Drug discovery is a complex and time-consuming process that often relies on trial and error. Recent advancements in quantum computing and artificial intelligence (AI) have provided new tools to accelerate this process. In this project, we explore the application of the Variational Quantum Eigensolver (VQE) in conjunction with Graph Neural Networks (GNNs) for drug detection. The VQE algorithm is used to efficiently approximate the ground state energy of molecular systems, which is crucial for understanding molecular properties relevant to drug design. GNNs, on the other hand, are powerful AI models capable of learning complex relationships in graph-structured data, such as molecular structures. By combining these two technologies, we aim to improve the accuracy and efficiency of molecular property prediction compared to traditional methods. Our approach involves encoding molecular structures into graphs and using GNNs to extract meaningful features. These features are then fed into the VQE algorithm to predict molecular properties. We demonstrate the effectiveness of our approach on a dataset of molecular structures with known properties. Our results show that the VQE-GNN model outperforms traditional methods in terms of both accuracy and speed, highlighting the possibility of quantum computing and AI in revolutionizing drug discovery.