An international team of researchers have unveiled a hybrid quantum-classical model that successfully designed two promising small molecules to target a protein implicated in cancer, marking a significant step in the use of quantum computing for drug discovery. The study, published in Nature, demonstrated how combining quantum and classical computational tools could enhance the design of potential drugs for KRAS, a protein long considered difficult to target due to its structural complexity. Scientists have long been interested in targeting KRAS because it is a protein implicated in various cancers, including lung, colorectal, and pancreatic cancers. That makes it a critical target for therapeutic development. Its structural complexity and role in cell signaling, though, have historically made it challenging to inhibit effectively. In this study, researchers synthesized 15 candidate molecules, two of which showed promise as KRAS inhibitors in preliminary tests, paving the way for further development. Drug discovery is a time-intensive and costly process, often spanning over a decade and requiring billions of dollars in investment. Generative models, which use machine learning to predict new molecular structures with desired properties, have emerged as a way to navigate the vast chemical space of potential drug candidates.

Full research : Researchers have developed a hybrid quantum-classical model to design two small molecules targeting the KRAS protein, a key player in cancer biology.