Background/Objectives: Dietary composition and physical activity are major determinants of gut microbiome structure, and dysbiosis is strongly associated with metabolic disorders. While both diet and exercise independently influence the gut microbiome, their interactive effects—particularly across different exercise modalities—remain incompletely understood. This study investigated the combined effects of diet type (normal chow [NC] vs. high-fat diet [HFD]) and exercise modality (control [C], voluntary [V], and forced [F]) on gut microbiota composition in rats. Methods: Sixty-three Wistar rats were randomized into six groups according to diet and exercise status. Fecal samples were collected and analyzed using full-length 16S rRNA gene sequencing (Oxford Nanopore Technologies). Alpha and beta diversity metrics were calculated, and taxonomic composition was assessed at phylum and genus levels. Results: HFD groups exhibited significantly higher alpha diversity than NC groups (Shannon index: 3.47–3.63 vs. 2.76–2.94, p < 0.001), with forced exercise associated with a greater diversity than voluntary exercise. Beta-diversity analysis confirmed diet as the dominant factor influencing microbial structure (PERMANOVA p = 0.001), with exercise providing an additional modulatory effect. Firmicutes, Bacteroidota, Deferribacterota, and Proteobacteria predominated, with Firmicutes decreasing under HFD. Forced exercise significantly enriched beneficial genera, including Akkermansia (detected exclusively in exercised HFD groups; p = 0.03), Blautia, Coprococcus, and Roseburia. Akkermansia abundance correlated positively with exercise distance (p < 0.001) and negatively with body weight (p < 0.01). Conclusions: Structured exercise, particularly forced treadmill training, attenuates HFD-associated dysbiosis and promotes the beneficial gut bacteria that is associated with metabolic health. These findings highlight exercise modality as a critical factor in dietary strategies targeting gut microbiome modulations.

Zebrafish (Danio rerio) are widely used in biomedical research due to their genetic similarity to humans and rapid development. Efficient management of large embryo populations is essential for experimental reproducibility and high-throughput screening, yet manual counting and sorting methods are labor-intensive, time-consuming, and pose ergonomic risks including musculoskeletal disorders. We evaluated a commercially available AI-powered automated embryo sorting system against manual methods across 117,956 embryos to assess efficiency, accuracy, and reliability in operational facility conditions. The automated system performed simultaneous counting and quality classification at 17.3 embryos/min, while manual counting alone achieved 24.5–25.9 embryos/min (p < 0.001). The automated system provided one-pass processing convenience, though at lower instantaneous throughput than manual counting. With significant ergonomic benefits. However, performance analysis revealed 13.41% systematic undercounting (p = 0.004), limited correlation between automated classifications and developmental outcomes (survival, hatching, deformity rates p > 0.05), and 50.8% false negative rate for GFP fluorescence detection in transgenic embryos. These limitations reflect the current state of machine learning algorithm training rather than fundamental technological constraints. The system’s AI architecture enables continuous improvement as algorithms encounter diverse embryo populations and incorporate user feedback through customizable training platforms. Our large-scale operational evaluation provides quantitative performance benchmarks for facilities considering automation adoption and contributes valuable real-world training data for algorithm refinement. We recommend context-dependent implementation: automated processing for high-volume routine workflows where speed and ergonomic benefits are prioritized, combined with manual validation for transgenic line maintenance and accuracy-critical applications. As an early-generation commercial platform with machine learning at its core, the system demonstrates clear improvement pathways through expanded training datasets and user-contributed algorithm optimization.