Search

Since the camouflage object is highly similar to the surrounding environment with a rather small size,the general detection algorithm is not fully applicable to the camouflaged object detection task,which makes the detection of camouflaged object more challenging than the general detection task.In order to solve this problem,the existing methods are analyzed in this paper and a detection algorithm for camouflage object is proposed based on the YOLO v5 algorithm.A new feature extraction network combined with attention mechanism is designed to highlight the feature information of the camouflage target.The original path aggregation network is improved so that the high,middle and lowly level feature map information is fully fused.The semantic information of the target is strengthened by nonlinear pool module,and the detection feature map size is increased to improve the detection recall rate of the small size target.On a public camouflage target dataset,the proposed algorithm is tested with 7 algorithms.The mAP of the proposed algorithm is 4.4% higher than that of the original algorithm,while the recall rate has improved 2.8%,which verifies the effectiveness of the algorithm for camouflaged object detection and the great advantage in accuracy compared with other algorithms.

Motivation Target discovery is a crucial step in drug development, as it directly affects the success rate of clinical trials. Knowledge graphs (KGs) offer unique advantages in processing complex biological data and inferring new relationships. Existing biomedical KGs primarily focus on tasks such as drug repositioning and drug–target interactions, leaving a gap in the construction of KGs tailored for target discovery. Results We established a comprehensive biomedical KG focusing on target discovery, termed TarKG, by integrating seven existing biomedical KGs, nine public databases, and traditional Chinese medicine knowledge databases. TarKG consists of 1 143 313 entities and 32 806 467 relations across 15 entity categories and 171 relation types, all centered around 3 core entity types: Disease, Gene, and Compound. TarKG provides specialized knowledges for the core entities including chemical structures, protein sequences, or text descriptions. By using different KG embedding algorithms, we assessed the knowledge completion capabilities of TarKG, particularly for disease–target link prediction. In case studies, we further examined TarKG's ability to predict potential protein targets for Alzheimer's disease (AD) and to identify diseases potentially associated with the metallo-deubiquitinase CSN5, using literature analysis for validation. Furthermore, we provided a user-friendly web server (https://tarkg.ddtmlab.org) that enables users to perform knowledge retrieval and relation inference using TarKG. Availability and implementation TarKG is accessible at https://tarkg.ddtmlab.org. [ABSTRACT FROM AUTHOR]

Named entity recognition serves as an important foundation for many downstream tasks in the field of natural language processing. As an important international language, Chinese is unique in many aspects. Traditionally, models of Chinese named entity recognition tasks use sequence labeling mechanisms that require conditional random fields to capture label dependencies. However, this approach is prone to misclassification of labels. Aiming at this problem, a span-based named entity recognition model called RIB-NER is proposed. Firstly, the method provides character-level embedding through RoBERTa as a model embedding layer to obtain more contextual semantic and lexical information. Secondly, IDCNN is used to increase the position information between words with parallel convolution kernels, so that the connection between words is closer. At the same time, a BiLSTM network is integrated in the model to obtain context information. Finally, a Biaffine model is employed to score the start and end tokens in the sentence, and these tokens are used to explore spans. The proposed algorithm is tested on MSRA and Weibo corpora, the results show that it can accurately identify entity boundaries, achieving F1 scores of 95.11% and 73.94% respectively. Compared with traditional deep learning approaches, it demonstrates better recognition performance. [ABSTRACT FROM AUTHOR]

This paper aims at the problem that the fall irrigation quota of drip irrigation farmland under mulch cannot be effectively determined due to the extremely uneven spatial distribution of water and salt and the significant effects of freezing and thawing in the seasonal freeze-thaw area. In response to this problem, based on the field experiment data, this paper uses the joint simulation method of HYDRUS- 2D and SHAW model to simulate the soil water and salt dynamics under different autumn irrigation quotas under the conditions of the Yellow River water irrigation, and studies the single and multi-year autumn irrigation quota of drip irrigation farmland under mulch. The results show that: * When the single year autumn irrigation is conducted, for mildly saline soil, the recommended autumn irrigation quota is 1 100 m³/hm²; for moderately saline soil, the recommended autumn irrigation quota is 2 100 m³/hm²; for heavily saline soil, the recommended autumn irrigation quota is 2 500 m³/hm² when only for the purpose of improving soil quality. * When irrigating in autumn every few years, the non-saline soil should be irrigated in autumn at least once every 3 years. The recommended autumn irrigation quota is 2 000 m³/hm² for irrigation every three years, and the recommended autumn irrigation quota is 1 350 m³/hm² for irrigation every two years. The soil with mild, moderate and severe salinization must be irrigated in autumn every year. [ABSTRACT FROM AUTHOR]

The E69K mutation is one of the most frequent protein tyrosine phosphatase-2 (SHP2) mutations in leukemia, and it can cause the increase in the protein activity. Recent studies have shown that the E69K mutation was fairly sensitive to the allosteric inhibitor of SHP2 (SHP099). However, the molecular mechanism of the allosteric drug SHP099 inhibiting SHP2E69K remains unclear. Thus, the molecular dynamic simulations and the post-dynamics analyses (RMSF, PCA, DCCM, RIN and the binding free energies) for SHP2WT, SHP2WT-SHP099, SHP2E69K and SHP2E69K-SHP099 were carried out, respectively. Owing to the strong binding affinity of SHP099 to residues Thr219 and Arg220, the flexibility of linker region (residues Val209-Arg231) was reduced. Moreover, the presence of SHP099 kept the autoinhibition state of the SHP2 protein through enhancing the interactions between the linker region and Q loop in PTP domain, such as Thr219/Val490, Thr219/Asn491, Arg220/Ile488 and Leu254/Asn491. In addition, it was found that the residues (Thr219, Arg220, Leu254 and Asn491) might be the key residues responsible for the conformational changes of protein. Overall, this study may provide an important basis for understanding how the SHP099 effectively inhibited the SHP2E69K activity at the molecular level. [ABSTRACT FROM AUTHOR]

Owing to its unique function to release the progeny virus particles from the surface of an infected cell, neuraminidase has drawn special attention for developing new drugs to treat influenza viruses. The 150-cavity that is adjacent to the active pocket of the group-1 neuraminidase (N1) renders the conformational change from ‘open’ form to ‘closed’ form when enzyme is binding with a ligand. Consequently, it would be a better strategy to design multi-binding-site inhibitors including X and R groups with proper shapes, sizes and electronic charges fitting into the active site. The NCI and ZINC fragment databases were screened for finding the optimal fragments with de novo design technique. By doing so, 24 derivatives of oseltamivir were obtained by linking the fragments at two different sites of the scaffold of oseltamivir. Molecular docking and dynamics showed that these compounds not only adopt more favourable conformation but also have stronger binding interaction with receptor. Most importantly, all compounds skilfully pass through the cleft (formed by Glu119 and Arg156) and fit into 150-cavity. Therefore, the selected 24 derivatives may become promising candidates for treating influenza virus; in addition, the findings reported here may at least provide useful insights and stimulate new strategy in this area. [ABSTRACT FROM AUTHOR]

Groundwater recharge is an important component of the groundwater system. On the North China Plain ( NCP), groundwater is the main water supply. Because of large-scale overexploitation, the water table has declined, which has produced severe adverse effects on the environment and ecosystem. In this article, tracer experiment and watershed model were used to calculate and analyze NCP groundwater recharge. In the tracer experiment, average recharge was 108 mm/year and recharge coefficient 0.16. With its improved irrigation, vegetation coverage and evapotranspiration modules, the INFIL3.0 model was used for calculation of groundwater recharge. Regional modeling results showed an average recharge of 102 mm/year and recharge coefficient 0.14, for 2001-2009. These values are very similar to those from the field tracer experiment. Influences in the two methods were analyzed. The results can provide an important reference for NCP groundwater recharge. [ABSTRACT FROM AUTHOR]