Fruit tree diseases have a great influence on agricultural production. Artificial intelligence technologies have been used to help fruit growers identify fruit tree diseases in a timely and accurate way. In this study, a dataset of 10,000 images of pear black spot, pear rust, apple mosaic, and apple rust was used to develop the diagnosis model. To achieve better performance, we developed three kinds of ensemble learning classifiers and two kinds of deep learning classifiers, validated and tested these five models, and found that the stacking ensemble learning classifier outperformed the other classifiers with the accuracy of 98.05% on the validation dataset and 97.34% on the test dataset, which hinted that, with the small‐ and middle‐sized dataset, stacking ensemble learning classifiers may be used as cost‐effective alternatives to deep learning models under performance and cost constraints.

Based on the BERTopic model, this study analyzes 15,744 scientific papers in the field of functional agriculture from 1995 to 2024 to uncover core themes and evolutionary trends in global functional agriculture, and particularly focuses on revealing the developmental trajectory in China. The results indicate that global functional agriculture research is characterized by diverse themes and intensive study, forming a multi-topic cross-network centered on plant chemical extraction and agricultural soil research, with a focus on food nutrition, human health, and environmental protection. By contrast, China’s functional agriculture research demonstrates a more focused and in-depth approach, concentrating on functional food development and agricultural environmental protection themes, with notable growth trends in areas such as selenium-enriched products and resistant starch. Combined with China’s agricultural development environment, this study makes the following suggestions for the development of functional agriculture in China: (1) Promoting interdisciplinary cooperation between functional agriculture and other technologies. (2) Developing agricultural products with Chinese characteristics and forming Chinese functional agricultural product brands. (3) Utilizing smart farming technology to boost functional agriculture.

Identifying polyphenotype genes that simultaneously regulate important agronomic traits (e.g., plant height, yield, and disease resistance) is critical for developing novel high-quality crop varieties. Predicting the associations between genes and traits requires the organization and analysis of multi-dimensional scientific data. The existing methods for establishing the relationships between genomic data and phenotypic data can only elucidate the associations between genes and individual traits. However, there are relatively few methods for detecting elite polyphenotype genes. In this study, a knowledge graph for traits regulating-genes was constructed by collecting data from the PubMed database and eight other databases related to the staple food crops rice, maize, and wheat as well as the model plant Arabidopsis thaliana. On the basis of the knowledge graph, a model for predicting traits regulating-genes was constructed by combining the data attributes of the gene nodes and the topological relationship attributes of the gene nodes. Additionally, a scoring method for predicting the genes regulating specific traits was developed to screen for elite polyphenotype genes. A total of 125,591 nodes and 547,224 semantic relationships were included in the knowledge graph. The accuracy of the knowledge graph-based model for predicting traits regulating-genes was 0.89, the precision rate was 0.91, the recall rate was 0.96, and the F1 value was 0.94. Moreover, 4,447 polyphenotype genes for 31 trait combinations were identified, among which the rice polyphenotype gene IPA1 and the A. thaliana polyphenotype gene CUC2 were verified via a literature search. Furthermore, the wheat gene TraesCS5A02G275900 was revealed as a potential polyphenotype gene that will need to be further characterized. Meanwhile, the result of venn diagram analysis between the polyphenotype gene datasets (consists of genes that are predicted by our model) and the transcriptome gene datasets (consists of genes that were differential expression in response to disease, drought or salt) showed approximately 70% and 54% polyphenotype genes were identified in the transcriptome datasets of Arabidopsis and rice, respectively. The application of the model driven by knowledge graph for predicting traits regulating-genes represents a novel method for detecting elite polyphenotype genes.

Polyphenols are a diverse group of plant-derived bioactives that have been investigated as multi-target candidates for the potential prevention and management of neurodegenerative diseases (NDDs). We conducted an integrated bibliometric and mechanistic scoping review covering 12 polyphenol classes and seven major NDDs using records from PubMed, Embase, the Cochrane Library, and Web of Science (1940–2024). Research landscapes and emerging themes were mapped using keyword co-occurrence, clustering analyses, and BERTopic modeling. Mechanistic evidence was synthesized across core pathways, including oxidative stress, neuroinflammation, proteostasis (amyloid/tau and α-synuclein), mitochondrial dysfunction, and cholinergic modulation, to link preclinical findings with clinical outcomes. Publication output increased markedly after 2000, with China and the United States contributing the most records. Four persistent hotspots were identified: (1) antioxidant and neuroprotective effects (e.g., resveratrol, curcumin); (2) anti-inflammatory activity and intracellular signaling; (3) cognition, aging, and sex-specific responses in clinical research; and (4) animal models of memory impairment. Clinically investigated interventions include epigallocatechin gallate, Ginkgo biloba extracts, olive/cocoa polyphenols, and flavonoid-rich mixtures; however, limited bioavailability and heterogeneous trial designs constrain the strength of effect estimates. Advances in delivery systems, computational screening, and precision nutrition may improve translation. Overall, polyphenols show multi-target neuroprotective potential, but larger and more standardized clinical trials are needed to support evidence-based nutritional strategies for NDD prevention and management.

Due to the growing expansion of scientific literature and knowledge, access to scholarly contents is becoming more challenging. This paper presents a research profiling framework driven by scientific knowledge graphs (SKGs), which aims at achieving the deep fusion and thorough disclosure of scientific resources and domain knowledge, as well as satisfying the needs of researchers for knowledge overview and acquisition in a reasonable period of time using fine-grained and multi-dimensional profiling scenarios. Further, we conduct the experiment of the SKG construction task on a specific domain by combining scientific literature from Web Of Science and an open knowledge base, and develop a prototype system for user's single entity search to validate the approach, with profile presentations of overall graph view, literature profile, hotness topics list, high-impact experts, and providing a service of profile viewing and download.

In this paper, an overall architecture and service model of cloud service platform of sci-tech information based on cloud computing for agricultural research system were proposed, aiming at promoting the co-construction and sharing among information service institutions in agricultural research system. The platform will integrate resources and services of co-construction institutions into a shared body, and form a new science and technology information service system to provide network infrastructure, resources, platform and various application services for agricultural research system. And through dynamic management and distribution of a variety of services, it will meet the needs of users at different levels, such as institutions, academic teams and individuals and so on.