The New Answer to Drug Discovery: Quantum Machine Learning in Preclinical Drug Development

The Research & Development (R&D) phase of drug development Drug discovery and development (D&D) is a complex and costly endeavor, typically requiring six to nine years [1] and four hundred to fourteen hundred million USD [2] for the research and development (R&D) phase alone. To transform this process, we propose a novel concept that combines Quantum-based Machine Learning network (QML) and Quantum Computing Simulation (QS) to expedite the R&D phase to three to six months and reduce the cost to merely fifty to eighty thousand USD. Our approach takes as inputs the target protein/gene structure and the primary assay [3]. For Hit Generation [3], the QML network generates potential hits [4] based on the molecular structure of the target protein, while the QS filters molecules from the primary assay according to their reaction and binding efficacy with the target protein. Then, for Lead Optimization [3], the resulting molecules from QML and QS are compared, and the ones that are common to both processes are subjected to dozens of molecular variations, while others are only modified slightly. Finally, all optimized molecules undergo multiple rounds of QS filtering with high standards for reaction efficacy and safety, producing a few dozen pre-clinical-trial-ready drugs. Our concept of QML and QS integration can also be applied to other fields, such as agricultural research, genetic editing, and aerospace engineering. Keywords: Quantum Computer, Hit to Lead, Lead Optimization Simulation, Machine Learning.