Comprehensive Assessment of BERT-Based Methods for Predicting Antimicrobial Peptides.

In recent years, the prediction of antimicrobial peptides (AMPs) has gained prominence due to their high antibacterial activity and reduced susceptibility to drug resistance, making them potential antibiotic substitutes. To advance the field of AMP recognition, an increasing number of natural language processing methods are being applied. These methods exhibit diversity in terms of pretraining models, pretraining data sets, word vector embeddings, feature encoding methods, and downstream classification models.

Sulfonated Azocalix[4]arene: A Universal and Effective Taste-Masking Agent.

Many active pharmaceutical ingredients have a specific bitter taste. To enhance patient compliance and treatment efficacy, taste-masking agents are crucial in oral drug formulations. Confronting numerous bitter drug molecules with varied structures, the pharmaceutical field strives to explore and develop universal and effective masking approaches.

Calixarene-Based Supramolecular Sensor Array for Pesticide Discrimination.

The identification and detection of pesticides is crucial to protecting both the environment and human health. However, it can be challenging to conveniently and rapidly differentiate between different types of pesticides. We developed a supramolecular fluorescent sensor array, in which calixarenes with broad-spectrum encapsulation capacity served as recognition receptors.

Supramolecular 3 in 1: A Lubrication and Co-Delivery System for Synergistic Advanced Osteoarthritis Therapy.

The complexity, heterogeneity, and drug resistance of diseases necessitate a shift in therapeutic paradigms from monotherapy to combination therapy, which could augment treatment efficiency. Effective treatment of advanced osteoarthritis (OA) requires addressing three key factors contributing to its deterioration: chronic joint inflammation, lubrication dysfunction, and cartilage-tissue degradation. Herein, we present a supramolecular nanomedicine of multifunctionality via molecular recognition and self-assembly.

Coupling Reliable Interfacial Carrier Migration Channels with Visible-Light Response Antennas in ZnO-Based Heterostructure for Ameliorated Photocatalytic Hydrogen Generation.

Engineering targeted and reliable charge transfer pathways in multiphase photocatalysts remains a challenge. Herein, we conceptualize the Cd@CdS-ZnO/reduced graphene oxide (rGO)/ZnS heterostructures coupled with reliable carrier migration channels and visible-light response antennas by building rGO-integrated electrochemical nanoreactors and an ion-exchange process. In this ternary catalyst, the Cd clusters and rGO perform as charge relays to boost carrier transport via the Z-scheme route and accelerate photogenerated carriers to react with surface-adsorbed substances.

Causing Leaf Rust on in China.

Thistle, Cirsium setosum (Willd.) M. Bieb.

Supramolecular Integration of Multifunctional Nanomaterial by Mannose-Decorated Azocalixarene with Ginsenoside Rb1 for Synergistic Therapy of Rheumatoid Arthritis.

The complexity and progressive nature of diseases require the exploitation of multifunctional materials. However, introducing a function inevitably increases the complexity of materials, which complicates preparation and decreases reproducibility. Herein, we report a supramolecular integration of multifunctional nanomaterials based on mannose-modified azocalix[4]arene (ManAC4A) and ginsenoside Rb1 (Rb1), which showed advances of simplicity and reproducibility.

Multi-Modal Vehicle Trajectory Prediction by Collaborative Learning of Lane Orientation, Vehicle Interaction, and Intention.

Accurate trajectory prediction is an essential task in automated driving, which is achieved by sensing and analyzing the behavior of surrounding vehicles. Although plenty of research works have been invested in this field, it is still a challenging subject due to the environment's complexity and the driving intention uncertainty. In this paper, we propose a joint learning architecture to incorporate the lane orientation, vehicle interaction, and driving intention in vehicle trajectory forecasting.

Deep learning segmentation of glomeruli on kidney donor frozen sections.

Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution ( ) and at external institutions ( ) were used in this study.

Screening of dominant strains in red sour soup from Miao nationality and the optimization of inoculating fermentation conditions.

Red sour soup is a traditional fermented product in southwest China. Currently, the existing production process mainly adopts the method of natural fermentation, with long fermentation cycles and poor stability between batches. Rapid establishment of dominant strains can accelerate the formation of lactic acid, which can inhibit the growth of miscellaneous bacteria.

Dynamics of microbial communities, texture and flavor in Suan zuo yu during fermentation.

Suan zuo yu is a traditional Chinese fermented product. We explored the microbial diversity, the dynamic changes of texture and flavor compounds at different fermentation times (up to 24 d). Results showed that Weissella and Lactobacillus may play a vital role in fermentation especially for the flavor.

Data-Driven Calibration of Soil Moisture Sensor Considering Impacts of Temperature: A Case Study on FDR Sensors.

Commercial soil moisture sensors have been widely applied into the measurement of soil moisture content. However, the accuracy of such sensors varies due to the employed techniques and working conditions. In this study, the temperature impact on the soil moisture sensor reading was firstly analyzed.

Discriminative dictionary learning for abdominal multi-organ segmentation.

An automated segmentation method is presented for multi-organ segmentation in abdominal CT images. Dictionary learning and sparse coding techniques are used in the proposed method to generate target specific priors for segmentation. The method simultaneously learns dictionaries which have reconstructive power and classifiers which have discriminative ability from a set of selected atlases.

Geodesic patch-based segmentation.

Label propagation has been shown to be effective in many automatic segmentation applications. However, its reliance on accurate image alignment means that segmentation results can be affected by any registration errors which occur. Patch-based methods relax this dependence by avoiding explicit one-to-one correspondence assumptions between images but are still limited by the search window size.