Key points are not available for this paper at this time.
Bioprospecting—the search for bioactive compounds from natural sources—has been a cornerstone of drug discovery for centuries. However, traditional methods of bioprospecting are time-consuming, resource-intensive, and limited by the complexity of natural compounds and ecosystems. Artificial Intelligence (AI) is emerging as a transformative tool in this field, significantly enhancing the speed, efficiency, and accuracy of natural compound discovery. This review explores the application of AI in bioprospecting for bioactive natural products, particularly for biopharmaceutical purposes. We discuss the current AI techniques employed in bioprospecting, such as machine learning (ML), deep learning (DL), and cheminformatics, and how they are used to predict bioactivity, screen large compound libraries, and design novel bioactive molecules. AI-driven tools enable the exploration of natural products from diverse and previously inaccessible ecosystems, while also assisting in optimizing high-throughput screening processes. Furthermore, we evaluate case studies where AI has successfully identified antimicrobial, anticancer, and anti-inflammatory compounds from natural sources. However, integrating AI in bioprospecting also presents challenges, including data quality issues, model interpretability, and ethical concerns related to biodiversity conservation. Looking ahead, we explore emerging trends in AI-driven bioprospecting, including its potential to revolutionize personalized medicine and enable precision bioprospecting. We conclude by emphasizing the critical role of cross-disciplinary collaboration in leveraging AI’s capabilities to drive sustainable and efficient biopharmaceutical development, paving the way for a new era in natural product drug discovery.
Chigozie et al. (Tue,) studied this question.