PHARMA- AI DRIVEN DRUG REPURPOSING PLATFORM

Abstract

Drug discovery is a time-consuming, costly, and complex process that often takes more than a decade and billions of dollars to develop a new drug. Drug repurposing, also known as drug repositioning, has emerged as a promising alternative approach that identifies new therapeutic uses for existing drugs, significantly reducing development time and cost. This project proposes PHARMA – an AI-driven drug repurposing platform that leverages advanced machine learning and deep learning techniques to accelerate the identification of potential drug-disease associations. The proposed system utilizes large-scale biomedical datasets, including gene expression profiles, drug chemical structures, protein interactions, and clinical trial data. Data preprocessing and feature extraction techniques are applied to transform raw biomedical data into meaningful representations. Machine learning algorithms such as Random Forest, Support Vector Machine (SVM), and Gradient Boosting are employed to analyze patterns, while deep learning models such as neural networks and graph-based models are used to capture complex relationships between drugs, targets, and diseases. The platform predicts potential drug candidates for specific diseases by analyzing similarity patterns, biological pathways, and molecular interactions. Additionally, natural language processing (NLP) techniques are used to extract insights from scientific literature and clinical reports. The system is evaluated using metrics such as accuracy, precision, recall, and AUC score, demonstrating improved prediction performance compared to traditional approaches. Overall, the PHARMA platform provides an efficient, scalable, and intelligent solution for drug repurposing, supporting faster drug discovery and improved healthcare outcomes.