Quantum Computing in Drug Discovery

Abstract

The drug discovery process has always been a problem for the pharmaceutical industry’s low rates of success, high expenses, and long-time frames. Quantum computing (QC) is being touted as a revolutionary advancement because of its unparalleled speed to carry out intricate multi molecular simulation and optimization. Unfortunately, its practical use has been suppressed due to the absence of proper hardware and the integration problems with traditional systems. Our solution is a quantum-classical pipeline for drug discovery. This pipeline utilizes machine learning (ML) for protein-ligand binding, drug property optimization, and even de novo drug design. In this paper we describe the pipeline, its components, the way it operates using NISQ devices, and the improvements it has in terms of accuracy and scalability (93.5% vs 78.2%) when compared with classical methods. Finally, we summarize how this can aid in modern drug discovery. It could significantly decrease the cost and timeline for pharmaceutical innovations.