L-theanine, a non-protein amino acid naturally occurring in tea leaves, is recognized for its antioxidant, anti-inflammatory, and neuroprotective properties. Despite its known benefits, the mechanisms by which L-theanine influences lifespan extension remain poorly understood. This study investigated the effects of L-theanine on the lifespan of Caenorhabditis elegans and explored the underlying mechanisms. Our findings indicate that L-theanine significantly diminishes the accumulation of advanced glycation end products (AGEs), which are biomarkers closely linked to aging and age-related diseases. Through an AGE-level analysis, we observed that L-theanine, when administered during early adulthood, notably extended the lifespan of Caenorhabditis elegans under both normal and high-glucose-induced stress conditions. L-theanine enhanced the lifespan under typical conditions and provided protective effects against high-glucose-induced stress. A further analysis demonstrated that L-theanine extends the lifespan of Caenorhabditis elegans by modulating the DAF-2/DAF-16 insulin-like signaling pathway and reducing the accumulation of advanced glycation end products (AGEs). In summary, this study identified L-theanine as a potential anti-aging intervention that extends the lifespan by reducing AGE accumulation and regulating insulin-like signaling pathways. These findings provide new insights for developing anti-aging strategies and lay the groundwork for further research on the potential benefits of L-theanine in mammals. Future studies could explore the molecular mechanisms, test L-theanine in mammalian models, and assess the long-term side effects.

The identification of hazardous chemicals is critical for mitigating environmental and health risks, yet existing methods often lack efficiency and accuracy. This study presents HazChemNet, a deep learning model integrating attention-based autoencoders and mixture-of-experts architectures, designed to predict chemical hazardousness from molecular structures. The study utilized a dataset of 2428 hazardous compounds from China’s 2015 hazardous chemical list. Features were derived from molecular fingerprints and physicochemical descriptors, with external validation on 52 unseen chemicals achieving 92.3% accuracy for hazardous and 84.6% for non-hazardous classifications. Experimental validation using C. elegans assays confirmed model predictions for critical compounds. Ablation studies confirmed hydrogen bonding features as pivotal predictors, alongside molecular fingerprints. This work bridges the gap between AI-driven innovation and chemical safety, offering a transformative tool for sustainable industrial practices and proactive risk management in a rapidly evolving global landscape.