A Review of Artificial Intelligence Driven Drug Discovery Programs for Infectious Disease Management in Nigerian Healthcare

Abstract

The use of artificial intelligence in drug discovery has revamped the identification and development of therapeutic compounds for infectious diseases in Nigeria. This review analyzes the applications of machine learning algorithms and deep neural networks in accelerating drug candidate screening, with particular focus on endemic diseases including malaria, tuberculosis, and neglected tropical diseases. Recent implementations of AI platforms in Nigerian research centers have demonstrated a 60% reduction in lead optimization time and a 40% decrease in false-positive rates during initial compound screening. Neural network architectures, particularly graph neural networks and transformer models, have enabled rapid prediction of protein-ligand interactions and molecular property optimization, leading to the identification of novel antimalarial compounds with improved efficacy. Analysis of 25 AI-driven drug discovery projects in Nigeria between 2020-2024 reveals that 8 candidates have progressed to clinical trials, with three showing promising results in Phase II studies for antimalarial and antituberculosis applications. Current challenges include limited computational infrastructure, data standardization issues, and the need for expanded genomic databases of local pathogen strains. Despite these limitations, AI-enhanced drug discovery platforms have reduced the average time from target identification to lead compound selection from 24 months to 9 months in Nigerian research settings, while decreasing associated costs by approximately 45%. These technologies suggest a paradigm shift in addressing infectious disease burden through AI-augmented pharmaceutical research in resource-limited settings