With the development of artificial intelligence (AI) in complicated imaging and remote sensing technologies, plant research is transitioning from manual measurements to automated data collecting. High-throughput image-based phenotyping enables the precise and automated acquisition of traits across various spatial and temporal scales, ranging from controlled laboratory settings to intricate field. Furthermore, AI facilitates the combination of satellite observations, unmanned aerial vehicle (UAV) imaging, soil and climate data, and spatiotemporal information to enhance the precision of trait monitoring and yield prediction. These advances enhance the ability to evaluate and predict crop performance under variable environmental conditions. This paper offers a cross-disciplinary paradigm for accurate and sustainable modern agriculture by merging AI methodologies with plant phenotyping and yield forecasting.

Background: Traditional genetic mapping has advanced plant trait studies but struggles to capture epistasis, pleiotropy, and genotype-environment (G × E) interactions in genomic prediction (GP). Recently, artificial intelligence (AI) has provided innovative methods. Main body: This review outlines the transition from traditional frameworks to AI-enabled approaches for plant trait analysis. Specifically, major statistical and AI methods are summarized; current strategies for combining genomic, transcriptomic, metabolomic, phenotypic, and environmental data are described; and examinations are carried out over how graph-based and Transformer models represent regulatory networks and higher-order interactions. This paper further explores developments in multi-task learning, cross-population and cross-species transfer, and emerging foundation-style models. Key issues related to interpretability, reproducibility, data quality, and evaluation practices are considered in the context of practical deployment. Conclusion: AI-driven models are reshaping plant trait analysis by extending traditional association methods toward scalable, biologically informed prediction. Continued efforts in data standardization, transparent models, and validation across time and environments will determine the broader impact of these approaches in crop improvement.

Background: The oral cavity harbors a dynamic microbial ecosystem that interacts with epithelial barriers, host immunity, and local tissue environments. Disruption of this balance is increasingly recognized as a key driver of major oral diseases, including periodontitis, dental caries, and oral squamous cell carcinoma (OSCC). However, the biological links between microbial ecology, immune regulation, and disease progression are insufficiently integrated, limiting mechanistic understanding and translational progress. Methods: This structured narrative review searched PubMed/MEDLINE, Web of Science, Embase, and Scopus for relevant studies on oral microbiome ecology, mucosal immunity, dysbiosis, oral diseases, and emerging therapies. Evidence was narratively synthesized across microbiome ecology, mucosal immunology, disease pathogenesis, and translational research, with consideration of study type, mechanistic relevance, and translational significance. Results: Current evidence supports that oral homeostasis relies on coordinated interactions among commensal microbial communities (CMC), epithelial and salivary barriers, and immune surveillance. Dysbiosis disrupts this equilibrium by promoting the expansion of pathobionts, amplifying inflammatory responses, and contributing to tissue injury. This systems-level perspective helps explain the persistence and heterogeneity of oral diseases beyond pathogen-centered models. Emerging technologies are reshaping this field. These include microbiome-modulating therapies, host-directed interventions, multi-omics approaches, and artificial intelligence (AI). These approaches are advancing disease stratification, biomarker discovery, and precision therapeutic development. Conclusion: Oral diseases should be understood as disorders of host-microbiome-immune disequilibrium rather than as isolated infections. This perspective highlights the need for integrated strategies that consider microbial ecology, immune regulation, epithelial barrier function, and clinical context to improve prevention, diagnosis, and treatment in precision oral medicine.

Genetic and molecular studies increasingly explain anesthetic and analgesic responses at the level of defined conductances, neuronal populations, and injury states. Their clinical implications depend on distinguishing target engagement from changes in firing and, ultimately, from a measurable therapeutic effect. This review examines recent evidence linking sodium, potassium, calcium, and sensory transduction channels to pain and inhibitory receptor composition, chloride regulation, and arousal circuits to anesthesia. Selective NaV1.8 inhibition provides an unusually complete translational example, spanning channel pharmacology, recordings from human sensory neurons, and randomized postoperative trials. Nevertheless, residual firing during substantial NaV1.8 inhibition and divergent explanations of NaV1.7-null analgesia show why the effects of a drug cannot be inferred directly from a genetic phenotype. Structural studies now resolve anesthetic binding and gating mechanisms in GABAA, NMDA, and HCN1 channels, while circuit experiments distinguish emergence, immobility, and antinociception. Neuroimmune signaling extends beyond cytokine-driven excitation to include inhibitory synapse removal, sex-dependent cellular pathways, and active pain resolution. Chromatin regulation, RNA modification, and neuronal senescence can stabilize altered excitability after injury. Human ganglion and spinal cord atlases, Patch-seq, and sensory assembloids provide more relevant models for connecting these mechanisms across scales, although none substitute for clinical validation. We emphasize research published from 2021 onward, retaining foundational studies where they establish a causal mechanism. The resulting evidence supports cell- and state-specific intervention rather than a single molecular explanation of anesthesia or chronic pain and identifies practical requirements for translating genetic discovery into perioperative treatment.