When classifying breeds of dogs, the accuracy of classification significantly affects breed identification and dog research. Using images to classify dog breeds can improve classification efficiency; however, it is increasingly challenging due to the diversities and similarities among dog breeds. Traditional image classification methods primarily rely on extracting simple geometric features, while current convolutional neural networks (CNNs) are capable of learning high-level semantic features. However, the diversity of dog breeds continues to pose a challenge to classification accuracy. To address this, we developed a model that integrates multiple CNNs with a machine learning method, significantly improving the accuracy of dog images classification. We used the Stanford Dog Dataset, combined image features from four CNN models, filtered the features using principal component analysis (PCA) and gray wolf optimization algorithm (GWO), and then classified the features with support vector machine (SVM). The classification accuracy rate reached 95.24% for 120 breeds and 99.34% for 76 selected breeds, respectively, demonstrating a significant improvement over existing methods using the same Stanford Dog Dataset. It is expected that our proposed method will further serve as a fundamental framework for the accurate classification of a wider range of species.

The Resource for Coronavirus 2019 (RCoV19) is an open-access information resource dedicated to providing valuable data on the genomes, mutations, and variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In this updated implementation of RCoV19, we have made significant improvements and advancements over the previous version. Firstly, we have implemented a highly refined genome data curation model. This model now features an automated integration pipeline and optimized curation rules, enabling efficient daily updates of data in RCoV19. Secondly, we have developed a global and regional lineage evolution monitoring platform, alongside an outbreak risk pre-warning system. These additions provide a comprehensive understanding of SARS-CoV-2 evolution and transmission patterns, enabling better preparedness and response strategies. Thirdly, we have developed a powerful interactive mutation spectrum comparison module. This module allows users to compare and analyze mutation patterns, assisting in the detection of potential new lineages. Furthermore, we have incorporated a comprehensive knowledgebase on mutation effects. This knowledgebase serves as a valuable resource for retrieving information on the functional implications of specific mutations. In summary, RCoV19 serves as a vital scientific resource, providing access to valuable data, relevant information, and technical support in the global fight against COVID-19. The complete contents of RCoV19 are available to the public at https://ngdc.cncb.ac.cn/ncov/.

The severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) has evolved many high‐risk variants, resulting in repeated COVID‐19 waves over the past years. Therefore, accurate early warning of high‐risk variants is vital for epidemic prevention and control. However, detecting high‐risk variants through experimental and epidemiological research is time‐consuming and often lags behind the emergence and spread of these variants. In this study, HiRisk‐Detector a machine learning algorithm based on haplotype network, is developed for computationally early detecting high‐risk SARS‐CoV‐2 variants. Leveraging over 7.6 million high‐quality and complete SARS‐CoV‐2 genomes and metadata, the effectiveness, robustness, and generalizability of HiRisk‐Detector are validated. First, HiRisk‐Detector is evaluated on actual empirical data, successfully detecting all 13 high‐risk variants, preceding World Health Organization announcements by 27 days on average. Second, its robustness is tested by reducing sequencing intensity to one‐fourth, noting only a minimal delay of 3.8 days, demonstrating its effectiveness. Third, HiRisk‐Detector is applied to detect risks among SARS‐CoV‐2 Omicron variant sub‐lineages, confirming its broad applicability and high ROC‐AUC and PR‐AUC performance. Overall, HiRisk‐Detector features powerful capacity for early detection of high‐risk variants, bearing great utility for any public emergency caused by infectious diseases or viruses.

Background: The homeobox gene 5 (HOXB5) encodes a transcription factor that regulates the embryonic development of the central nervous system. Notably, its expression pattern and prognostic role in glioma remain unelucidated. Methods: This study identified the relationship between HOXB5 and glioma by investigating HOXB5 expression data from The Cancer Genome Atlas and the Genotype Tissue Expression databases and validating the obtained data using the Chinese Glioma Genome Atlas database. Western blots were used to identify HOXB5 expression levels in glioma cells and clinical samples. Kaplan–Meier and multivariate Cox regression analyses were performed to assess the prognostic value of HOXB5. The key functions and signaling pathways related to HOXB5 were analyzed using GO, KEGG, and GSEA. Immune infiltration was calculated using the microenvironment cell populations-counter, estimate the proportion of immune and cancer, and ESTIMATE algorithms. Results: The expression of HOXB5 was upregulated in glioma and generally increased with malignancy. HOXB5 was an independent prognostic factor for glioma patients. A nomogram was further built that integrated HOXB5, and it showed stratifying prediction accuracy and efficiency. HOXB5 was associated with the regulation of cell growth, endothelial cell growth, and the IL-6/JAK-STAT3 pathway, and was determined to possibly promote stomatal specimen enrichment and angiogenesis. Conclusion: HOXB5 protein is overexpressed in glioma and might serve as a good predictive factor of this disease.

Influenza A virus (IAV) poses a persistent threat to global public health due to its broad host adaptability, frequent anti-genic variation, and potential for cross-species transmission. Accurate identification of IAV subtypes is essential for effective epidemic surveillance and precise disease control. Here, we present Influ-BERT, a domain-adaptive pretrained model based on the Transformer architecture. Optimized from DNABERT-2, Influ-BERT was developed using a dedicated corpus of ~900 000 influenza genome sequences. We constructed a custom Byte Pair Encoding tokenizer, and employed a two-stage training strategy involving domain-adaptive pretraining followed by task-specific fine-tuning. This approach significantly enhanced identification performance for IAV subtypes. Experimental results demonstrate that Influ-BERT outperforms both traditional machine learning approaches and general genomic language models, such as DNABERT-2, Necleotide Transformer, and MegaDNA, in the task of IAV subtype identification. The model consistently achieved F1-scores above 97% across five subtype classification tasks and exhibited stable performance gains for subtypes that are underrepresented in sequencing data, including H5N8, H1N2, and H13N6. Beyond subtype identification, Influ-BERT was successfully applied to additional tasks including respiratory virus identification, IAV pathogenicity prediction, and identification of IAV genomic fragments and functional genes, demonstrating robust performance throughout. Further interpretability analysis using sliding window perturbation confirmed that the model focuses on biologically significant genomic regions, providing insight into its improved predictive capability.

A transition-metal-free synthesis of 1-pyrroline derivatives via the cyclization of terminal alkynes with 2-azaallyls is presented, which provides an efficient method for the synthesis of medicinally polysubstituted and functionalized pyrrolines.