Gero, a biotech company focused on aging and longevity, has conducted research demonstrating the potential of quantum computing for drug design and generative chemistry. The study, published in Scientific Reports, presents a hybrid quantum-classical machine-learning model that bridges classical and quantum computational devices to generate novel chemical structures for potential drugs, marking a significant milestone in the industry. Gero’s recent advancements, including a target discovery deal with Pfizer, have garnered attention from experts in the longevity field and paved the way for exploring the application of quantum computing in drug discovery.

The research team, composed of physics, machine learning, quantum physics, and drug design experts, developed a hybrid model combining a discrete variational autoencoder (DVAE) and a state-of-the-art quantum annealer called D-Wave. The model was trained to sample from the distribution of drug-like and synthetically accessible molecules, generating 2,331 novel chemical structures with properties resembling biologically active compounds. Notably, less than 1% of the generated molecules closely resembled those in the training set, indicating a high level of novelty in the generated compounds.

The findings suggest that quantum computing has the potential to revolutionize drug discovery by addressing the challenge of the vast and unexplored chemical diversity space. The structural complexity of drug-like molecules poses a significant computational hurdle for classical computing, making quantum computing a more efficient alternative. As quantum hardware advances, the research team anticipates transforming the hybrid model into a fully quantum generative chemistry algorithm, enabling accelerated training and more efficient drug-design applications.

In conclusion, the research demonstrates the excellent potential of hybrid quantum-classical machine learning for drug discovery. It highlights the ability to generate novel chemical structures using commercially available quantum hardware, paving the way for future advancements in drug design. Further development of quantum machine-learning models and the transition to fully quantum models hold promise for discovering transformative treatments for aging-related diseases and conditions. Collaborations between quantum computing experts, pharmaceutical companies, and medical researchers are crucial for driving progress in this field.

References

• Gircha, A. I., Boev, A. S., Avchaciov, K., Fedichev, P. O., & Fedorov, A. K. (2023). Hybrid quantum-classical machine learning for generative chemistry and drug design. Scientific Reports, 13(1), 8250. https://doi.org/10.1038/s41598-023-32703-4
• Longevity Biotech Gero Entered a Research Collaboration with Pfizer to Discover Potential Targets for Fibrotic Diseases. (2023, January 6). Pfizer; Pfizer. https://www.pfizer.com/news/press-release/press-release-detail/longevity-biotech-gero-entered-research-collaboration