A Systematic Review of Computational Innovations for Drug Discovery Against Diphtheria in Nigeria

Abstract

This systematic review explores the impact of computational innovations in drug discovery aimed at combating diphtheria in Nigeria. Diphtheria remains a significant health concern in less developed regions, where traditional drug discovery methods often face challenges of inefficiency and high costs. This review highlights the potential of advanced computational techniques, such as Computer-Aided Drug Design (CADD) and Ligand-Based Drug Design (LBDD), as transformative, cost-effective solutions. By systematically analyzing data from Chembl and PubChem databases, this study applies machine learning algorithms to predict bioactivity of compounds targeting the diphtheria toxin. The findings suggest that computational tools, including machine learning models, can significantly enhance the identification and development of effective treatments for diphtheria, thereby alleviating some of the burden on local healthcare systems. Additionally, this review identifies existing gaps in current research and suggests future directions, emphasizing the need for specialized training and standardized protocols in computational drug design to optimize the efficacy of these innovative approaches.