AI-Driven Drug Design MVP Integrating DEEPScreen and Related Tools

Drug discovery is a complex, time-consuming, and costly process, often taking over a decade and billions of dollars to bring a new drug to market. Recent advances in artificial intelligence (AI) and deep learning (DL) have enabled significant improvements in early-stage drug-target interaction (DTI) prediction, reducing both time and cost . This paper presents a Minimum Viable Product (MVP) framework integrating ligand-based deep learning approaches, such as DEEPScreen, with structure-based virtual screening using GNINA and AutoDock Vina. The proposed system enables researchers to quickly match candidate small molecules with protein or enzyme targets, facilitating hit identification and prioritization. We discuss model architectures, dataset preparation, integration strategies, and potential applications in academic and industrial drug discovery settings.