Engineering Enhances Carrier and Phonon Scattering for Superior Thermoelectric Performance in Yb-Filled Skutterudites.

Thermoelectric (TE) performance in materials is often constrained by the strong coupling between carrier and phonon transport, necessitating trade-offs between electrical and thermal properties that limit improvements in the figure of merit (). Herein, a novel strategy is proposed to achieve simultaneous energy filtering and enhanced phonon scattering, effectively optimizing the TE properties of CoSb-based skutterudites. By introducing CuTe nanoprecipitates into the YbCoSb matrix, interfacial barriers are formed, which selectively filter low-energy charge carriers, significantly improving the Seebeck coefficient while maintaining high carrier mobility.

Lattice defect engineering advances n-type PbSe thermoelectrics.

Te-free thermoelectrics have garnered significant interest due to their immense thermoelectric potential and low cost. However, most Te-free thermoelectrics have relatively low performance because of the strong electrical and thermal transport conflicts and unsatisfactory compatibility of interfaces between device materials. Here, we develop lattice defect engineering through Cu doping to realize a record-high figure of merit of ~1.

Enhancing Wheat Spike Counting and Disease Detection Using a Probability Density Attention Mechanism in Deep Learning Models for Precision Agriculture.

This study aims to improve the precision of wheat spike counting and disease detection, exploring the application of deep learning in the agricultural sector. Addressing the shortcomings of traditional detection methods, we propose an advanced feature extraction strategy and a model based on the probability density attention mechanism, designed to more effectively handle feature extraction in complex backgrounds and dense areas. Through comparative experiments with various advanced models, we comprehensively evaluate the performance of our model.

Federated cross-view e-commerce recommendation based on feature rescaling.

As big data technologies continue to evolve, recommendation systems have found broad application in domains such as online retail and social networking platforms. However, centralized recommendation systems raise numerous data privacy concerns. Federated learning addresses these concerns by allowing model training on client devices and aggregating model parameters without sharing raw data.

Environmental Effects on the Interfacial Chemical Reactions at RTV Silicone-Silica Interfaces.

Silicone sealants and adhesives are extensively used in construction, automotive, industrial, and electronic applications because they exhibit excellent mechanical properties, strong adhesion, and good weather resistance. Room-temperature vulcanized (RTV) silicones develop good adhesion to many substrates and do not require heat for curing, which leads to flexible use in many applications. Although it is known that various factors such as relative humidity and temperature affect the curing of the RTV silicone adhesives, the interfacial chemistry that occurs during the curing process is still poorly understood but critical for success in adhesive applications.

A dynamic receptive field and improved feature fusion approach for federated learning in financial credit risk assessment.

Federated Learning (FL) uses local data to perform distributed training on clients and combines resulting models on a public server to mitigate privacy exposure by avoiding data sharing. However, further research indicates that communication overheads continue to be the primary limitation for FL relative to alternative considerations. This is especially true when training models on non-independent and identically distributed data, such as financial default risk data, where FL's computational costs increase significantly.

Integration of Diffusion Transformer and Knowledge Graph for Efficient Cucumber Disease Detection in Agriculture.

In this study, a deep learning method combining knowledge graph and diffusion Transformer has been proposed for cucumber disease detection. By incorporating the diffusion attention mechanism and diffusion loss function, the research aims to enhance the model's ability to recognize complex agricultural disease features and to address the issue of sample imbalance efficiently. Experimental results demonstrate that the proposed method outperforms existing deep learning models in cucumber disease detection tasks.

Analysis of the Tensile Properties and Probabilistic Characteristics of Large-Tow Carbon Fiber-Reinforced Polymer Composites.

Large-tow carbon fiber-reinforced polymer composites (CFRP) have great application potential in civil engineering due to their low price, but their basic mechanical properties are still unclear. The tensile properties of large-tow CFRP rods and plates were investigated in this study. First, the tensile properties of unidirectional CFRP rods and plates were studied, and the test results of the relevant mechanical properties were statistically analyzed.

U-shaped convolutional transformer GAN with multi-resolution consistency loss for restoring brain functional time-series and dementia diagnosis.

Introduction: The blood oxygen level-dependent (BOLD) signal derived from functional neuroimaging is commonly used in brain network analysis and dementia diagnosis. Missing the BOLD signal may lead to bad performance and misinterpretation of findings when analyzing neurological disease. Few studies have focused on the restoration of brain functional time-series data.

Promoted Na Solubility and Modified Band Structure for Achieving Exceptional Average by Extra Mn Doping in PbTe.

Na doping strategy provides an effective avenue to upgrade the thermoelectric performance of PbTe-based materials by optimizing electrical properties. However, the limited solubility of Na inherently restricts the efficiency of doping, resulting in a relatively low average , which poses challenges for the development and application of subsequent devices. Herein, to address this issue, the introduced spontaneous Pb vacancies and additional Mn doping synergistically promote Na solubility with a further modified valence band structure.

Multifunctional GeMnTe Synergistically Optimizes Thermoelectric Properties of SnTe-InTe Alloys.

SnTe-InTe alloys ensure excellent electrical properties in the whole temperature region due to the resonant level. Nevertheless, temperature-sensitive resonance states and single phonon scattering restrict further improvement of thermoelectric performance. Consequently, it is anticipated that additional electrically independent scattering sources should be introduced to impede phonon transport.

A model-driven approach for fast modeling of three-dimensional laser point cloud in large substation.

Using point cloud to reconstruct the 3D model of a substation is crucial for smart grid operation. Its main objective is to swiftly capture equipment point cloud data and align each device's model within the large and noisy point cloud scene of the substation. However, substation reconstruction needs improvement due to the low efficiency of traditional noise-resistant clustering methods and challenges in accurately classifying similar-looking electrical equipment.

Band engineering enhances thermoelectric performance of Ag-doped SnSe.

Ag doping can effectively increase the carrier concentration of-type SnSe polycrystalline, thereby enhancing the thermoelectric (TE) performance. However, the key role of the transport valence band in Ag-doped SnSe remains unclear. Particularly, understanding the influence of evaluating the optimal balance between band convergence and carrier mobility on weighted mobility is a primary consideration in designing high-performance TE materials.

Hybrid mesh for magnetotelluric forward modeling based on the finite element method.

Unstructured tetrahedral grids have been applied in magnetotelluric (MT) forward modeling using the finite element (FE) method because of their adaptability to complex anomalies. However, high-quality results require an extreme refinement of the near-surface area, which leads to excessive meshes and an increased degree of freedom (DoF) of the governing equation of the finite element system. To reduce the computational cost, we have developed a hybrid mesh based on triangular prisms and tetrahedrons.

Reversible Thermoresponsive Peptide-PNIPAM Hydrogels for Controlled Drug Delivery.

Mixed thermoreversible gels were successfully fabricated by the addition of a thermosensitive polymer, poly(-isopropylacrylamide) (PNIPAM), to fibrillar nanostructures self-assembled from a short peptide IK. When the temperature was increased above the lower critical solution temperature of the PNIPAM, the molecules collapsed to form condensed globular particles, which acted as cross-links to connect different peptide nanofibrils and freeze their movements, resulting in the formation of a hydrogel. Since these processes were physically driven, such hydrogels could be reversibly switched between the sol and gel states as a function of temperature.

Enzyme-Triggered Morphological Transition of Peptide Nanostructures for Tumor-Targeted Drug Delivery and Enhanced Cancer Therapy.

The use of smart drug carriers to realize cancer-targeted drug delivery is a promising method to improve the efficiency of chemotherapy and reduce its side effects. A surfactant-like peptide, Nap-FFGPLGLARKRK, was elaborately designed for cancer-targeted drug delivery based on an enzyme-triggered morphological transition of the self-assembled nanostructures. The peptide has three functional motifs: the aromatic motif of Nap-FF- to promote peptide self-assembly, the enzyme-cleavable segment of -GPLGLA- to introduce enzyme sensitivity, and the positively charged -RKRK- segment to balance the molecular amphiphilicity as well as to facilitate interaction with cell membranes.

Super-Resolution Fluorescence Microscopy Study of the Production of K1 Capsules by Escherichia coli: Evidence for the Differential Distribution of the Capsule at the Poles and the Equator of the Cell.

The production of Escherichia coli K1 serotype capsule was investigated using direct stochastic optical reconstruction microscopy with live bacteria and graphene oxide-coated coverslips, overcoming many morphological artifacts found in other high-resolution imaging techniques. Super-resolution fluorescence images showed that the K1 capsular polysaccharide is not uniformly distributed on the cell surface, as previously thought. These studies demonstrated that on the cell surfaces the K1 capsule at the poles had bimodal thicknesses of 238 ± 41 and 323 ± 62 nm, whereas at the equator, there was a monomodal thickness of 217 ± 29 nm.

Coadsorption of a Monoclonal Antibody and Nonionic Surfactant at the SiO/Water Interface.

During the formulation of therapeutic monoclonal antibodies (mAbs), nonionic surfactants are commonly added to attenuate structural rearrangement caused by adsorption/desorption at interfaces during processing, shipping, and storage. We examined the adsorption of a mAb (COE-3) at the SiO/water interface in the presence of pentaethylene glycol monododecyl ether (CE), polysorbate 80 (PS80-20EO), and a polysorbate 80 analogue with seven ethoxylates (PS80-7EO). Spectroscopic ellipsometry was used to follow COE-3 dynamic adsorption, and neutron reflection was used to determine interfacial structure and composition.

Quenched Stochastic Optical Reconstruction Microscopy (qSTORM) with Graphene Oxide.

Quenched Stochastic Optical Reconstruction Microscopy (qSTORM) was demonstrated with graphene oxide sheets, peptides and bacteria; a method of contrast enhancement with super-resolution fluorescence microscopy. Individual sheets of graphene oxide (GO) were imaged with a resolution of 16 nm using the quenching of fluorescence emission by GO via its large Resonant Energy Transfer (RET) efficiency. The method was then extended to image self-assembled peptide aggregates (resolution 19 nm) and live bacterial cells (resolution 55 nm, the capsular structure of E.

Graphene Oxide-Assisted Accumulation and Layer-by-Layer Assembly of Antibacterial Peptide for Sustained Release Applications.

Fabrication of antibacterial materials with sustained release of active components is of great importance for long-term antibacterial applications. Graphene oxide (GO) has been found to be an excellent carrier for accumulating the antibacterial peptide of G(IIKK)I-NH and mediating its loading into the layer-by-layer (LBL) films for sustained release applications. G(IIKK)I-NH takes random coiled conformation in monomeric state below 0.