Insilico Medicine, an AI-driven drug discovery company, has demonstrated the potential advantages of using quantum generative adversarial networks (GANs) in generative chemistry. The study was published in the Journal of Chemical Information and Modeling. It was supported by University of Toronto Acceleration Consortium director Alán Aspuru-Guzik, Ph.D., and scientists from the Hon Hai (Foxconn) Research Institute.
GANs are a machine learning algorithm that can be used to generate new data similar to existing data. In drug discovery, GANs can generate new molecules with the desired properties for a particular drug target. The study found that the quantum-trained GAN could generate molecules with better properties than the classical GAN. This suggests that quantum computing could accelerate the drug discovery process.
The study is also a significant step forward in using quantum computing for drug discovery. It shows that quantum computing can train GANs to generate molecules with desired properties. This could lead to the development of new drugs that are more effective and less harmful than existing ones.