J. Geetha

Natural products represent an essential source of bioactive materials with potent biological activity, traditional approaches for their discovery and development remain time consuming and resource-intensive. Recent advances of Artificial Intelligence (AI) and machine learning (ML) are transforming natural product research by enabling predictive modeling, high throughput screening, automated compound identification and integration of complex omics datasets. Other AI and ML methods such as deep learning, neural networks and generative algorithms are enhancing drug discovery by predicting bioactivity and structural elucidation, and optimizing pharmacokinetic properties of natural products. Furthermore, AI, ML, and other technologies are opening new possibilities, such as genome mining for biosynthetic gene clusters, promoting dereplication strategies, and integrating multi-omics datasets to understand natural product biosynthesis and pharmacology at the systems level. This review summarizes the recent applications of AI and ML in natural product discovery, metabolomics, cheminformatics and pharmacology, present highlighted successful case studies, associated challenges and future perspectives for AI-driven sustainable drug discovery.

The rising prevalence of diabetes necessitates accurate, noninvasive methods for early detection and personalized management. Breathomics, the investigation of exhaled volatile organic compounds (VOCs), offers a promising approach for evaluating glycemic control, oxidative stress, and metabolic alterations associated with diabetes. Specific VOCs, such as acetone, isoprene, and ethanol, reflect glucose fluctuations, lipid oxidation, and insulin sensitivity, linking metabolic changes to real‐time physiological states. Recent analytical advancements in gas chromatography–mass spectrometry, proton transfer reaction–mass spectrometry, and electronic nose technologies have enhanced the reliability and clinical applicability of breath‐based assessments. The investigations focus on integrating VOC‐based metabolic signatures with lifestyle and behavioral factors to establish a precision, noninvasive framework for diabetes management. This review also discusses key challenges that remain in standardizing breath analysis techniques, interpreting complex breath data, and implementing breath‐based technology into personalized diabetes management. Breathomics provides a novel pathway for dynamic real‐time assessment of metabolic health, bridging physiological biomarkers with lifestyle responses to enable individualized diabetes management.