Oxidative stress is a state of imbalance between the process of producing and removing reactive oxygen species (ROS). With advancing age or in certain situations where oxidative stress cannot be combated, various pathologies such as inflammatory bowel diseases or neoplasia may occur. Over the past decade, a surge of intriguing discoveries has linked subtoxic levels of oxidative stress to key processes, including the maintenance of mucosal homeostasis, regulation of protective inflammation, and even the control of tissue wound healing. Given the complexity and limited understanding of oxidative mechanisms involved in human intestinal pathology, the relevance of experimental models becomes a critical consideration in efforts to elucidate these processes. Although diverse, none of these models fully replicate human digestive pathology; however, they remain valuable for developing new therapeutic strategies. This paper examines the main markers of oxidative stress and its mechanism and their impact on the intestinal tract, as well as the most widely used animal models that have contributed valuable insights into the pathogenesis of inflammatory bowel diseases (IBD).

Background/Objectives: Convolutional Neural Networks (CNNs) and advanced image pre-processing can enhance the classification of antioxidant effects applied on zebrafish intestine. This study proposes a hybrid technique that combines four deep learning (DL) models: the pre-trained Xception CNN, a custom-built autoencoder, a custom-built CNN, and a Vision Transformer (ViT). Methods: For classification features generated by DL models, the Support Vector Machine (SVM), Random Forest (RF), and k-Nearest Neighbors (kNN) algorithms were proposed. Contrast-Limited Adaptive Histogram Equalization (CLAHE) and the mentioned DL artificial intelligence (AI) algorithms were applied to improve the accuracy of the classification of histological images of zebrafish intestinal morphology. Results: In a binary classification, the following classes were studied on zebrafish intestine: (i) control and experimental-induced oxidative stress (OS); (ii) OS versus OS and theobromine (TB); and (iii) OS versus OS and caffeine (CAF). The novelty of the research lies in applying CLAHE to enhance image quality and utilizing four hybrid models to improve classification accuracy compared to raw images, when a private dataset of zebrafish intestine histology under certain chemical treatments (OS, TB, CAF) was employed. Conclusions: The best results are obtained in a binary classification with a hybrid combination of Xception and SVM for OS versus OS and TB classes, with an accuracy of 84.6% for pre-processed images, better than raw images, when the accuracy was 78.4%.

Background and Objectives: Oxidative stress plays a central role in numerous pathological and toxicological processes, and in vivo investigations are essential for understanding integrated systemic responses. Methylxanthines have been reported to modulate redox homeostasis through multiple mechanisms, but their effects in aquatic vertebrate models under metal nanoparticle-induced oxidative stress remain poorly characterized. Materials and Methods: In the present study, adult zebrafish were exposed for 15 days to ZnO nanoparticles (0.69 mg/L) as a pro-oxidant model, and to methylxanthines (caffeine, theobromine, theophylline; 50 mg/L). Oxidative stress biomarkers were assessed by measuring the levels of glutathione peroxidase 1 (GPx1), catalase (CAT), superoxide dismutase (SOD), and reduced glutathione (GSH) in whole-body homogenates using ELISA. Complementary molecular docking was performed to investigate methylxanthine–enzyme interactions. Results: The most substantial change was observed for SOD level, which significant increased compared to the control group (from 0.122 to 1.090 ng/g; p = 0.001), followed by CAT, which rose from 38.3 pg/g to 100.8 pg/g; p = 0.001), and GPX1 which increased from 84.3 pg/g to 142.2 pg/g; p = 0.011). In parallel, GSH levels decreased by 58.7% (p = 0.001). Co-exposure to methylxanthines significantly modulated the ZnO-NPs exposure response, by mitigating the increase in antioxidant enzyme levels and restoring glutathione. Among the tested compounds, theobromine exerted the strongest protective effect on GPx1 and GSH and caffeine primarily influenced CAT and SOD, whereas theophylline showed overall weaker responses. The molecular docking investigation indicated that all tested methylxanthines can attach to different cavities of the antioxidant enzymes. Theophylline and theobromine established hydrogen bonds and π-stacking interactions with the interfacing amino acids, potentially contributing to the modulation of enzymes stabilization and function under physiological conditions. Conclusions: ZnO-NPs trigger a robust systemic response in zebrafish, whereas methylxanthines display distinct compound-specific modulating effects.