Identifying new drug-like molecules for undruggable proteins — those that have proven impossible to target with conventional drugs — remains a challenge. The prevailing theory is that we have simply not explored the full chemical space to identify previously unseen molecules that could potentially target these proteins. Therefore, methods that can explore the vast chemical space (~1060 molecules) beyond the reach of conventional approaches are needed.
A collaborative research group from labs around the world has published a hybrid quantum–classical generative model for small molecule design to target the KRAS protein, which has historically been resistant to drug discovery efforts, for cancer therapy. To do this, they introduce a quantum circuit Born machine (QCBM) into a classical generative algorithm, creating a hybrid quantum–classical model. Mohammad Ghazi Vakili, a postdoctoral fellow at the University of Toronto and the lead author of the publication, explains how it works: “QCBM creates initial molecular fragments that serve as the starting token for a classical long short-term memory (LSTM) model. The LSTM then builds upon these high-quality fragments, progressively adding atoms based on the QCBM’s output. Moreover, we trained the QCBM using a local filter that we designed for this target during the first epochs, then switched to a reward system provided by Chemistry42 — a machine learning platform that assigns a score to each generated molecule — thus optimizing our quantum model for more promising ligand candidates.”