Recent Papers

The traditional drug discovery process is costly, time-intensive, and prone to high failure rates, often taking over a decade to develop a new medication. Drug repurposing, which involves identifying new therapeutic uses for existing drugs, offers a promising strategy to accelerate drug development and reduce costs. However, conventional repurposing approaches are limited by their dependence on clinical observations and experimental screenings. Recent advancements in artificial intelligence (AI) and machine learning (ML) have introduced data-driven methodologies capable of analyzing vast biomedical datasets, predicting drug-target interactions, and identifying potential therapeutic candidates.Despite these advancements, AI-driven drug repurposing faces significant challenges, including data heterogeneity, model interpretability, limited availability of high-quality labelled data, and the need for experimental validation of AI-generated predictions. This study explores AI-based strategies for drug repurposing, focusing on deep learning models, graph-based drug-target interaction predictions, and natural language processing (NLP) techniques for analyzing biomedical literature. Additionally, it addresses key challenges such as model explainability, generalizability, and data biases while proposing solutions to enhance AIs efficiency in expediting drug discovery and improving clinical outcomes.

Copyright © 2025 Jasshan Bhalgat. This is an open access article distributed under the Creative Commons Attribution License.