Prediction of the Bioactive Potential of Moringa Oleifera Compound Using Supervised and Unsupervised Learning Approaches

Source abstract

Indonesia is recognized as one of the world’s megadiverse countries because of its rich biodiversity, including many medicinal plants such as Moringa oleifera. This plant has long been used in traditional medicine and is known to contain various bioactive compounds with potential pharmacological properties. However, the exploration and utilization of these compounds, especially those with antibiotic activity, are still limited. One major challenges in drug discovery is the identification and validation of bioactive compounds, which usually require extensive laboratory experiments, high costs, and long periods of time. In addition, conventional experimental method often depend on advanced laboratory facilities and specialized expertise. To overcome these limitations, computational approaches based on machine learning have emerged as promising alternatives for accelerating the discovery of potential drug compounds. Therefore, this study aims to develop and implement machine learning based computational methods to predict the antibiotic potential of bioactive compounds found in Moringa oleifera. The analysis applies both supervised and unsupervised learning approaches to identify molecular patterns, classify compound characteristics, and evaluate the relationships among bioactive compounds based on their structural properties. The results show that the proposed approaches can improve the prediction performance of antibiotic activity and identifying several potential candidate compounds that may act as promising antibiotic agents. Furthermore, combination supervised and unsupervised learning techniques provides deeper insights into the molecular characteristics of the compounds. These findings demonstrate that computational methods can serve as efficient and reliable strategies to support and accelerate natural product based drug discovery and development.